ArticlePDF Available

ChatGPT impacts on access-efficiency, employment, education and ethics: The socio-economics of an AI language model

Authors:
  • Caleb University Imota Lagos Nigeria
  • Pan Atlantic University
  • Babcock University, Ilishan-Remo, Nigeria.

Abstract and Figures

Generative artificial intelligence (AI) models, such as ChatGPT, have gained significant attention in various fields, including healthcare, education, and industry. This article aims to provide an overview of the impacts of ChatGPT on access, efficiency, jobs, and education, using technological determinism theory and social construction of technology theory as frameworks. The study highlights the potential benefits of ChatGPT in healthcare, education, and business, emphasizing the need for ethical considerations and human oversight. It acknowledges the limitations of ChatGPT in understanding context and tone and stresses the importance of ethical guidelines and best practices. The impact on the labor market and industries depends on how ChatGPT is socially constructed and used, with possibilities of job displacement and creation of new opportunities. In education, ChatGPT can enhance personalized learning, student engagement, and critical thinking skills, but accuracy, reliability, and ethical implications must be addressed. Policy recommendations include implementing ethical guidelines, maintaining human involvement, investing in training and reskilling programs, balancing human judgement and machine learning in education, considering the impact on the labor market, and addressing social and cultural implications. Collaboration with experts in AI, ethics, education, labor market analysis, and social and cultural studies is essential in developing comprehensive guidelines and policies for responsible use of ChatGPT.
Content may be subject to copyright.
BizEcons Quarterly (2023) 16: 1-17
© Strides Educational Foundation ISSN: 2695-2246
1,3 School of Management and Social Sciences, Pan Atlantic University, Lagos, Nigeria. olaniyievans@gmail.com
2 Dept. of Finance, Babcock University, Nigeria.
4 McPherson University, Ogun State, Nigeria.
5 Dept. of Economics, Trinity University, Yaba, Lagos.
6 W. Frank Barton School of Business, Wichita State University, Kansas, USA.
ChatGPT impacts on access-efficiency, employment, education and ethics:
The socio-economics of an AI language model
Olaniyi Evans1 Olawale Wale-Awe2 Osuji Emeka3
Olawale O. Ayoola4 Raymond Alenoghena5 Sesan Adeniji6
Received: 2 December 2022 / Accepted: 5 August 2023
This paper and more can be downloaded for free from https://bizecons.5profz.com/
Abstract
Generative artificial intelligence (AI) models, such as ChatGPT, have gained significant attention in various fields, including
healthcare, education, and industry. This article aims to provide an overview of the impacts of ChatGPT on access, efficiency,
jobs, and education, using technological determinism theory and social construction of technology theory as frameworks. The
study highlights the potential benefits of ChatGPT in healthcare, education, and business, emphasizing the need for ethical
considerations and human oversight. It acknowledges the limitations of ChatGPT in understanding context and tone and
stresses the importance of ethical guidelines and best practices. The impact on the labor market and industries depends on
how ChatGPT is socially constructed and used, with possibilities of job displacement and creation of new opportunities. In
education, ChatGPT can enhance personalized learning, student engagement, and critical thinking skills, but accuracy,
reliability, and ethical implications must be addressed. Policy recommendations include implementing ethical guidelines,
maintaining human involvement, investing in training and reskilling programs, balancing human judgement and machine
learning in education, considering the impact on the labor market, and addressing social and cultural implications.
Collaboration with experts in AI, ethics, education, labor market analysis, and social and cultural studies is essential in
developing comprehensive guidelines and policies for responsible use of ChatGPT.
Keywords: ChatGPT, access, efficiency, employment, education, ethics
1 Introduction
The development of generative artificial intelligence (AI) models, such as ChatGPT, has garnered considerable attention across
various fields, particularly healthcare, education, and industry. ChatGPT is a natural language processing model that uses
machine learning algorithms to generate human-like responses to user input. Its advanced language-modeling capabilities
have been shown to enhance access to information, increase productivity, and streamline communication in various fields
(Hopkins et al., 2023; Mattas, 2023). However, the increased use of ChatGPT and similar models has raised ethical and
economic concerns regarding job displacement, privacy, and accountability (Zarifhonarvar, 2023).
In the healthcare sector, ChatGPT has the potential to revolutionize patient care and access to information. According to
Hopkins et al. (2023), ChatGPT can serve as an intelligent chatbot to provide patients with accurate and reliable information
regarding their conditions, treatment options, and clinical trials. Some authors suggest that ChatGPT can improve patient
satisfaction and reduce the burden on healthcare providers by automation of routine tasks. In the education sector, ChatGPT
has been shown to enhance the learning experience by provision of personalized and adaptive feedback to students (Baidoo-
Anu & Owusu Ansah, 2023). ChatGPT can also support teachers by provision of automated grading and feedback on student
work, freeing up more time for instructional planning and creative activities. In industry, ChatGPT and similar models are
expected to affect employment by automation of routine tasks, which can lead to job displacement (Felten et al., 2023).
However, the impact of ChatGPT on employment remains uncertain, and some researchers suggest that it can create new job
opportunities in areas such as AI development, data analytics, and ethics (Zarifhonarvar, 2023).
Relying on technological determinism theory and social construction of technology theory, this literature review paper aims to
therefore provide an overview of impacts of ChatGPT on access, efficiency, jobs and education, as well as identify gaps in
existing research and future directions for research in this area. By following rigorous methodology, the literature review
provides a comprehensive overview of current state of research on impacts of ChatGPT.
2 EVANS ET AL.
The justification for this literature review is based on the growing interest in the use of chatbots powered by AI technology like
ChatGPT in various industries and sectors. Potential benefits of ChatGPT have been documented in healthcare (Hopkins et al.,
2023; Sallam, 2023), higher education (Firaina & Sulisworo, 2023; Baidoo-Anu & Owusu Ansah, 2023), ophthalmology
(Antaki et al., 2023), libraries and academia (Lund & Wang, 2023), and labor market (Zarifhonarvar, 2023). Thus, this
literature review aims to provide a comprehensive and up-to-date understanding of the potential impacts of ChatGPT on
various sectors and industries.
Furthermore, the significance of this study lies in its comprehensive overview of the current state of research on the use of
ChatGPT in various fields. The review explores the potential benefits and drawbacks of ChatGPT in different contexts, including
healthcare education and research (Sallam, 2023), higher education (Firaina & Sulisworo, 2023; Baidoo-Anu & Owusu Ansah,
2023), and libraries (Lund & Wang, 2023), among others. It also examines economic impact of ChatGPT on different industries
and occupations. The review, therefore, provides valuable insights into the potential of ChatGPT to revolutionize access and
efficiency in different fields (e.g., education), as well as identify knowledge gaps and future research directions.
2 Theoretical Framework
Technological determinism theory argues that technology drives societal change, and individuals have limited control over the
direction of this change. According to Marshal McLuhan, a prominent technological determinist, the impact of technology is
"all-encompassing and thorough in the way it shapes and structures society" (Azam et al., 2020, p. 134). This perspective
suggests that the development and implementation of technology have a significant impact on society and its institutions,
including education, work, and communication (Evans, 2022; Evans & Mesagan, 2022; Evans & Oni, 2022; Guevara, 2022;
Adeola & Evans, 2022; Adeola et al., 2023; Evans, 2023). For example, Guevara's (2022) study of television journalists during
COVID-19 pandemic illustrates how the sudden shift to remote work and use of digital tools for reporting was a result of
technological determinism. Journalists had to adapt to new technologies and ways of working to continue the production of
content, which underscores how technology influences professional practices.
In the context of ChatGPT, technological determinism theory may be applied to argue that the introduction of an AI language
model will have a profound impact on access, efficiency, jobs, and education, regardless of individuals' agency. This theory
suggests that technology has potential to revolutionize various fields, such as healthcare, education, public health, tourism,
and business. However, this also suggests that there are potential negative consequences, such as impact on employment and
data privacy. This theory suggests that the development and implementation of ChatGPT should be guided by a thorough
analysis of its potential impacts, both positive and negative.
Technological determinism theory has, however, been criticized for oversimplifying complex relationship between technology
and society. Diniasti and Haqqu's (2022) analysis of documentary film "The Social Dilemma" demonstrates that reception of
technological determinism among teenagers is not straightforward. While some participants believed that technology has a
deterministic effect on society, others highlighted the role of human agency in technology and its impact.
Therefore, social context and individuals' interpretations of technology play a significant role in its impact on society. This
perspective is consistent with social construction of technology theory, a sociological approach that emphasizes how
technological innovation is shaped by social processes and not just by technological determinism. According to Kwok and Koh
(2021), social construction of technology theory emphasizes the study of social context in which technological innovation takes
place, particularly social values, norms, and power dynamics. This approach acknowledges that design, development, and use
of technology are not neutral, but rather, are shaped by social actors who hold different interests, values, and perspectives.
For example, Varney and May (2021) explored social construction of cross-reality technologies in learning, applying social
construction of technology theory. They found that adoption and use of cross-reality technologies in learning are shaped by
social factors such as educational policies, instructional practices, and user perceptions. They argued that social construction
of technology theory can help identify ways in which social context shapes design, development, and use of new educational
technologies, and can provide insights into how to design technologies that better align with the needs and goals of different
stakeholders.
In the context of ChatGPT, this theory suggests that technology's impact on society is not solely determined by its intrinsic
properties, but is also influenced by societal and cultural factors (e.g., norms and values of organizations and individuals who
use it). This theory suggests that the implementation of ChatGPT should be accompanied by a thorough analysis of social and
cultural context in which it will be used; also the development and implementation of technology should be guided by needs
and values of users. Overall, technological determinism provides a useful framework for analyzing the impact of ChatGPT on
society, but it should be considered in conjunction with other theoretical perspectives, such as social construction of technology
theory to fully understand the complex relationship between technology and society.
3 Methodology
The study employs a literature review approach to synthesize relevant literature on the impacts of ChatGPT on access,
efficiency, jobs, and education. This methodology is suitable for the research objectives, as it will enable identification and
analysis of extant knowledge and best practices in the field (Creswell, 2014). In line with Peters et al. (2020), this approach
BIZECONS QUARTERLY 3
will allow us to systematically search for and screen relevant studies, particularly both quantitative and qualitative research
designs, grey literature, and expert opinions. The inclusion criteria will focus on studies that explore impacts of ChatGPT on
access, efficiency, jobs, and education, published in English language journals from 2022 to 2023.
The initial step in this study involves conduct of a comprehensive review of academic and professional literature related to the
impacts of ChatGPT on access, efficiency, jobs, and education. The review includes journal articles, books, reports, and other
relevant sources, guided by research objectives; the sources are selected based on their relevance to research objectives (Grant
and Booth, 2009; Creswell, 2014). The literature review is conducted via databases such as Google Scholar, JSTOR, and
ProQuest.
