Article

An approach to the classification of educational chatbots

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Nowadays, chatbots have become popular tools in such a way that they are used in different sectors like commercial, elderly care, tourism, and education. The COVID-19 pandemic has forced many students and teachers to suspend face-to-face classes. Therefore, schools and governments have found it necessary to continue education remotely, using the resources provided by the Internet. This fact has created a greater interest in educational chatbots, so several projects have been proposed to develop these academic tools, each following its way of implementation and addressing issues from different points of view. This paper presents a proposal for chatbot classification, following the Systematic Mapping Study and an iterative method to review and classify educational chatbots. We also discuss the resulting categories and their characteristics and limitations and possible uses by developers and researchers.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... AI has effectively addressed complex challenges across diverse domains, including education (Ouyang et al., 2022). The integration of AI into education has made a substantial impact, as illustrated by enhancements in educational process efficiency (Javaid et al., 2023), the facilitation of global learning (Rahman & Watanobe, 2023), the customization of learning experiences (Ahmed & Miller, 2023), the development of more intelligent educational content (Filippi, 2023), and the optimization of academic administration for improved effectiveness and efficiency (Urquiza-Yllescas et al., 2022). ...
Article
Full-text available
The benefits of artificial intelligence (AI)-enabled language models, such as ChatGPT, have contributed to their growing popularity in education. However, there is currently a lack of evidence regarding the perception of ChatGPT, specifically among design students. This study aimed to understand the product design (PD) and user experience design (UXD) students’ views on ChatGPT and focused on an Indian university. The study employed a survey research design, utilizing questionnaires as the primary data collection method. The collected data (n = 149) was analyzed using descriptive statistics (i.e., frequency, percentage, average, and standard deviation (SD). Inferential statistics (i.e., one-way ANOVA) was used to understand the significant differences between the programs of study, gender, and academic level. The findings indicate that the students expressed admiration for the capabilities of ChatGPT and found it to be an interesting and helpful tool for their studies. In addition, the students’ motivation towards using ChatGPT was moderate. Furthermore, the study observed significant differences between PD and UXD students and differences based on gender and academic level on certain variables. Notably, UXD students reported that ChatGPT does not understand their questions well, and formulating effective prompts for the tool was more challenging than for PD students. Based on the findings, the study recommends how educators should consider integrating ChatGPT into design education curricula and pedagogical practices. The insights aim to contribute to refining the use of ChatGPT in educational settings and exploring avenues for improving its effectiveness, ultimately advancing the field of AI in design education.
... In the education sector, chatbots are being used to provide 24/7 access to information, enhance student learning experiences, and improve productivity and communication [5]. The COVID-19 pandemic has further accelerated the interest in educational chatbots, leading to the development of various academic tools [6]. However, the use of chatbots in education also presents technical challenges, such as the need for personalized service and the processing of helpdesk requests [7]. ...
Conference Paper
This review delves into the dynamic landscape of chatbots in higher education, tracing their evolution, rationale, and multifaceted applications. Beginning with an exploration of historical developments and their transition into education, insights from systematic reviews and case studies underscore chatbots' potential to enhance personalized and adaptive learning. The integration of chatbots in higher education is rationalized by their ability to boost user satisfaction, improve virtual student services, and provide diverse academic support. While promises abound, challenges such as privacy concerns and task complexity comprehension need addressing. The classification of chatbots, including rule-based, and machine learning-based, is dissected, offering a nuanced understanding of their functionalities. Case studies spotlight successful implementations, yet ethical considerations, adoption challenges, and potential biases loom large. Looking ahead, the review identifies research gaps and underscores the need for practical implementation strategies, privacy management, and exploration of ethical implications, providing a comprehensive guide for stakeholders navigating the transformative potential of chatbots in higher education.
... Chatbots are computer programs that mimic human-like conversation with users using natural language or text, thus creating a sense of interpersonal interaction [1], [2]. Earlier versions of chatbots relied on rudimentary pattern matching and textual analysis, but modern versions use knowledgebased models [3]. ...