We follow the guidelines proposed by Snyder (2019) and Paul and Criado (2020) for writing a comprehensive literature review.
This includes the synthesis of key findings from included studies, critical evaluation of quality and limitations of research, and
identification of future research directions. These rigorous methodology guidelines provide a comprehensive overview of
current state of research on the impacts of ChatGPT on access, efficiency, jobs, and education, and help identify knowledge
gaps and future research directions.
According to Grant and Booth (2009), an appropriate sample size for a literature review will depend on the research questions,
scope of review, and available resources. For this study, the appropriate sample size for the literature is determined by a
preliminary search to identify the number of relevant studies or articles. 74 articles are identified through a database search
and by review of reference lists of key articles on the topic. This sample size is justified based on fact that studies identified are
of high quality and provide rich and relevant data that address research questions (Bettany-Saltikov, 2010).
According to Fink (2014), there are several sampling techniques that can be used in a literature review, particularly
convenience sampling, random sampling, stratified sampling, and purposive sampling. This study adopts purposive sampling
because it involves selection of studies based on their relevance to research objectives, as determined by researchers expertise
and knowledge of field (Fink, 2014). In this study, purposive sampling is accomplished through various methods, for example,
the use of specific keywords to search for relevant studies in databases (e.g., PubMed or Google Scholar). The researchers then
screens the studies based on their relevance to research objectives.
4 ChatGPT Impacts on Access-efficiency
Existing studies cover a wide range of topics related to the ChatGPT impacts on access/efficiency, as shown in Table 1. The
different studies on ChatGPT reveal its potential to transform efficiency in various fields such as education, healthcare,
journalism, and research. One common thread is the potential of ChatGPT to revolutionize access to information. Hopkins et
al. (2023), for example, highlight how ChatGPT can provide cancer patients with 24/7 access to information, support, and
advice; such leads to improvement in their quality of life. Zuccon and Koopman (2023) reported that prompt information
significantly improved accuracy of ChatGPT's answers in health-related questions. Similarly, Noy and Zhang (2023) suggest
that the use of generative AI can increase productivity in certain tasks, such as brainstorming and idea generation. Gabrielson
et al. (2023) found that ChatGPT showed promise in improving efficiency of urologists by reduction of documentation time
and provision of clinical decision support. The findings suggest that the use of ChatGPT to access various fields such as
healthcare, education, and business can have both positive and negative implications. From the perspective of technological
determinism theory, the introduction of ChatGPT can lead to a paradigm shift in healthcare, education, and business which
can lead to the improvement of patients' quality of life by provision of 24/7 access to information, support, and advice. The
increasing use of ChatGPT and similar models therefore has significant potential to impact various fields, including healthcare,
education, and industry.
ChatGPT has had a significant impact on access and efficiency in various industries, particularly customer service, healthcare,
and e-commerce. As a large language model, ChatGPT can be integrated into chatbots and virtual assistants, which can provide
customers with instant and personalized support and information. This not only improves customer satisfaction but also
increases the efficiency of customer service operations. The fact that ChatGPT can handle multiple requests simultaneously
reduces the need for human support agents. ChatGPT can also be used to automate routine and repetitive tasks (e.g., data entry
and scheduling) which further improves operational efficiency.
Moreover, ChatGPT can improve access to information and services for individuals with disabilities or language barriers. For
example, ChatGPT can be used to develop speech-to-text and text-to-speech tools, which make it easier for individuals with
hearing or speech impairments to communicate and access information. Similarly, ChatGPT can be used to develop translation
tools that can assist non-native speakers of a language to understand and communicate in a foreign language. In this way,
ChatGPT can help break down linguistic barriers and promote equal access to information and services.
Table 1. ChatGPT Impacts on Access-efficiency
Authors/date
Research
objectives/questions
Methodology
Results/implications
Hopkins et al.
(2023)
To examine the impact of
ChatGPT on cancer
Literature review
The use of ChatGPT in providing information to
cancer patients represents a paradigm-shift in
healthcare. It can provide 24/7 access to
4 EVANS ET AL.
patients' access to
information.
information, support, and advice, thus improving
patients' quality of life.
Lund and Wang
(2023)
To explore how AI and
GPT could impact
academia and libraries.
Literature review
ChatGPT can enhance information access and
retrieval, personalization, and efficiency in
academic and library settings. However, it also
poses ethical concerns, such as privacy, bias, and
control over data.
Biswas (2023)
To explore the role of
ChatGPT in public health.
Literature review
ChatGPT can be used to analyze health-related
data, generate patient-specific recommendations,
and provide mental health support. However, it
also raises concerns about data privacy, security,
and bias.
Abdullah et al.
(2022)
To provide an overview of
ChatGPT fundamentals,
applications, and social
impacts.
Literature review
ChatGPT has various applications in natural
language processing, chatbots, language
translation, and creative writing. It can also have
social impacts, such as employment disruption,
information control, and ethical concerns.
Noy and Zhang
(2023)
To investigate the
productivity effects of
generative AI, including
ChatGPT.
Lab experiment
The use of generative AI can increase productivity
in certain tasks, such as brainstorming and idea
generation. However, it can also lead to
overreliance, reduced creativity, and biased
outputs.
Carvalho and
Ivanov (2023)
To explore the
applications, benefits, and
risks of using ChatGPT for
tourism.
Literature review
ChatGPT has the potential to revolutionize the
tourism industry, but ethical and privacy concerns
must be addressed.
George and
George (2023)
To review the impact of
ChatGPT AI on several
business sectors.
Literature review
ChatGPT has the potential to improve business
processes and outcomes, but careful consideration
of ethical and privacy concerns is necessary.
Chen (2023)
To examine the possible
impact of ChatGPT on
library reference services.
Literature review
ChatGPT can enhance library reference services by
providing quick and accurate responses to user
queries, but librarians must ensure ethical and
privacy concerns are addressed.
Lund et al. (2023)
To investigate the impact
of ChatGPT on scholarly
publishing and the ethics
of large language models.
Literature review
The use of ChatGPT in scholarly publishing raises
concerns around authorship, transparency, and
bias, which must be addressed through ethical
guidelines and best practices.
Patel and Lam
(2023)
To explore the potential of
using ChatGPT for
discharge summaries.
Literature review
ChatGPT can improve the accuracy and efficiency
of discharge summaries, but ethical and privacy
concerns must be addressed.
Doshi et al.
(2023)
To examine the potential
negative impacts of
ChatGPT on healthcare.
Opinion piece
The use of ChatGPT in healthcare can lead to
dehumanization, loss of autonomy, and biases,
which must be addressed through ethical
guidelines and best practices.
Kalla and Smith
(2023)
To analyze the impact of
ChatGPT on various fields
of study
Literature review
and analysis of
various studies
ChatGPT has a significant impact on various
fields, such as healthcare, education, business, and
finance. The analysis also identified potential risks
and limitations of ChatGPT in some areas, such as
bias and ethical issues.
Alshurafat (2023)
To examine the usefulness
and challenges of ChatGPT
for accounting
professionals
Literature review
and analysis of
previous studies and
case studies
ChatGPT can be useful in automating repetitive
and time-consuming accounting tasks, but there
are challenges, such as technical limitations,
privacy and security concerns, and the need for
human oversight. Accounting professionals should
also be trained to effectively use ChatGPT to
optimize its benefits.
Haleem et al.
(2023)
To study the features,
abilities, and challenges of
ChatGPT as a support tool
in various domains
Literature review
and analysis of
previous studies,
surveys, and case
studies
ChatGPT has several useful features and abilities,
such as generating human-like responses and
assisting with tasks such as customer service and
medical diagnosis. However, there are challenges
such as technical limitations, ethical concerns, and
the need for human oversight. The study also
identified potential applications of ChatGPT in
BIZECONS QUARTERLY 5
various domains such as healthcare, education,
and finance.
Liebrenz et al.
(2023)
To explore the ethical
challenges of using
ChatGPT for generating
scholarly content in
medical publishing.
Conceptual study
The use of ChatGPT in medical publishing raises
ethical concerns around authorship, transparency,
and bias, which must be addressed.
To explore the impact of
ChatGPT and large
language models on
nuclear medicine.
Literature review,
expert opinions
ChatGPT and LLMs have the potential to improve
accuracy and efficiency in nuclear medicine.
However, there are concerns about bias and the
need for human oversight.
To provide a
multidisciplinary
perspective on the
opportunities, challenges,
and implications of
ChatGPT and generative
conversational AI.
Literature review,
expert opinions
ChatGPT and generative conversational AI have
the potential to revolutionize various industries
and fields, but there are also concerns about
ethics, privacy, and the need for human oversight.
Collaboration between experts from various
disciplines is needed to fully understand and
harness their potential.
Gabrielson et al.
(2023)
To evaluate the potential of
ChatGPT to improve the
efficiency of urologists.
Retrospective
analysis of patient
data, survey
ChatGPT showed promise in improving efficiency
by reducing documentation time and providing
clinical decision support.
Wang et al.
(2023)
To investigate whether
ChatGPT can write an
effective Boolean query for
systematic review
literature search
A dataset of 1,000
systematic review
queries and
comparison of
ChatGPT with
baseline methods
(BM25 and
BM25+BERT).
The study found that ChatGPT performed
comparably to the baseline methods on the MAP
metric and outperformed them on the recall
metric. ChatGPT showed potential as an effective
tool for generating Boolean queries for systematic
review literature search.
Zuccon and
Koopman (2023)
To investigate how prompt
knowledge impacts health
answer correctness when
using ChatGPT as a
conversational agent
Evaluated ChatGPT's
performance in
answering health-
related questions.
The evaluation
metrics used were
accuracy, mean
reciprocal rank
(MRR), and
normalized
discounted
cumulative gain
(NDCG).
The study found that prompt information
significantly improved the accuracy of ChatGPT's
answers. ChatGPT's performance was better on
the high-quality answer dataset than on the
Google search result dataset. The study also found
that MRR and NDCG were useful evaluation
metrics for assessing the quality of ChatGPT's
answers. The study highlights the importance of
prompt information when using conversational
agents for health-related questions.
Antaki et al.
(2023)
To evaluate the
performance of ChatGPT in
ophthalmology and analyze
its successes and
shortcomings.
Retrospective study
using a dataset of
medical
consultations with
10 ophthalmologists
and ChatGPT.
The study found that ChatGPT was able to provide
accurate information in ophthalmology and had a
high degree of success in responding to patient
inquiries. However, it also showed limitations in
some areas, such as understanding the context and
tone of the conversation. The study suggests that
ChatGPT can be a useful tool for ophthalmology,
but its limitations need to be considered in clinical
practice.
Mathew (2023)
To investigate if ChatGPT
is a world changer and how
it can impact different
areas.
Case study
The case study highlights the potential of ChatGPT
in transforming different fields, such as education,
healthcare, and journalism. It also discusses the
ethical concerns associated with the use of
ChatGPT, such as biases and data privacy. The
study concludes that ChatGPT has the potential to
revolutionize the world, but its responsible use
needs to be ensured.
Verma (2023)
To examine the impact of
ChatGPT on traditional
library management.
Case study,
interviews, survey
ChatGPT improved the efficiency of the library
system by reducing response time and increasing
accessibility.
6 EVANS ET AL.
5 ChatGPT Impacts on Employment
The literature has shown that ChatGPT has the potential to significantly impact labor market and various industries (see Table
2). Felten et al. (2023) predict that technology will lead to job displacement in some sectors while creating new job
opportunities in others; policymakers should prepare for these changes. Zarifhonarvar (2023) finds similar results through
econometric analysis, with emphasis on the need for upskilling and reskilling programs to help workers transition into new
roles. However, Lahvis (2023) argues that the introduction of ChatGPT is likely to exacerbate extant inequalities in labor
market; policymakers should work to ensure that its benefits are distributed equitably. Tiwary (2023) finds that while most
people had a positive view of AI and ChatGPT, concerns were raised about job displacement and ethical considerations.
The social construction of technology theory suggests that ChatGPT's impact on labor market and various industries will
depend on how it is socially constructed and used. While some researchers predict job displacement in some sectors, others
emphasize potential for creating new job opportunities and need for upskilling and reskilling programs to help workers
transition to new roles. Additionally, Lahvis argues that policymakers must ensure that ChatGPT's benefits are distributed
equitably to avoid exacerbating existing inequalities in labor market. Therefore, how society constructs and uses ChatGPT will
determine its impact and whether its benefits are distributed equitably.
As a large language model, ChatGPT has had significant impacts on employment, particularly in the field of natural language
processing and artificial intelligence. The development of such models has led to increased demand for skilled professionals
in these areas, particularly software engineers, data scientists, and linguists. Further, the use of ChatGPT in various industries,
such as healthcare, finance, and e-commerce, has led to the creation of new job roles and opportunities. Companies now seek
individuals with experience in natural language processing to develop and implement ChatGPT-based solutions that can
improve business operations, enhance customer experience, and increase productivity.
On the other hand, the use of ChatGPT and other large language models has also raised concerns about the potential
displacement of human workers. As these models become increasingly sophisticated, they have the potential to replace certain
jobs that involve human language processing, such as customer service representatives, content writers, and translators.
However, it is important to note that while ChatGPT can automate certain tasks, it cannot fully replace human intelligence,
creativity, and empathy. Instead, the use of ChatGPT can free up human workers from mundane and repetitive tasks, allowing
them to focus on more complex and higher-value work that requires critical thinking and problem-solving skills. Therefore,
while there may be some short-term displacement of jobs, the long-term impacts of ChatGPT on employment may lead to the
creation of new and more meaningful job opportunities.
Table 2. Related literature on ChatGPT Impacts on employment
Authors/Date
Research
Objectives/Questions
Methodology
Felten et al.
(2023)
To explore the impact of
language models such as
ChatGPT on industries and
occupations
Literature
review and
expert opinions
Zarifhonarvar
(2023)
To analyze the labor market
impacts of ChatGPT from an
economic perspective
Econometric
analysis and
literature review
Salah et al.
(2023)
To investigate the impact of
ChatGPT on psychological
well-being, with a focus on
harmful stereotypes and job
anxiety as moderators
Experimental
study with pre-
and post-
intervention
surveys
Lahvis (2023)
To explore the implications
of ChatGPT for labor and
employment
Literature
review and
expert opinions
Taecharungroj
(2023)
To analyze public reactions
to ChatGPT on Twitter
Social media
analysis and
sentiment
analysis
BIZECONS QUARTERLY 7
Aljanabi (2023)
To discuss potential future
directions and applications of
ChatGPT
Literature
review and
expert opinions
Atlas (2023)
To explore the potential of
ChatGPT in higher education
and professional
development
Literature
review
Homolak (2023)
To analyze the opportunities
and risks of ChatGPT in
medicine, science, and
academic publishing
Literature
review
Tiwary (2023)
To examine the opinions of
netizens, academicians, and
information professionals
about AI, with a special
reference to ChatGPT
Online survey
Zarifhonarvar,
(2023)
To examine the potential
economic impact of ChatGPT
on the labor market.
Literature
review,
economic
analysis
6 ChatGPT Impacts on Education
The impact of ChatGPT on education has been a topic of interest for researchers in different fields (see Table 4). A systematic
review by Sallam (2023) highlighted the potential of ChatGPT in healthcare education, research, and practice; however
concerns about its impact on patient privacy, security, and trust need to be addressed. In contrast, Baidoo-Anu and Owusu
Ansah (2023) conducted a literature review and identified potential benefits of ChatGPT in promoting teaching and learning
in education. ChatGPT has the potential to enhance personalized learning, encourage student engagement, and facilitate the
development of critical thinking skills.
Other researchers have also discussed the potential of ChatGPT in enhancing specific fields, such as science education (Cooper,
2023), medical education (Eysenbach, 2023; Hisan and Amri, 2023), foreign language teaching and learning (Hong, 2023),
and tourism education (Ivanov and Soliman, 2023; Skavronskaya et al., 2023). Kalla and Smith (2023) find that ChatGPT can
enhance research capabilities in various fields, while Atlas (2023) suggests that it can be used for personalized learning,
training, and professional development.
ChatGPT has had significant impacts on education, particularly in the areas of language learning and personalized education.
As a large language model, ChatGPT has the ability to generate natural language responses to a wide range of questions and
prompts, which makes it a valuable tool for language learners. ChatGPT can provide instant feedback, explanations, and
examples. This way it helps learners to improve their grammar, vocabulary, and comprehension. ChatGPT can also be used to
create interactive and engaging learning experiences (e.g., chatbots and virtual assistants), that can personalize the learning
process and adapt to the needs and preferences of individual learners.
Moreover, ChatGPT can also enhance the accessibility and inclusivity of education by provision of support for students with
disabilities or language barriers. For example, ChatGPT can be used to develop speech-to-text and text-to-speech tools, which
make it easier for students with hearing or speech impairments to participate in class. Similarly, ChatGPT can be used to
develop translation tools that can assist non-native speakers of a language to understand and communicate in a foreign
language. In this way, ChatGPT can help to break down linguistic barriers and promote equal access to education for all
students.
Table 3. Related literature on ChatGPT impacts on education
Authors/Date
Research
Objectives/Questions
Methodology
Results/Implications
Sallam (2023)
To review the utility of
ChatGPT in healthcare
education, research, and
practice and identify valid
concerns
Systematic
review
ChatGPT can provide promising perspectives for
healthcare education, research, and practice, but valid
concerns about its impact on patient privacy, security, and
trust need to be addressed.
8 EVANS ET AL.
Baidoo-Anu,
and Owusu
Ansah (2023)
To understand the
potential benefits of
ChatGPT in promoting
teaching and learning in
education
Literature review
ChatGPT has the potential to enhance personalized
learning, encourage student engagement, and facilitate
the development of critical thinking skills in education.
Arif et al. (2023)
To discuss the potential
impact of ChatGPT on
medical education and
research.
Literature review
ChatGPT can enhance medical education by providing
interactive simulations, adaptive learning, and
personalized feedback. It can also facilitate medical
research by analyzing large datasets and generating
hypotheses. However, it also raises ethical concerns about
patient privacy, data quality, and accountability.
Teng (2023)
To investigate the role of
ChatGPT in scientific
writing, reviewing, and
editing for open-access
TESOL journals.
Case study
ChatGPT can assist non-native English-speaking authors
in improving their writing, especially in terms of grammar
and syntax. However, it cannot replace human editors in
terms of language style, logic, and content accuracy.
Alkhaqani
(2023)
To identify the challenges
and opportunities of
using ChatGPT in nursing
education
Literature review
ChatGPT can provide opportunities for nursing education
such as enhancing clinical decision-making and
promoting critical thinking. However, challenges such as
lack of resources and limited access to technology need to
be addressed.
Zhai (2022)
To explore ChatGPT user
experience and its
implications for education
Survey
ChatGPT has the potential to enhance student
engagement and learning experience in education, but
privacy concerns need to be addressed.
Jalil etal. (2023)
To examine the promises
and perils of ChatGPT in
software testing
education
Survey
ChatGPT can provide opportunities for software testing
education such as enhancing student engagement and
automating repetitive tasks. However, concerns about
accuracy and security need to be addressed.
Ivanov and
Soliman (2023)
To explore the
implications of ChatGPT
for tourism education and
research
Literature review
ChatGPT can enhance personalized learning and provide
opportunities for research in tourism education. However,
ethical and privacy concerns need to be addressed.
Hong (2023)
To examine the impact of
ChatGPT on foreign
language teaching and
learning
Literature review
ChatGPT has the potential to enhance foreign language
teaching and learning by providing personalized feedback
and enhancing communication skills. However, concerns
about the lack of human interaction need to be addressed.
Farrokhnia et al.
(2023)
To conduct a SWOT
analysis of ChatGPT and
identify implications for
educational practice and
research
SWOT analysis
ChatGPT has strengths such as enhancing personalized
learning and weaknesses such as accuracy and security
concerns. Opportunities include promoting critical
thinking and threats include lack of human interaction.
Educational institutions need to address these factors to
effectively incorporate ChatGPT in education.
Cooper (2023)
To examine the potential
of ChatGPT to enhance
science education
Qualitative
research design:
exploratory case
study
ChatGPT has the potential to enhance science education
by providing personalized learning experiences,
facilitating discussion and collaboration, and improving
student engagement. However, there are also concerns
about the accuracy and reliability of the information
generated by ChatGPT, as well as the ethical implications
of using AI in education.
Eysenbach
(2023)
To explore the role of
ChatGPT, generative
language models, and
artificial intelligence in
medical education
Opinion piece
ChatGPT has potential in medical education for
enhancing clinical reasoning skills, facilitating the
creation of medical case studies, and improving patient
communication. However, concerns exist regarding the
accuracy and ethics of using AI in medicine, and the need
to balance human judgement and machine learning.
Skavronskaya et
al. (2023)
Does ChatGPT have the
potential to enhance
tourism education
Opinion piece
ChatGPT has the potential to enhance tourism education
by providing students with a personalized learning
experience, facilitating language learning and cultural
exchange, and improving student engagement. However,
there are concerns about the potential impact of AI on
employment in the tourism industry, as well as the ethical
implications of using AI in education.
BIZECONS QUARTERLY 9
Malinka et al.
(2023)
To examine the potential
of ChatGPT in higher
education
Qualitative
research design:
exploratory case
study
ChatGPT has potential in higher education for facilitating
personalized learning experiences, improving student
engagement, and enhancing the efficiency of assessment
processes. However, concerns exist regarding the accuracy
and reliability of the information generated by AI, as well
as the ethical implications of using AI in education.