Article
Full-text available
Increasing use of artificial intelligence tools in programming education calls for a deeper understanding of their effect on students’ learning. This paper presents a study that investigates the experiences of part-time undergraduate students using ChatGPT in a five-week Java programming course. After each exercise, students provided feedback via anonymous surveys in which they rated different suitability aspects of ChatGPT. The majority viewed ChatGPT positively and suitable for learning programming concepts. However, its suitability for specific implementation tasks received mixed reviews. Students found it easy to adapt ChatGPT’s generated code to the exercises’ implementation tasks. The students primarily used it for acquiring background knowledge, learning syntax and programming concepts and suggesting suitable algorithms. Yet, some abstained from using it due to concerns to not garner sufficient programming proficiency, retrieving partially incorrect or misleading generated code, preferring an independent working style, or general skepticism about its benefits. Finally, in response to our findings, we also discuss three perspective directions for improving the suitability of LLM chatbots for students in programming education.
... A chatbot is a computer program that simulates a conversation with users through natural language or text, giving the illusion of communicating with a human [1], [2]. Early chatbots relied on simpler pattern matching and string processing, but more advanced ones now use complex knowledge-based models [3]. ...
Article
Full-text available
ChatGPT has sparked both excitement and skepticism in education. To analyze its impact on teaching and learning it is crucial to understand how students perceive ChatGPT and assess its potential and challenges. Toward this, we conducted a two-stage study with senior students in a computer engineering program (n=56). In the first stage, we asked the students to evaluate ChatGPT using their own words after they used it to complete one learning activity. The returned responses (3136 words) were analyzed by coding and theme building (36 codes and 15 themes). In the second stage, we used the derived codes and themes to create a 27-item questionnaire. The students responded to this questionnaire three weeks later after completing other activities with the help of ChatGPT. The results show that the students admire the capabilities of ChatGPT and find it interesting, motivating, and helpful for study and work. They find it easy to use and appreciate its human-like interface that provides well-structured responses and good explanations. However, many students feel that ChatGPT's answers are not always accurate and most of them believe that it requires good background knowledge to work with since it does not replace human intelligence. So, most students think that ChatGPT needs to be improved but are optimistic that this will happen soon. When it comes to the negative impact of ChatGPT on learning, academic integrity, jobs, and life, the students are divided. We conclude that ChatGPT can and should be used for learning. However, students should be aware of its limitations. Educators should try using ChatGPT and guide students on effective prompting techniques and how to assess generated responses. The developers should improve their models to enhance the accuracy of given answers. The study provides insights into the capabilities and limitations of ChatGPT in education and informs future research and development.
Article
With the immense interest in ChatGPT worldwide, education has seen a mix of both excitement and skepticism. To properly evaluate its impact on education, it is crucial to understand how far it can help students without prior knowledge answer assessment questions. This study aims to address this question as well as the impact of the question type. We conducted multiple experiments with computer engineering students (experiment group: = 41 to 56), who were asked to use ChatGPT to answer previous test questions before learning about the related topics. Their scores were then compared with the scores of previous-term students who answered the same questions in a quiz or exam setting (control group: = 24 to 61). The results showed a wide range of effect sizes, from-2.55 to 1.23, depending on the question type and content. The experiment group performed best answering code analysis and conceptual questions but struggled with code completion and questions that involved images. On the other hand, the performance in code generation tasks was inconsistent. Overall, the ChatGPT group's answers lagged slightly behind the control group's answers with an effect size of −0.16. We conclude that ChatGPT, at least in the field of this study, is not yet ready to rely on by students who don't have sufficient background to evaluate generated answers. We suggest that educators try using ChatGPT and educate students on effective questioning techniques and how to assess the generated responses. This study provides insights into the capabilities and limitations of ChatGPT in education and informs future research and development.
Preprint
Full-text available
For advanced human-computer interaction, research on natural language processing is on trend, resulting in the development of innate and natural interaction modalities, such as chatbots. A chatbot is a software application that makes it possible to conduct conversations in a natural language for various user queries in an online mode, thus grabbing much attention in business and commercial applications. Various chatbot models have been reported previously, but no comprehensive chatbot model has been available for processing all human languages under all user applications. As a result, researchers have started to dedicate their efforts to develop their own chatbot model based on a specific language for some specific applications. With this specific goal, we have proposed a chatbot model for conservation in the English language that handles queries in the sociological domain based on a hybrid approach. The proposed chatbot model using generative and retrieval techniques, can handle one-word as well as descriptive responses to user sociological queries. We claim that the proposed chatbot can meet the needs of small-to medium-sized organizations for their research queries, and that this model is comparatively more interactive, easy to maintain, and cost-effective against the previous models.