Hisan and Amri
(2023)
To explore the potential
of ChatGPT in medical
education
Opinion piece
ChatGPT has the potential to enhance medical education
by facilitating personalized learning experiences,
improving clinical reasoning skills, and enhancing the
efficiency of medical case studies. However, concerns exist
regarding the accuracy and ethics of using AI in medicine,
and the need to balance human judgement and machine
learning.
Rudolph et al.
(2023)
To examine the potential
of ChatGPT in higher
education
Opinion piece
ChatGPT has the potential to enhance higher education by
facilitating personalized learning experiences, improving
student engagement, and enhancing the efficiency of
assessment processes. However, concerns exist regarding
the accuracy and reliability of the information generated
by AI, as well as the ethical implications of using AI in
education.
Tlili et al. (2023)
To explore the potential
of ChatGPT in higher
education
Qualitative
research design:
case study
ChatGPT has potential in education for enhancing student
engagement, improving language learning and
communication skills, and facilitating personalized
learning experiences. However, concerns exist regarding
the accuracy and reliability of the information generated
Kasneci et al.
(2023)
To examine the
opportunities and
challenges of ChatGPT for
education
Literature review
and critical
analysis
ChatGPT can support personalized and adaptive learning,
enhance student engagement, and facilitate content
creation. However, there are also concerns about potential
biases, data privacy, and ethical considerations.
Talan and
Kalinkara
(2023)
To evaluate the use of
ChatGPT as an
assessment tool for an
anatomy course
Experimental
study with 20
participants
ChatGPT achieved 80% accuracy in grading anatomy
essays, which is comparable to human graders. However,
it also highlighted the importance of designing
appropriate prompts and providing clear instructions for
students.
Bishop (2023)
To discuss the
implications of ChatGPT
for education, research,
and writing
Literature review
and critical
analysis
ChatGPT can facilitate writing and research tasks, but it
also raises questions about authorship, intellectual
property, and authenticity. Moreover, it can reinforce
existing biases and perpetuate misinformation if not
properly trained and evaluated.
Curtis (2023)
To examine the impact of
artificial intelligence,
including ChatGPT, on
academic publishing.
Literature review
ChatGPT can assist in writing, editing, and peer-reviewing
academic manuscripts. It can also automate certain
publishing processes and reduce publication costs.
However, it also raises concerns about authorship,
plagiarism, and the role of human editors and reviewers.
Ali et al. (2023)
To investigate the impact
of ChatGPT on motivation
for learning English
among teachers and
students
Survey of
teachers and
students in a
Saudi Arabian
university
ChatGPT can be a useful tool to supplement English
language learning, particularly for providing instant
feedback, generating creative ideas, and improving
speaking and writing skills. The study found that both
teachers and students had positive attitudes towards
ChatGPT, but some concerns were raised, such as the
need for human interaction and the lack of
personalization.
Macdonald et al.
(2023)
To investigate whether
ChatGPT can draft a
research article using
population-level vaccine
effectiveness analysis as
an example
A population-
level vaccine
effectiveness
analysis as input
to ChatGPT and
evaluation using
human
evaluation
metrics
(adequacy,
coherence, and
fluency) and
The study found that ChatGPT was able to draft a research
article that achieved a moderate level of quality, with high
fluency but lower adequacy and coherence. The study
suggests that ChatGPT can potentially save time and effort
for researchers by automating some of the drafting
process of research articles. However, the authors caution
that human editing is still necessary to improve the
quality of the article.
10 EVANS ET AL.
automated
metrics (ROUGE
and BLEU).
Kung et al.
(2023)
To investigate the
potential of using
ChatGPT as an AI-
assisted tool for medical
education, specifically for
the United States Medical
Licensing Examination
(USMLE)
A dataset of
USMLE-style
questions. The
evaluation
metrics used
were accuracy,
F1-score, and
time to answer.
The study found that ChatGPT's performance was
comparable to that of human examinees on the USMLE
questions, with high accuracy and F1-score. ChatGPT's
time to answer was much shorter than that of human
examinees.
Subramani et al.
(2023)
To evaluate the
performance of ChatGPT
in medical physiology
university examination.
Quantitative
research
involving 125
medical students
and a test.
The study found that ChatGPT was not able to perform
well in answering medical physiology questions in the
university examination. However, it showed potential in
providing hints and guiding students in their learning
process. The study suggests that ChatGPT can be a useful
tool for students to enhance their learning and
understanding of the subject, but it cannot replace human
expertise in the evaluation process.
Alshater (2022)
To explore the role of
ChatGPT in enhancing
academic performance in
higher education.
Case study
The study found that the use of ChatGPT improved the
academic performance of university students, especially in
writing assignments and exams. ChatGPT was found to be
a useful tool in enhancing students' learning and
understanding of the subject. The study suggests that
ChatGPT can be integrated into the educational system to
enhance the quality of education and learning outcomes.
Firaina and
Sulisworo
(2023)
To explore the frequency
and impact of using
ChatGPT on productivity
in higher education.
Quantitative
survey research
involving 100
university
students and a
questionnaire.
The study found that ChatGPT was frequently used by
university students to enhance their productivity.
Students reported that the use of ChatGPT improved their
productivity in academic tasks such as writing
assignments and conducting research.
Kalla and Smith
(2023)
To examine the impact of
ChatGPT on different
fields of study
Survey and
literature review
The authors find that ChatGPT has the potential to greatly
enhance research capabilities in various fields. They also
suggest that future research should explore ethical
considerations surrounding the use of AI in research.
Pettinato Oltz
(2023)
To examine the potential
of ChatGPT in legal
education
Case study
ChatGPT can be used to enhance legal education by
providing interactive and personalized learning
experiences.
Lee (2023)
To explore the potential
of ChatGPT in medical
education
Literature review
ChatGPT can be used for medical education in various
ways, such as virtual patient simulations and personalized
learning.
7 ChatGPT Impacts and Ethics
Most of the studies in Table 1-3 suggest that ChatGPT has limitations that need to be considered in practice. Antaki et al. (2023)
reported that ChatGPT can provide accurate information in ophthalmology, but its limitations in understanding context and
tone of conversation need to be addressed. Likewise, Subramani et al. (2023) found that ChatGPT was not able to perform well
in answering medical physiology questions in university examination. It only showed potential in the provision of hints and
the guide to students in their learning process. In context of healthcare, an AI model such as ChatGPT may make
recommendations that are not suitable for certain populations due to underrepresentation of these populations in training
data (Sallam, 2023).
Lund and Wang (2023), and Biswas (2023) argue that it poses ethical concerns such as privacy, bias, and control over data.
Similarly, Arif et al. (2023) discuss ethical concerns about patient privacy, data quality, and accountability. Curtis (2023) raises
concerns about authorship, plagiarism, and the role of human editors and reviewers in academic publishing. Iskender (2023)
emphasizes need to use the technology responsibly, while Taecharungroj (2023) finds that there were concerns about ethical
considerations in public reactions to ChatGPT on Twitter. Homolak (2023) also highlights importance of addressing ethical
and legal considerations in use of ChatGPT. Beerbaum's (2023) conceptual study highlights the need for a Generative Artificial
Intelligence (GAI) Ethics Taxonomy to mitigate ethical risks associated with ChatGPT; the study argues that the use of ChatGPT
in GAI-RPA requires careful consideration of ethical issues.
In line with the reviewed studies, the development and use of ChatGPT has raised numerous ethical concerns, particularly in
areas of privacy, fairness, and transparency. As a large language model that relies on vast amounts of data to generate
BIZECONS QUARTERLY 11
responses, ChatGPT raises questions regarding the collection, storage, and use of personal data. There is a risk that personal
information may be inadvertently shared or misused, which could lead to breaches of privacy and security. Moreso, the use of
ChatGPT in decision-making processes raises concerns about fairness and accountability, as well as the potential for bias and
discrimination.
Further, the development and use of ChatGPT raise broader ethical questions about the role of artificial intelligence in society.
As ChatGPT becomes increasingly sophisticated and ubiquitous, it raises questions about its potential impact on employment,
education, and social interaction. There is a risk that the widespread use of ChatGPT may lead to the displacement of certain
jobs, the automation of certain tasks, and the loss of human interaction and socialization. There is also a risk that ChatGPT
may perpetuate existing biases and stereotypes in the data on which it is trained, which might lead to discriminatory outcomes.
Therefore, it is important to carefully consider the ethical implications of ChatGPT and to ensure that it is developed and used
in a way that respects privacy, promotes fairness, and mitigates the potential for bias and discrimination (Beerbaum, 2023;
Iskender, 2023).
However, the use of ChatGPT in education also raises concerns about the potential for over-reliance on technology and the loss
of human interaction and socialization. While ChatGPT can provide valuable feedback and support, it cannot fully replace the
benefits of face-to-face interactions with teachers and peers. The use of ChatGPT in education may also require additional
resources and training for teachers to effectively integrate the technology into the classroom. Therefore, while ChatGPT has
the potential to transform education, it is important to carefully consider its impacts and limitations and to ensure that it is
used in a way that complements, rather than replaces, human teachers and interactions.
8 Discussion
The use of ChatGPT in various fields can bring about both positive and negative implications, and its potential to revolutionize
industries such as healthcare, education, and business must be carefully considered in light of ethical and privacy concerns
(Arif et al., 2023; Biswas, 2023; Curtis, 2023; Lund & Wang, 2023, Taecharungroj, 2023). Technological determinism theory
suggests that the introduction of ChatGPT can lead to a paradigm shift in different sectors, providing 24/7 access to
information, support, and advice, but it also raises concerns about privacy, bias, and control over data. Similarly, in academic
and library settings, ChatGPT can enhance information access and retrieval, personalization, and efficiency, but it can also lead
to overreliance, reduced creativity, and biased outputs. In medical education and research, ChatGPT has significant impacts,
but ethical concerns around patient privacy, data quality, and accountability must be addressed. Ethical guidelines and best
practices must be implemented to mitigate potential risks and ensure responsible use of technology (Arif et al., 2023; Biswas,
2023; Curtis, 2023; Lund & Wang, 2023, Taecharungroj, 2023).
The social construction of technology theory suggests that technology is not neutral, but rather shaped by social and cultural
factors. use of ChatGPT in various domains highlights its potential benefits and challenges, particularly in relation to ethical
concerns, bias, and human oversight. To mitigate these risks, ethical guidelines and best practices must be implemented, and
human involvement should be maintained. This study also identified potential applications of ChatGPT in various domains
such as healthcare, education, and finance. However, the use of ChatGPT in these areas also requires careful consideration of
ethical issues and potential risks. While ChatGPT has the potential to revolutionize various fields, ethical concerns and human
oversight must be maintained to ensure its safe and effective use.
Studies on ChatGPT reveal its potential to transform various fields such as education, healthcare, journalism, and research.
However, some studies suggest that ChatGPT has limitations in understanding context and tone of conversation, and it may
not perform well in answering certain types of questions. Moreover, ethical concerns associated with use of ChatGPT, such as
bias and data privacy, need to be addressed.
The use of ChatGPT can save time and effort for researchers, improve the efficiency of library systems, and reduce
documentation time for urologists. However, its potential in transforming fields must be accompanied by responsible use,
addressing its limitations and ethical concerns. According to social construction of technology theory, technology is not an
objective or neutral force, but rather is shaped by social and cultural factors. Studies on ChatGPT highlight the importance of
considering social and ethical concerns and suggest that technology must be integrated and adapted to suit specific contexts
and social practices. The studies on ChatGPT highlight the importance of considering social and cultural factors that shape its
use and impact in different contexts.
The introduction of ChatGPT is expected to have a significant impact on various industries and labor market. According to
technological determinism theory, this impact will be determined by technology itself, independent of social and cultural
factors. While technology is predicted to create new job opportunities in some sectors, it may also displace jobs in others,
highlighting the need for upskilling and reskilling programs. Moreover, ethical considerations such as responsible use of
technology must be addressed to ensure that benefits are distributed equitably and that existing inequalities in labor market
are not exacerbated.
However, social construction of technology theory suggests that impact of ChatGPT on labor market and various industries
will depend on how it is socially constructed and used. While some researchers predict job displacement in some sectors, others
emphasize potential for creating new job opportunities and the need for upskilling and reskilling programs to help workers
12 EVANS ET AL.
transition into new roles. Additionally, positive impact of ChatGPT on various fields, including research, education, and
healthcare, depends on its social construction and use. Its advanced language processing capabilities can be used in various
industries, but ethical considerations must be addressed to use technology responsibly.
In field of education, ChatGPT is expected to have both opportunities and challenges, as identified by social construction of
technology theory. While it has the potential to enhance personalized learning, encourage student engagement, and promote
critical thinking skills, there are concerns about accuracy, reliability, security, privacy, and ethical implications. Educational
institutions need to balance human judgement and machine learning to effectively incorporate ChatGPT in education. A SWOT
analysis has identified its strengths, weaknesses, opportunities, and threats for educational practice and research, and
educational institutions need to address these factors to effectively incorporate ChatGPT in education.
To prepare for impact of ChatGPT, policymakers and organizations must ensure that benefits are distributed equitably and
ethical considerations are addressed. Educational institutions must balance human judgement and machine learning and
consider ethical implications of using AI in education. impact of ChatGPT on labor market and various industries will depend
on how it is socially constructed and used, and adoption and implementation of ChatGPT will depend on social and cultural
factors. Therefore, it is important to carefully consider implications of using ChatGPT and address any concerns before
implementing it in various fields.
9 Conclusion
The literature review highlights the potential benefits and challenges associated with the use of ChatGPT in various fields such
as healthcare, education, and business. The technological determinism theory suggests that ChatGPT has the potential to
revolutionize industries by providing 24/7 access to information, support, and advice. However, ethical concerns around
privacy, bias, and control over data must be considered to ensure responsible use of the technology. The implementation of
ethical guidelines and best practices can help mitigate potential risks and ensure its safe and effective use.
The social construction of technology theory suggests that technology is shaped by social and cultural factors, and therefore,
the impact of ChatGPT on various domains must be considered in light of ethical concerns, bias, and human oversight. The
literature review highlights the various limitations of ChatGPT, particularly in understanding context and tone of the
conversation. The literature reviewed also highlights the need to maintain human involvement and implement ethical
guidelines and best practices to address these concerns. While ChatGPT has the potential to bring significant changes to various
fields, its limitations and ethical concerns need to be carefully considered.
Moreover, in line with the social construction of technology theory, the impact of ChatGPT on the labor market and various
industries will depend on how it is socially constructed and used. While some studies predict job displacement in some sectors,
others emphasize the potential for creating new job opportunities and the need for upskilling and reskilling programs to help
workers transition to new roles. Thus, the positive impact of ChatGPT on various fields, including research, education, and
healthcare, depends on its social construction and use.
In the field of education, ChatGPT has the potential to enhance personalized learning, encourage student engagement, and
promote critical thinking skills. However, accuracy, reliability, security, privacy, and ethical implications must be considered.
Educational institutions must balance human judgement and machine learning and consider the ethical implications of the
use of AI in education. Increased research can help identify the strengths, weaknesses, opportunities, and threats to
educational practice and research.
9.1 Policy Recommendations
Based on the literature reviewed, the following policy recommendations can be made to ensure the responsible use of ChatGPT
in various fields. First, ethical guidelines and best practices must be implemented to mitigate potential risks and ensure
responsible use of the technology. Policymakers and organizations should collaborate with experts in AI and ethics to develop
comprehensive guidelines that address concerns around privacy, bias, and control over data. These guidelines should be
regularly reviewed and updated to reflect the evolving landscape of AI technology.
Second, human involvement should be maintained in the use of ChatGPT. While technology has the potential to enhance
efficiency and productivity, it should not replace human judgement entirely. Also, policymakers and organizations can invest
in training and reskilling programs for workers whose jobs may be impacted by the adoption of ChatGPT. This will help ensure
a smooth transition to the new technology and reduce the risk of job displacement.
Third, educational institutions must balance human judgement and machine learning to effectively incorporate ChatGPT in
education. This includes addressing concerns around accuracy, reliability, security, privacy, and ethical implications.
Educational policymakers and organizations should collaborate with experts in AI and education to develop comprehensive
guidelines and best practices for the use of ChatGPT in education. This will help ensure that the technology is effectively
integrated into existing educational practices and does not compromise the quality of education.
Fourth, the impact of ChatGPT on the labor market and various industries must be carefully considered. Policymakers and
organizations should collaborate with experts in labor market analysis to identify the potential impact of ChatGPT on different
BIZECONS QUARTERLY 13
sectors and design appropriate policies and programs to mitigate likely job displacement. This may include upskilling and
reskilling programs, job placement services, and social safety nets for affected workers.
Finally, the social and cultural factors that shape the use and impact of ChatGPT in different contexts must be considered.
Policymakers and organizations should collaborate with experts in social and cultural studies to identify the potential social
and cultural implications of the adoption of ChatGPT and design appropriate policies and programs to address these concerns.
This will help to ensure that the technology is effectively integrated into existing social and cultural practices and does not
compromise the values and norms of different communities.
9.2 Future Research Directions
Despite the numerous benefits and potential applications of ChatGPT, there are still several limitations that need to be
addressed, and future research can help to improve the technology and mitigate potential risks. Some studies suggest that
ChatGPT may struggle to understand the context and tone of the conversation, and may not perform well in answering certain
types of questions. To overcome these limitations, researchers can explore ways to improve the technology's ability to
understand nuances in language and context. Ethical concerns (e.g., biases and data privacy) need to be addressed, and further
research can help to develop ethical guidelines and best practices for the responsible use of ChatGPT. Future research can also
explore the impact of ChatGPT on society and culture, including its potential to exacerbate existing inequalities and impact the
labor market.
In addition to addressing the limitations of ChatGPT, future research can also explore new applications of the technology and
its potential to transform industries and society. For example, the use of ChatGPT in journalism and media can enhance the
efficiency of news production and improve the quality of news reporting. In finance, ChatGPT can be used for risk management
and fraud detection. Further research can also explore the potential of ChatGPT in fields such as law, psychology, and social
work. However, as ChatGPT becomes more widely used, it is important to ensure that ethical considerations are taken into
account and that the technology is used responsibly. On the whole, future research can help to maximize the potential benefits
of ChatGPT while mitigating potential risks and ethical concerns.
References
Abdullah, M., Madain, A., & Jararweh, Y. (2022, November). ChatGPT: Fundamentals, Applications and Social Impacts.
In 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS) (pp. 1-
8). IEEE.
Adeola, O., & Evans, O. (2023). Digital Technology and Emergency Risk Communications of African Governments:
Experiences and Lessons from Covid-19 Pandemic. In Public Sector Marketing Communications, Volume II:
Traditional and Digital Perspectives (pp. 105-129). Cham: Springer International Publishing.
Adeola, O., Evans, O., & Okafor, L. E. (2023). Does social media moderate the link between tourism and economic wellbeing?
Evidence from the iterated GMM approach. Tourism Analysis.
https://doi.org/10.3727/108354223X16820219583340.
Alberts, I. L., Mercolli, L., Pyka, T., Prenosil, G., Shi, K., Rominger, A., & Afshar-Oromieh, A. (2023). Large language models
(LLM) and ChatGPT: what will the impact on nuclear medicine be?. European journal of nuclear medicine and
molecular imaging, 1-4.
Ali, J. K. M., Shamsan, M. A. A., Hezam, T. A., & Mohammed, A. A. (2023). Impact of ChatGPT on Motivation for Learning
English: Teachers and Students' Voices.
Aljanabi, M. (2023). ChatGPT: Future directions and open possibilities. Mesopotamian Journal of Cybersecurity, 2023, 16-
17.
Alkhaqani, A. L. (2023). ChatGPT and Nursing Education: Challenges and Opportunities. Al-Rafidain Journal of Medical
Sciences (ISSN: 2789-3219), 4, 50-51.
Alshater, M. (2022). Exploring the role of artificial intelligence in enhancing academic performance: A case study of
ChatGPT. Available at SSRN.
Alshurafat, H. (2023). The usefulness and challenges of chatbots for accounting professionals: application on
ChatGPT. Available at SSRN 4345921.
Antaki, F., Touma, S., Milad, D., El-Khoury, J., & Duval, R. (2023). Evaluating the performance of chatgpt in ophthalmology:
An analysis of its successes and shortcomings. medRxiv, 2023-01.
14 EVANS ET AL.
Arif, T. B., Munaf, U., & Ul-Haque, I. (2023). The future of medical education and research: Is ChatGPT a blessing or blight in
disguise?. Medical education online, 28(1), 2181052.
Atlas, S. (2023). ChatGPT for higher education and professional development: A guide to conversational AI.
Azam, J. A. N., Shakirullah, S., Sadaf, N. A. Z., Owais, K. H. A. N., & Khan, A. Q. (2020). Marshal McLuhan’s technological
determinism theory in the arena of social media. Theoretical and Practical Research in the Economic Fields, 11(2),
133-137.
Baidoo-Anu, D., & Owusu Ansah, L. (2023). Education in the era of generative artificial intelligence (AI): Understanding the
potential benefits of ChatGPT in promoting teaching and learning. Available at SSRN 4337484.
Beerbaum, D. O. (2023). Generative Artificial Intelligence (GAI) Ethics Taxonomy-Applying Chat GPT for Robotic Process
Automation (GAI-RPA) as Business Case. Available at SSRN 4385025.