Article
Full-text available
This literature review presents the History, Technology, and Applications of Natural Dialog Systems or simply chatbots. It aims to organize critical information that is a necessary background for further research activity in the field of chatbots. More specifically, while giving the historical evolution, from the generative idea to the present day, we point out possible weaknesses of each stage. After we present a complete categorization system, we analyze the two essential implementation technologies, namely, the pattern matching approach and machine learning. Moreover, we compose a general architectural design that gathers critical details, and we highlight crucial issues to take into account before system design. Furthermore, we present chatbots applications and industrial use cases while we point out the risks of using chatbots and suggest ways to mitigate them. Finally, we conclude by stating our view regarding the direction of technology so that chatbots will become really smart.
Article
Full-text available
Chatbots are currently used in various online applications, most of the case for shopping or as a personal assistant. These chatbots offer a range of potential benefits, including personalization and 24/7 instant availability. These positive aspects of chatbots can be beneficial in the educational sector. They represent a new type of human-machine interface in natural language. However, chatbots in academia have received only limited attention, for example by providing organizational support for studies or courses and exams. This branch of research is just emerging in the scientific community, therefore, in our article, we set up a chatbot in the field of educational and professional guidance which is based on the theory of John Holland and the RIASEC questionnaire in order to determine the dominant type of personality of undergraduate and graduate students that wants to enter the job market.
Article
Full-text available
Several domain-specific assistants in the form of chatbots have conquered many commercial and private areas. However, there is still a limited level of systematic knowledge of the distinctive characteristics of design ele- ments for chatbots to facilitate development, adoption, implementation, and further research. To close this gap, the paper outlines a taxonomy of design elements for chatbots with 17 dimensions organized into the perspectives intel- ligence, interaction and context. The conceptually groun- ded design elements of the taxonomy are used to analyze 103 chatbots from 23 different application domains. Through a clustering-based approach, five chatbot arche- types that currently exist for domain-specific chatbots are identified. The developed taxonomy provides a structure to differentiate and categorize domain-specific chatbots according to archetypal qualities that guide practitioners when taking design decisions. Moreover, the taxonomy serves academics as a foundation for conducting further research on chatbot design while integrating scientific and practical knowledge.
Conference Paper
Full-text available
Abstract—Students often struggle to communicate with their peers or lecturers about some of the issues they face during their time at university, either it be academic or personal. One of these issues is introductory programming, in instances were they choose to memorise code in order to pass rather than understanding how the logic behind the code actually works. Programming requires an understanding of how a certain logical flows and algorithm work. In this article, we discuss the difficulties that students face in introductory programming. We have also developed an interactive AI chatbot tool that students can interact with on some of the academic issues they may face. They can ask for advice on how to understand algorithms and what measures to take in order to understand programming logic and visualise metal models of the algorithms. The chatbot can also be used for personal advice. A survey that was conducted showed that there is a need for such a tool in aiding students through their university life. Index Terms—Artificial Intelligence, Chatbot, Struggling Stu- dents, Advisory, Novice Programmers.
Conference Paper
Full-text available
Natural language tutors have been an active research topic for decades and the widespread use of chat interfaces lead to a high level of acceptance of chatbots. Despite that, conversational AI has not found its way into the practice of corporate e-learning yet. In this paper we present a novel approach to leverage the advances in the field of conversational AI for corporate e-learning. Following a design science approach, we identify the pivotal stakeholders and design objectives. We propose a service architecture and demonstrate its feasibility with a prototypical implementation. Finally, we conclude that the proposed approach has the potential to lower entry barriers for conversational AI for the practice of corporate e-learning.