Bettany-Saltikov, J. 2010. How to do a systematic literature review in nursing: a step-by-step guide. McGraw-Hill Education.
Bishop, L. (2023). A computer wrote this paper: What chatgpt means for education, research, and writing. Research, and
Writing (January 26, 2023).
Biswas, S. S. (2023). Role of Chat GPT in Public Health. Annals of Biomedical Engineering, 1-2.
Carvalho, I., & Ivanov, S. (2023). ChatGPT for tourism: applications, benefits and risks. Tourism Review.
Chen, X. (2023). Chatgpt and its possible impact on library reference services. Internet Reference Services Quarterly, 1-9.
Cooper, G. (2023). Examining Science Education in ChatGPT: An Exploratory Study of Generative Artificial
Intelligence. Journal of Science Education and Technology, 1-9.
Creswell, J. W. 2014. Research design: qualitative, quantitative, and mixed methods approaches. Sage publications.
Curtis, N. (2023). To ChatGPT or not to ChatGPT? The impact of artificial intelligence on academic publishing. The Pediatric
Infectious Disease Journal, 42(4), 275.
Diniasti, T. H., & Haqqu, R. (2022, December). Receiving Messages of Technological Determinism in the Documentary Film
“The Social Dilemma”: Analysis of Receptions in Teenagers. In 7th International Conference on Social and Political
Sciences (ICoSaPS 2022) (pp. 74-85). Atlantis Press.
Doshi, R. H., Bajaj, S. S., & Krumholz, H. M. (2023). ChatGPT: Temptations of Progress. The American Journal of Bioethics,
1-3.
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., ... & Wright, R. (2023). “So what if ChatGPT wrote
it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for
research, practice and policy. International Journal of Information Management, 71, 102642.
Evans, O. (2022). ICT and the provision of social services in low-income countries: the moderating role of institutional
quality. Journal of Enterprising Communities: People and Places in the Global Economy,
https://doi.org/10.1108/JEC-07-2021-0094.
Evans, O. (2023). The investment dynamics in renewable energy transition in Africa: The asymmetric role of oil prices,
economic growth and ICT. International Journal of Energy Sector Management. https://doi.org/10.1108/JEC-07-
2021-0094
Evans, O., & Mesagan, E. P. (2022). ICT-trade and pollution in Africa: Do governance and regulation matter?. Journal of Policy
Modeling, 44(3), 511-531.
Evans, O., & Oni, O. (2022). Fintech, Cryptocurrency and Blockchain Technology: Towards Promoting a Digital Africa.
In Digital Business in Africa: Social Media and Related Technologies (pp. 193-215). Cham: Springer International
Publishing.
Evans, O., Nwaogwugwu, I., Vincent, O., Wale-Awe, O., Mesagan, E., & Ojapinwa, T. (2023). The socio-economics of the 2023
fuel subsidy removal in Nigeria. BizEcons Quarterly, 17, 12-32.
Eysenbach, G. (2023). The role of chatgpt, generative language models, and artificial intelligence in medical education: A
conversation with chatgpt and a call for papers. JMIR Medical Education, 9(1), e46885.
Farrokhnia, M., Banihashem, S. K., Noroozi, O., & Wals, A. (2023). A SWOT analysis of ChatGPT: Implications for educational
practice and research. Innovations in Education and Teaching International, 1-15.
BIZECONS QUARTERLY 15
Felten, E., Raj, M., & Seamans, R. (2023). How will Language Modelers like ChatGPT Affect Occupations and
Industries?. arXiv preprint arXiv:2303.01157.
Fink, A. 2014. Conducting research literature reviews: From the internet to paper. Sage publications.
Firaina, R., & Sulisworo, D. (2023). Exploring the Usage of ChatGPT in Higher Education: Frequency and Impact on
Productivity. Buletin Edukasi Indonesia, 2(01), 67-74.
Gabrielson, A. T., Odisho, A. Y., & Canes, D. (2023). Harnessing Generative Artificial Intelligence to Improve Efficiency Among
Urologists: Welcome ChatGPT. The Journal of Urology, 10-1097.
George, A. S., & George, A. H. (2023). A Review of ChatGPT AI's Impact on Several Business Sectors. Partners Universal
International Innovation Journal, 1(1), 9-23.
Gergen, K. J. 2001. Social construction in context. Sage Publications.
Grant, M. J. and Booth, A. 2009. A typology of reviews: An analysis of 14 review types and associated methodologies. Health
Information & Libraries Journal, 26(2), pp. 91-108.
Guevara, S. (2022). The forced adoption of technology: a qualitative study on television journalists’adaptation during the
coronavirus pandemic through the lens of technological determinism.
Haleem, A., Javaid, M., & Singh, R. P. (2023). An era of ChatGPT as a significant futuristic support tool: A study on features,
abilities, and challenges. BenchCouncil transactions on benchmarks, standards and evaluations, 100089.
Hisan, U. K., & Amri, M. M. (2023). ChatGPT and Medical Education: A Double-Edged Sword. Journal of Pedagogy and
Education Science, 2(01).
Homolak, J. (2023). Opportunities and risks of ChatGPT in medicine, science, and academic publishing: a modern Promethean
dilemma. Croatian Medical Journal, 64(1), 1-3.
Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: opportunities in education and
research. Journal of Educational Technology and Innovation, 3(1).
Hopkins, A. M., Logan, J. M., Kichenadasse, G., & Sorich, M. J. (2023). Artificial intelligence chatbots will revolutionize how
cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectrum, 7(2), pkad010.
Iskender, A. (2023). Holy or unholy? Interview with open AI’s ChatGPT. European Journal of Tourism Research, 34, 3414-
3414.
Ivanov, S., & Soliman, M. (2023). Game of algorithms: ChatGPT implications for the future of tourism education and
research. Journal of Tourism Futures.
Jalil, S., Rafi, S., LaToza, T. D., Moran, K., & Lam, W. (2023). Chatgpt and software testing education: Promises & perils. arXiv
preprint arXiv:2302.03287.
Kalla, D., & Smith, N. S. (2023) Study and Analysis of Chat GPT and its Impact on Different Fields of Study.
Kasneci, E., Seßler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., ... & Kasneci, G. (2023). ChatGPT for good?
On opportunities and challenges of large language models for education. Learning and Individual Differences, 103,
102274.
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., ... & Tseng, V. (2023). Performance of ChatGPT
on USMLE: Potential for AI-assisted medical education using large language models. PLoS digital health, 2(2),
e0000198.
Kwok, A. O., & Koh, S. G. (2021). Deepfake: a social construction of technology perspective. Current Issues in Tourism, 24(13),
1798-1802.
Lahvis, A. (2023) Artificial vs. Non-Artificial Intelligence: What Does ChatGPT Mean for Labor and Employment?.
Lee, H. (2023). The Rise of ChatGPT: Exploring its Potential in Medical Education. Anatomical Sciences Education.
Liebrenz, M., Schleifer, R., Buadze, A., Bhugra, D., & Smith, A. (2023). Generating scholarly content with ChatGPT: ethical
challenges for medical publishing. The Lancet Digital Health, 5(3), e105-e106.
Lund, B. D., & Wang, T. (2023). Chatting about ChatGPT: how may AI and GPT impact academia and libraries?. Library Hi
Tech News.
16 EVANS ET AL.
Lund, B. D., Wang, T., Mannuru, N. R., Nie, B., Shimray, S., & Wang, Z. (2023). ChatGPT and a new academic reality: Artificial
Intelligencewritten research papers and the ethics of the large language models in scholarly publishing. Journal of
the Association for Information Science and Technology.
Macdonald, C., Adeloye, D., Sheikh, A., & Rudan, I. (2023). Can ChatGPT draft a research article? An example of population-
level vaccine effectiveness analysis. Journal of Global Health, 13, 01003.
Malinka, K., Perešíni, M., Firc, A., Hujňák, O., & Januš, F. (2023). On the Educational Impact of ChatGPT: Is Artificial
Intelligence Ready to Obtain a University Degree?. arXiv preprint arXiv:2303.11146.
Mathew, A. (2023). Is Artificial Intelligence a World Changer? A Case Study of OpenAI’s Chat GPT. Recent Progress in Science
and Technology Vol. 5, 35-42.
Mattas, P. S. (2023). ChatGPT: A Study of AI Language Processing and its Implications. Journal homepage: www. ijrpr. com
ISSN, 2582, 7421.
Noviani, A. I. (2022). Social Construction of Social Media Technology in Community in Indonesia.
Noy, S., & Zhang, W. (2023). Experimental evidence on the productivity effects of generative artificial intelligence. Available
at SSRN 4375283.
Patel, S. B., & Lam, K. (2023). ChatGPT: the future of discharge summaries?. The Lancet Digital Health, 5(3), e107-e108.
Paul, J., & Criado, A. R. (2020). The art of writing literature review: What do we know and what do we need to
know?. International Business Review, 29(4), 101717.
Peters, M. D., Marnie, C., Tricco, A. C., Pollock, D., Munn, Z., Alexander, L., ... & Khalil, H. (2020). Updated methodological
guidance for the conduct of scoping reviews. JBI evidence synthesis, 18(10), 2119-2126.
Pettinato Oltz, T. (2023). ChatGPT, Professor of Law. Professor of Law (February 4, 2023).
Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher
education?. Journal of Applied Learning and Teaching, 6(1).
Salah, M., Alhalbusi, H., Abdelfattah, F., & Ismail, M. M. (2023). Chatting with ChatGPT: Investigating the Impact on
Psychological Well-being and Self-esteem with a Focus on Harmful Stereotypes and Job Anxiety as Moderator.
Sallam, M. (2023, March). ChatGPT Utility in Health Care Education, Research, and Practice: Systematic Review on the
Promising Perspectives and Valid Concerns. In Healthcare (Vol. 11, No. 6, p. 887). MDPI.
Skavronskaya, L., Hadinejad, A., & Cotterell, D. (2023). Reversing the threat of artificial intelligence to opportunity: a
discussion of ChatGPT in tourism education. Journal of Teaching in Travel & Tourism, 1-6.
Snyder, H. (2019). Literature review as a research methodology: An overview and guidelines. Journal of business
research, 104, 333-339.
Subramani, M., Jaleel, I., & Krishna Mohan, S. (2023). Evaluating the performance of ChatGPT in medical physiology
university examination of phase I MBBS. Advances in Physiology Education, 47(2), 270-271.
Taecharungroj, V. (2023). “What Can ChatGPT Do?” Analyzing Early Reactions to the Innovative AI Chatbot on Twitter. Big
Data and Cognitive Computing, 7(1), 35.
Talan, T., & Kalinkara, Y. (2023). The Role of Artificial Intelligence in Higher Education: ChatGPT Assessment for Anatomy
Course. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 7(1), 33-40.