Conference Paper
Full-text available
It is frequently the case for final degree projects (FDP) to represent the largest academic endeavor students have been involved with. The writing of the FDP technical report tends to be one of the hurdles. Due to their inexperience, students fail to meet quality standards in their writing efforts. Research shows that text and image plagiarism, poor literature searches and lack of synthesis are some of the most usual errors. Yet, these error-filled memories keep publishing in university-backed open repositories. This paper describes a solution to help both students and supervisors detecting basic quality errors in FDP reports. Based on a chatbot front-end called Ikastenbot, students can upload their reports while they are writing them and spot, before publication, possible errors in spelling and grammar, text and images reuse, and lack of proper referencing. We applied the techniques described on the memories of our university FDP repository. Results show that Ikastenbot is able to detect errors in almost every report. The source code of our solution has been published under an open-source license. CCS CONCEPTS • Human-centered computing → Ubiquitous and mobile computing systems and tools; Personal digital assistants
Chapter
Full-text available
We developed a virtual assistant that enables students to access interactive content adapted for an introductory undergraduate course on artificial intelligence. This chatbot is able to show answers to frequently asked questions in a hierarchical structured manner, leading students by either voice, text or tactile input to the content that better solves their questions and doubts. It was developed using Google Dialogflow as a simple way to generate and train a natural language model. Another convenience of this platform is its ability to collect usage data that is potentially useful for lecturers as learning indicators. The main purpose of this paper is to outline the methodology that guided our implementation so that it can be reproduced in different educational contexts and study chatbots as tools for learning. At the moment, several articles, news and blogs are writing about the potential, implementation and impact chatbots have in general contexts, however there is little to no literature proposing a methodology to reproduce them for educational purposes. In that respect, we developed four main categories as a generic structure of course content and focused on quick implementation, easy updating and generalization. The final product received a general approbation of the students due to its accessibility and well structured data.
Article
Full-text available
The globally widespread instant messaging (IM) mobile applications such as WhatsApp or Telegram were not originally educational tools, but they have become platforms for peer to peer assessment (P2P). The IM applications offer “chatbots” or “virtual assistant bots” that help students by providing them a multitude of services in the form of text or voice dialogs. A new method for integrating P2P assessment using voice recordings with the help of a chatbot is proposed. By using this system we can effectively improve both the typical learning and the P2P evaluation process of a massive open on-line course (MOOC). After a 2-month experiment, with 77 students that recorded 737 voice answers with a Telegram based chatbot, we describe in detail how to use a chatbot and the way to design voice-based challenges to perform a new kind of assignment in a MOOC, with 90% of the learners encouraging us to use chatbots in future courses.
Chapter
Full-text available
In Design Science Research (DSR) it is important to build on descriptive (Ω) and prescriptive (Λ) state-of-the-art knowledge in order to provide a solid grounding. However, existing knowledge is typically made available via scientific publications. This leads to two challenges: first, scholars have to manually extract relevant knowledge pieces from the data-wise unstructured textual nature of scientific publications. Second, different research results can interact and exclude each other, which makes an aggregation, combination, and application of extracted knowledge pieces quite complex. In this paper, we present how we addressed both issues in a DSR project that focuses on the design of socially-adaptive chatbots. Therefore, we outline a two-step approach to transform phenomena and relationships described in the Ω-knowledge base in a machine-executable form using ontologies and a knowledge base. Following this new approach, we can design a system that is able to aggregate and combine existing Ω-knowledge in the field of chatbots. Hence, our work contributes to DSR methodology by suggesting a new approach for theory-guided DSR projects that facilitates the application and sharing of state-of-the-art Ω-knowledge.
Conference Paper
Full-text available
Taxonomies constitute one fundamental type of artefact in design science, describing and classifying existing or future objects of a domain. Taxonomies support researchers and practitioners with analysing and understanding a domain, which in turn is a prerequisite for theory building. Despite the increasing interest in taxonomies (and methodological guidance for building them), there is hardly any guidance for researchers on how to rigorously evaluate taxonomies. Based on a literature analysis, this study sheds light on the question of whether, when, and how researchers currently evaluate taxonomies. We critically synthesize and comprehensively review 306 articles that are concerned with taxonomies. Surprisingly , we find that taxonomies are rarely evaluated in IS research, nor is there any consistency in terms of methods used for evaluations. We describe the methods used by IS researchers to evaluate taxonomies after taxonomy building has been completed. Being the first to systematically analyse tax-onomy evaluation, we propose a preliminary version of a framework for taxonomy evaluation which enables researchers to choose among the wide range of taxonomy evaluation methods available. Our study advances an informed and purposeful evaluation of taxonomies and contributes to bridging the gap between abstract design science evaluation strategies and concrete taxonomy evaluation methods.
Chapter
Full-text available
A chatbot can be defined as a computer program, designed to interact with users using natural language or text in a way that the user thinks he is having dialogue with a human. Most of the chatbots utilise the algorithms of artificial intelligence (AI) in order to generate required response. Earlier chatbots merely created an illusion of intelligence by employing much simpler pattern matching and string processing design techniques for their interaction with users using rule-based and generative-based models. However, with the emergence of new technologies more intelligent systems have emerged using complex knowledge-based models. This paper aims to discuss chatbots classification, their design techniques used in earlier and modern chatbots and how the two main categories of chatbots handle conversation context.