Teng, M. F. (2023). Scientific Writing, Reviewing, and Editing for Open-access TESOL Journals: The Role of ChatGPT.
Țicău, I. R., & Hadad, S. (2021). Technological Determinism vs. Social Shaping of Technology. The influence of activity trackers
on user’s attitudes. Management dynamics in the knowledge economy, 9(2), 147-163.
Tiwary, N. (2023). Netizens, Academicians, and Information Professionals' Opinions About AI With Special Reference To
ChatGPT. arXiv preprint arXiv:2302.07136.
Tlili, A., Shehata, B., Adarkwah, M. A., Bozkurt, A., Hickey, D. T., Huang, R., & Agyemang, B. (2023). What if the devil is my
guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learning Environments, 10(1), 15.
Varney, V., & May, D. (2021, July). Examining the Social Construction of Cross-reality Technologies in Learning. In 2021 ASEE
Virtual Annual Conference Content Access.
BIZECONS QUARTERLY 17
Verma, M. (2023). Novel Study on AI-Based Chatbot (ChatGPT) Impacts on the Traditional Library Management.
Wang, S., Scells, H., Koopman, B., & Zuccon, G. (2023). Can chatgpt write a good boolean query for systematic review literature
search?. arXiv preprint arXiv:2302.03495.
Zarifhonarvar, A. (2023). Economics of ChatGPT: A Labor Market View on the Occupational Impact of Artificial
Intelligence. Available at SSRN 4350925.
Zhai, X. (2022). ChatGPT user experience: Implications for education. Available at SSRN 4312418.
Zuccon, G., & Koopman, B. (2023). Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer
correctness. arXiv preprint arXiv:2302.13793.
... AI has increasingly integrated into our everyday lives and routine activities (Lee & Park, 2023). The development of AI models, such as OpenAI ChatGPT (Generative Pre-trained Transformer) and Google Gemini, is one of significant technological breakthroughs that has attracted a lot of attention in various fields including healthcare, education, research, journalism, and industry (Evans et al., 2023;Zhai, 2023). This was because of the high quality of their outputs across a wide range of topics and their language and content accuracy (Stahl & Eke, 2023). ...
... These findings in terms of the LLM benefits are in line with the study of Evans et al (2023). Evans et al (2023) have conducted a study to explore the impacts of ChatGPT on access-efficiency, employment, and education. ...
... These findings in terms of the LLM benefits are in line with the study of Evans et al (2023). Evans et al (2023) have conducted a study to explore the impacts of ChatGPT on access-efficiency, employment, and education. The findings revealed ChatGPT can be used to improve access and efficiency in a variety of industries and for individuals with disabilities or language barriers. ...
Article
Full-text available
This study explores the writing quality of two AI chatbots, OpenAI ChatGPT and Google Gemini. The research assesses the quality of the generated texts based on five essay models using the T.E.R.A. software, focusing on ease of understanding, readability, and reading levels using the Flesch-Kincaid formula. Thirty essays were generated, 15 from each chatbot, and evaluated for plagiarism using two free detection tools—SmallSEOTools and Check-Plagiarism—as well as one paid tool, Turnitin. The findings revealed that both ChatGPT and Gemini performed well in terms of word concreteness but demonstrated weaknesses in narrativity. ChatGPT showed stronger performance in referential and deep cohesion, while Gemini excelled in narrativity, syntactic simplicity and word concreteness. However, a significant concern was the degree of plagiarism detected in texts from both AI tools, with ChatGPT's essays exhibiting a higher likelihood of plagiarism compared to Gemini’s. These findings highlight the potential limitations and risks associated with using AI-generated writing.
... Applications of the chatbot use GenAI and LLMs for human-chatbot interactions [36]. While the aim of a chatbot is to mimic a human conversation, GenAI-driven chatbots' have demonstrated the capability to provide responses in applications for interactions in a variety of domains [26,[37][38][39]. ...
... Investigations into GenAI have identified its disruptive nature, with open research questions identifying the need for ongoing research to fully understand the socio-technical impact of GenAI and an understanding of hidden data in mass datasets in order to respond to questions and provide answers in real time. Moreover, GenAI-driven chatbots can be designed with instructions, guidelines, and considerations [26,37] to: ...
... • Technical and societal issues including the impact and effect(s) resulting from the development and implementation of GenAI-driven systems. • Such socio-technical effects of GenAI may be classified in terms of technological determinism (TD) as discussed in [37], which is characterized by delays in understanding such effects, as addressed in [64]. • ...
Article
Full-text available
Generative AI applications have played an increasingly significant role in real-time tracking applications in many domains including, for example, healthcare, consultancy, dialog boxes (common types of window in a graphical user interface of operating systems), monitoring systems, and emergency response. This paper considers generative AI and presents an approach which combines hedge algebra and a multilingual large language model to find hidden rules in big data for ChatGPT. We present a novel method for extracting natural language knowledge from large datasets by leveraging fuzzy sets and hedge algebra to extract these rules, presented in meta data for ChatGPT and generative AI applications. The proposed model has been developed to minimize the computational and staff costs for medium-sized enterprises which are typically resource and time limited. The proposed model has been designed to automate question–response interactions for rules extracted from large data in a multiplicity of domains. The experimental results show that the proposed model performs well using datasets associated with specific domains in healthcare to validate the effectiveness of the proposed model. The ChatGPT application in case studies of healthcare is tested using datasets for English and Vietnamese languages. In comparative experimental testing, the proposed model outperformed the state of the art, achieving in the range of 96.70–97.50% performance using a heart dataset.
... Sperandei et al. (2023) link low education levels with mental health outcomes among older adults, investigating the mediating effects of employment and income. Their research highlights the longterm impacts of educational attainment on life satisfaction and mental health in later life, 7 emphasizing the importance of maintaining employment and stable income as mediators that can alleviate some of the mental health risks associated with lower educational levels. ...
... This study highlights the potential of education and employment as powerful tools for social change, particularly in developing countries. Ayoola et al. (2023) delve into the socio-economic impacts of ChatGPT, an AI language model, on aspects such as access-efficiency, employment, education, and ethics. Their analysis provides a broader perspective on how emerging technologies like AI can transform educational access and employment landscapes while also raising ethical considerations. ...
Preprint
Full-text available
In this article, we analyze the relationships that connect graduates from high school, the training system and employment rates and conditions in the Italian regions between 2004 and 2022. The data used refer to the Istat Bes database. The results show that the growth in the number of high school graduates is positively associated with higher university education and employment with the exception of job satisfaction. Subsequently we also present a clusterization with k-Means algorithm confronting the Silhouette Coefficient with the Elbow Method. Finally, we confront seven different machine-learning algorithms for the prediction of the level of graduated from high school. We also present economic policy suggestions to increase schooling in the Italian regions. The results are critically discussed.
... Thus, we examine the economic, workplace, and educational impacts over the entertainment and social applications of the technology. As there were no validated scales that measure ChatGPT's risk and benefits, we constructed our scale items based on a Pew survey on automation (Smith & Anderson, 2017) and a recent review article on ChatGPT's impact (Evans et al., 2023). We measured risk perceptions across different domains, including the economy (two items: "ChatGPT will increase inequality between the rich and poor" and "People will have a hard time finding jobs"), the workplace (two items: "ChatGPT will distract employees from their tasks, leading to lower efficiency" and "ChatGPT will lead people to make unethical judgments"), and the education ("ChatGPT will reduce critical thinking skills" and "Chat GPT will be used for cheating and plagiarism"). ...
... Instead, there should be rules and regulations for accountability, integrity, transparency, and honesty. Several studies [166], [215], [216] investigate the use of ChatGPT in academic writing, highlighting concerns about authorship, transparency, and bias that demand the establishment of ethical guidelines and commitment to best practices. Careful consideration of which academic skills are crucial for researchers is needed. ...
Preprint
Full-text available
The past few decades have witnessed an upsurge in data, forming the foundation for data-hungry, learning-based AI technology. Conversational agents, often referred to as AI chatbots, rely heavily on such data to train large language models (LLMs) and generate new content (knowledge) in response to user prompts. With the advent of OpenAI's ChatGPT, LLM-based chatbots have set new standards in the AI community. This paper presents a complete survey of the evolution and deployment of LLM-based chatbots in various sectors. We first summarize the development of foundational chatbots, followed by the evolution of LLMs, and then provide an overview of LLM-based chatbots currently in use and those in the development phase. Recognizing AI chatbots as tools for generating new knowledge, we explore their diverse applications across various industries. We then discuss the open challenges, considering how the data used to train the LLMs and the misuse of the generated knowledge can cause several issues. Finally, we explore the future outlook to augment their efficiency and reliability in numerous applications. By addressing key milestones and the present-day context of LLM-based chatbots, our survey invites readers to delve deeper into this realm, reflecting on how their next generation will reshape conversational AI.
Article
In this article, we investigate the critical intersections of AI, academic integrity, and disability in the context of a large undergraduate course. Our aim was to adapt the course to respond to generative AI (GenAI) to avoid entrenching barriers for students, and instead teach them how to use GenAI tools in ways that deepen their learning and uphold academic honesty. Grounded in disability justice and access pedagogies, we outline five design goals centered on guidelines for AI usage, education on responsible AI use, revised assessments, support for teaching assistants (TAs), and accessible materials. These activities are detailed in our methodology. In our findings, we provide a critical reflection of the course adaptation, taking up issues such as varying levels of familiarity with GenAI, students’ capacity to engage with course changes, resistance to GenAI, instructors’ relational shifts to AI, and feelings of demoralization among the teaching team. We conclude by offering practical recommendations for educators, calling for learning communities to view this disruption as an invitation to listen to disabled students.
Article
Large language models (LLM) have been promising recently in the medical field, with numerous applications in clinical neuroscience. OpenAI’s launch of Generative Pre-trained Transformer 3.5 (GPT-3.5) in November 2022 and its successor, Generative Pre-trained Transformer 4 (GPT 4) in March 2023 have garnered widespread attention and debate surrounding natural language processing (NLP) and LLM advancements. Transformer models are trained on natural language datasets to predict and generate sequences of characters. Using internal weights from training, they produce tokens that align with their understanding of the initial input. This paper delves into ChatGPT’s potential as a learning tool in neurosurgery while contextualizing its abilities for passing medical licensing exams and neurosurgery written boards. Additionally, possibilities for creating personalized case presentations and study material are discussed alongside ChatGPT’s capacity to optimize the research workflow and perform a concise literature review. However, such tools need to be used with caution, given the possibility of artificial intelligence hallucinations and other concerns such as user overreliance, and complacency. Overall, this opinion paper raises key points surrounding ChatGPT’s role in neurosurgical education.