Conference Paper
Full-text available
Software that interacts with its users through natural language, so-called conversational agents (CAs), is permeating our lives with improving capabilities driven by advances in machine learning and natural language processing. For organizations, CAs have the potential to innovate and automate a variety of tasks and processes, for example in customer service or marketing and sales, yet successful design remains a major challenge. Over the last few years, a variety of platforms that offer different approaches and functionality for designing CAs have emerged. In this paper, we analyze 51 CA platforms to develop a taxonomy and empirically identify archetypes of platforms by means of a cluster analysis. Based on our analysis, we propose an extended taxonomy with eleven dimensions and three archetypes that contribute to existing work on CA design and can guide practitioners in the design of CA for their organizations.
Conference Paper
Full-text available
The purpose of this paper is to discuss about smart learning environments and present the FIT-EBot, a chatbot, which automatically gives a reply to a question of students about the services provided by the education system on behalf of the academic staff. The chatbot can play the role of an intelligent assistant, which provides solutions for higher-education institutions to improve their current services, to reduce labor costs, and to create new innovative services. Various artificial intelligence techniques such as text classification, named entity recognition are used in this work to enhance the system performance.
Conference Paper
Full-text available
With rapid progress in machine learning, language technologies and artificial intelligence, conversational agents (CAs) gain rising attention in research and practice as potential non-human teammates, facilitators or experts in collaborative work. However, designers of CAs in collaboration still struggle with a lack of comprehensive understanding of the vast variety of design options in the dynamic field. We address this gap with a taxonomy to help researchers and designers understand the design space and the interrelations of different design options and recognize useful design option combinations for their CAs. We present the iterative development of a taxonomy for the design of CAs grounded in state of the art literature and validated with domain experts. We identify recurring design option combinations and white spots from the classified objects that will inform further research and development efforts.
Conference Paper
Full-text available
Requirements extraction is an important element of the software development process. One of the most used techniques for requirements extraction is the interview. Initiatives to support the training and technical training of computing students in this area are being proposed, such as the development of support mechanisms. These initiatives are proposed by the fact that computing students are graduating with limited practical knowledge in requirements extraction. In parallel, chatterbots have been investigated as tools with the capacity to support the training of students from different areas of knowledge, since the main characteristic is verbal conversational behavior. In medicine, for example, they can take on the role of a sick patient to train students to extract information about the patient’s symptoms. One subject that has been explored in the context of educational chatterbots is context awareness, so that the chatterbot can present the right information for the right user. These surveys start from the premise that not every student has the same knowledge as their peers on the subject. Thus, in this research work in full paper we describe a chatterbot that offers support to Software Engineering Education, focusing mainly on the requirements extraction, which assumes the role of a stakeholder. A prototype of a chatterbot that is sensitive to student’s context is presented, as well as preliminary results on the impact of this support mechanism in Software Engineering Education.
Article
Full-text available
A chat-bots aims to make a conversation between both human and machine. The machine has been embedded knowledge to identify the sentences and making a decision itself as a response to answer a question. Chat-bots will be completely based on a text-based user interface, allowing the user to type commands and receive text as well as text to speech response. Chat-bots are usually stateful services, remembering previous commands in order to provide functionality. It can be utilized securely by an even larger audience when chat-bots technology is integrated with popular web services. The college inquiry chat-bots will be built using artificial algorithms that analyze user's queries and understand user's message. The response principle is matching the input sentence from a user. The User can ask the question any college-related activities through the chat-bot without physically available to the college for inquiry. The System analyses the question and then answers to the user. With the help of artificial intelligence, the system answers the query asked by the students. The system replies using an effective Graphical User Interface as if a real person is talking to the user. The user just has to register himself to the system and has to login to the system. The chat-bots consists of core and interface that is accessing the core in (MySQL).Natural language processing technologies are used for parsing, tokenizing, stemming and filtering the content of the complaint.