Article
Full-text available
With the rapid adoption of technological advancements (e.g., artificial intelligence or AI) and changes within higher education, the (un)employment (herein referring to utilizing or firing AI as an educational employee) of AI will change and likely become more complex. There is a pressing need to explore the research trends of employing AI in higher education. We conduct a review to examine the research designs, areas of impact, and nature of benefits and disadvantages offered by (un)employing AI in higher education. We searched SCOPUS, Web of Science, and Google and identified a total of 584 studies for review (145 from WOS, 289 from SCOPUS, and 150 from Google). Following our inclusion criteria, the authors screened and assessed the studies for eligibility until a consensus was reached. A total of 47 studies were included in the review. For research design and theory, we find that the most emergent trend is qualitative research design with a mix of technological and social theories (N = 13). For impact areas and valence of AI on (un)employment in higher education, we find that the most emergent trend is the impact of AI on labor and employment is a mix of valences by having the highest count of a mix of positive and negative (N = 13) followed by being negative (N = 9) and positive (N = 5). For the benefits and disadvantages of AI on (un)employment in higher education, we find that the most emergent trend is a mix of both technological and social, and pedagogical benefits and disadvantages (N = 21). The contribution of this work is in recognizing and characterizing plausible shifts to AI (un)employment in higher education and mitigation strategies.
Chapter
Generative AI is omnipresent in our daily lives, influencing everything from media and entertainment to personal care and healthcare. The Fourth Industrial Revolution has brought about significant developments in artificial intelligence, such as ChatGPT, which have gained prominence and changed the way data is created and produced. This chapter highlights the current use of AI in natural language processing. These models are based on machine learning. This chapter examines these models' possible benefits to the economy. The potential influence of generative AI on productivity might boost the world economy. All industry sectors will be significantly impacted by generative AI. The economy as a whole can benefit greatly from generative AI's ability to boost labor productivity. We can utilize generative AI's promise to build a more just, inclusive, and sustainable future for all people if we are aware of how it affects society. This chapter offers a comprehensive analysis of the potential exposure of generative AI, in particular to generative pre-trained transformers.
Article
Full-text available
The removal of fuel subsidy in Nigeria in 2023 has triggered a profound shift with far-reaching implications across economic, social, and environmental spheres. This study probes into the complex web of consequences arising from this drastic policy transformation, examining both the direct and indirect effects on the Nigerian society and economy. While the reallocation of resources from subsidies to vital sectors like healthcare, transport and education holds positive transformative potentials, ensuring effective utilization and equitable distribution of these funds warrants meticulous consideration. Achieving tangible improvements in essential services without unintentional negative consequences emerges as a central challenge. Drawing from historical precedents of subsidy removal attempts in Nigeria, the study underscores the importance of managing public sentiment and stakeholder reactions. The complexity arising from the interplay of economic, political, environmental, and societal factors necessitates a holistic approach. The study highlights the significance of informed decision-making to mitigate negative short-term impacts, harness long-term gains, and safeguard the vulnerable segments of the population. Policymakers must adopt a holistic approach that balances economic efficiency, social welfare, environmental sustainability, and inclusive growth. By addressing these multidimensional implications and drawing insights from both domestic and international experiences, Nigeria can navigate the complexities of subsidy removal effectively and work towards a prosperous and egalitarian society.
Article
Full-text available
Purpose Foundation models are a novel type of artificial intelligence algorithms, where models are pretrained at scale on unannotated data and fine-tuned for a myriad of downstream tasks such as generating text. This study assessed the accuracy of ChatGPT, a large language model, in the ophthalmology question-answering space. Design Evaluation of diagnostic test or technology. Participants ChatGPT - a publicly available large language model capable of dialogue. Methods We tested two versions of ChatGPT (January 9 “legacy” and ChatGPT Plus) on two popular multiple choice question banks used for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) exam. We generated two 260-question simulated exams from the Basic and Clinical Science Course (BCSC) Self-Assessment Program and the OphthoQuestions online question bank. We carried out logistic regression to determine the effect of the exam section, cognitive level (type of questions), and difficulty index on answer accuracy. We also performed a post hoc analysis using Tukey's test to decide if there were meaningful differences between the tested subspecialties. Main Outcome Measures We reported the accuracy of ChatGPT for each exam section in percentage correct by comparing ChatGPT’s outputs to the answer key provided by the question banks. We presented logistic regression results with a likelihood-ratio chi-square. We considered differences between exam sections statistically significant at a p-value <0.05 Results The legacy model achieved 55.8% accuracy on the BCSC set and 42.7% on the OphthoQuestions set. With ChatGPT Plus, accuracy increased to 59.4% ± 0.6 and 49.2% ±1.0, respectively. Accuracy improved with easier questions when controlling for the exam section and cognitive level. Logistic regression analysis of the legacy model showed that the exam section (LR 27.57, p=0.006) followed by question difficulty (LR 24.05, p<0.001) were most predictive of ChatGPT’s answers accuracy. While the legacy model performed best in general medicine and worst in neuro-ophthalmology (p<0.001) and ocular pathology (p=0.029), similar post hoc findings were not seen with ChatGPT Plus, suggesting more consistent results across exam sections. Conclusion ChatGPT, a publicly-available LLM, has encouraging performance on a simulated OKAP exam. Specialising LLMs through domain-specific pre-training may be necessary to improve their performance in ophthalmic subspecialties.
Article
Full-text available
This research aims to gain a deeper understanding of the views and rationality of lecturers in using ChatGPT in learning by explaining how lecturers use it in learning and their reasons for choosing or not choosing the technology. In this study, lecturers will be interviewed and asked to share their experiences and views on it. The data collected will be analyzed and interpreted to gain a deeper understanding of how the use of ChatGPT affects learning and why lecturers choose or do not choose the technology. In the interview results, ChatGPT helps users in finding information, ideas, translating texts, and providing alternative questions to deepen the understanding of the material. It is important to consider and verify information with more reliable and accurate sources. The use of ChatGPT in learning can be an interesting and effective alternative, but users also need to remain critical and selective in utilizing it. In further research, more interviews and case studies need to be conducted to obtain a more comprehensive understanding of the use of ChatGPT in learning. Although ChatGPT has limitations, respondents consider its use to improve productivity and learning efficiency. Therefore, the use of ChatGPT can be considered as an attractive alternative in learning, while maintaining a critical approach in utilizing it and verifying the information provided.
Article
Full-text available
ChatGPT has gained attention worldwide. In the medical education field, ChatGPT, or any similar large language model, provides a convenient way for students to access information and practice their skills. ChatGPT can simulate patient interactions, allowing students to practice their diagnostic and communication skills in a safe and controlled environment. ChatGPT can also answer questions and provide explanations for complex medical concepts. There have been attempts involving ChatGPT to assist researchers in writing journal articles. Due to its capabilities, ChatGPT has the potential to be abused and sparking ethical concerns. Unwise researchers can now employ ChatGPT to write academic articles. Similarly, irresponsible students, might utilize ChatGPT to cheat during exams. We investigated whether ChatGPT, in its current state, can answer Indonesian medical doctor examination problems. Among the 3 problems that we have picked, ChatGPT can only correctly answer 1 question. We also examine whether ChatGPT-generated abstracts can fool professionals and educators. We have brought 6 abstracts, 3 of which are taken from actual published papers, while the other 3 were generated by ChatGPT. We recruited 12 participants with either a medical doctor (M.D.), a doctorate (Ph.D.), or an M.D., Ph.D. degree from various institutions in Indonesia. Surprisingly, 4 of the participants couldn't guess a single abstract correctly, 6 could only identify 1 abstract accurately, one correctly guessed 2 abstracts, and one correctly identified 3 abstracts. Therefore, it is safe to say that ChatGPT, in its current state, has been able to fool professionals and educators.
Article
Full-text available
Purpose The paper aims to evaluate the ways ChatGPT is going to disrupt tourism education and research. Design/methodology/approach This is a conceptual paper. Findings ChatGPT has the potential to revolutionize tourism education and research because it can do what students and researchers should do, namely, generate text (assignments and research papers). Universities will need to reevaluate their teaching and assessment strategies and incorporate generative language models in teaching. Publishers will need to be more receptive toward manuscripts that are partially generated by artificial intelligence. In the future, digital teachers and research assistants will take over many of the cognitive tasks of tourism educators and researchers. Originality/value To the authors’ best knowledge, this is one of the first academic papers that investigates the implications of ChatGPT to tourism education and research.
Article
Full-text available
Purpose The rapid growth of artificial intelligence is disrupting various industries, including the tourism sector. This paper aims to outline the applications, benefits and risks of ChatGPT and large language models in general on tourism. It also aims to establish a research agenda for investigating the implications of these models in tourism. Design/methodology/approach Drawing on the available literature on ChatGPT, large language models and artificial intelligence, the paper identifies areas of application of ChatGPT for several tourism stakeholders. Potential benefits and risks are then considered. Findings ChatGPT and other similar models are likely to have a profound impact on several tourism processes. They will contribute to further streamline customer service in front-of-house operations and increase productivity and efficiency in back-of-house operations. Although negative consequences for human resources are expected, this technology mostly enhances tourism employees. Originality/value To the best of the authors’ knowledge, this is one of the first studies that explore the potential implications of ChatGPT in tourism and hospitality.
Chapter
Across the African continent, governments are implementing e-governance measures with websites, portals, social media pages and WhatsApp chatbots. These platforms enable the government to communicate more effectively and efficiently with their citizens, particularly during crisis situations like the Covid-19 pandemic. This chapter explores the challenges and prospects of utilising digital technology for emergency risk communications in Africa. Challenges to the use of digital technology for emergency risk communications in Africa include; the malicious use of electronic technology, the spread of misinformation, the digital divide, inadequate ICT skills, weak ICT infrastructure, limited access and bandwidth constraints. Critical success factors that have the potential for enhancing emergency risk communications leveraging digital technology are identified. The chapter provides insights that can guide the utilisation of digital technology in emergency risk communications in Africa, highlighting the need for a concerted approach to address the challenges and leverage the opportunities.KeywordsDigital technologyEmergency risk communicationsCovid-19E-governance
Article
The relevance of social media to tourism and, subsequently, economic wellbeing is demonstrable in the target marketing of tourism products and services to potential customers at tourist destinations. Using a dataset from the 40 most visited countries across different continents over the period 2009 to 2020, this study investigates the effect of tourism and social media on economic wellbeing. It also examines the moderating influence of social media on the underlying relationship. The study adopts the tourism-led growth hypothesis as the main theoretical rationale for the underlying relationship. The empirical analysis is conducted using the iterated general method of moments (GMM). The results show that tourism development helps to promote economic wellbeing, while social media has a dampening effect. Additionally, the findings indicate that a high level of social media penetration has a significant and positive moderating effect on the nexus between tourism and economic wellbeing. This suggests that social-media-driven tourism can significantly improve the economic wellbeing of destination countries. Conducive macroeconomic conditions and political stability are also concurrent with the contributory effects of tourism on the economic wellbeing of destination countries.