Conference Paper
Full-text available
Conversational interfaces are used for a variety of applications. They are constructed to offer useful services and to interact with the users in order to assist them. Towards this direction, the current paper presents the incorporation of the interactive chatterbot ALICE in a mobile-assisted English language learning application. This chatterbot is further enriched with mechanisms in order to support students while learning vocabulary in English. As such, apart from making conversation with this conversational agent, they can practice their vocabulary or even be evaluated by the chatterbot. Hence, this study offers a fertile ground to enhance pedagogical results such as fostering motivation and engagement, incrementing crucial language learning and assisting in the acquisition of cognitive skills. Finally, the students can chat with the pedagogic conversational agent either orally or by writing.
Article
Full-text available
Fuzzy comprehensive evaluation (FCE) is a synthetic appraisement method based on fuzzy mathematics, and evaluation result is practical and reliable, therefore, which is widely used in petroleum, construction and many other fields. This paper applies it to the evaluation of water flooding effect of oilfield. This paper introduces the principle of FCE method and the evaluation steps. The method is applied to the evaluation of water flooding development effect, which is helpful to improve the analysis level of oil and gas field development. Compared with the traditional method, this proposed method can reflect the difference of the evaluation units. Meanwhile, the weight vector is gotten by entropy method and analytic hierarchy process (AHP), which making the evaluation results more convincing. Taking W oilfield as an example, the ten factors (e.g., reserves controlled degree of water flooding, reserves producing degree of water flooding, recovery percent of recoverable reserves, water cut, water storage rate, oil recovery rate of residual recoverable reserves, cumulative water injection, maintenance of formation pressure, comprehensive decline rate, water flooding recovery) were evaluated by proposed FCE method. Then the membership matrix is established, and the weight vector is calculated by the entropy method and the AHP. Finally, the evaluation results of the two methods are obtained by fuzzy transformation and are consistent with the actual water flooding effect. Thus, the FEC method can be used as method to accurately evaluate the effect of oil field water flooding.
Conference Paper
Full-text available
The idea of interacting with computers through natural language dates back to the 1960s, but recent technological advances have led to a renewed interest in conversational agents such as chatbots or digital assistants. In the customer service context, conversational agents promise to create a fast, convenient, and cost-effective channel for communicating with customers. Although numerous agents have been implemented in the past, most of them could not meet the expectations and disappeared. In this paper, we present our design science research project on how to design cooperative and social conversational agents to increase service quality in customer service. We discuss several issues that hinder the success of current conversational agents in customer service. Drawing on the cooperative principle of conversation and social response theory, we propose preliminary meta-requirements and design principles for cooperative and social conversational agents. Next, we will develop a prototype based on these design principles.
Article
Full-text available
In this paper we present a software platform called Chatbot designed to introduce high school students to Computer Science (CS) concepts in an innovative way: by programming chatbots. A chatbot is a bot that can be programmed to have a conversation with a human or robotic partner in some natural language such as English or Spanish. While programming their chatbots, students use fundamental CS constructs such as variables, conditionals and finite state automata, among others. Chatbot uses pattern matching, state of the art lemmatization techniques, and finite state automata in order to provide automatic formative assessment to the students. When an error is found, the formative feedback generated is immediate and task-level. We evaluated Chatbot in two observational studies. An online nation-wide competition where more than 10 thousand students participated. And a mandatory in-class 15-lesson pilot course in 3 high schools. We measured indicators of student engagement (task completion, participation, self reported interest, etc.) and found that girls’ engagement with Chatbot was higher than boys’ for most indicators. Also, in the online competition, the task completion rate for the students that decided to use Chatbot was five times higher than for the students that chose to use the renown animation and game programming tool Alice. Our results suggest that the availability of automatic formative assessment, may have an impact on task completion and other engagement indicators among high school students.
Chapter
Chatbots are becoming increasingly important in the customer service sector due to their service automation, cost saving opportunities and broad customer satisfaction. Similarly, in the business-to-business (B2B) sector, more and more companies use chatbots on their websites and social media channels, to establish sales team contact, to provide information about their products and services or to help customers with their requests and claims. Customer relations in the B2B environment are especially characterized by a high level of personal contact service and support through expert explanations due to the complexity of the products and service offerings. In order to support these efforts, chatbots can be used to assist buying centers along the purchase decision process. However, B2B chatbots have so far only been marginally addressed in the scientific human-computer interaction and information systems literature. To provide both researchers and practitioners with knowledge about the characteristics and archetypal patterns of chatbots currently existing in B2B customer services, we develop and discuss a 17-dimensional chatbot taxonomy for B2B customer services based on Nickerson et al. [1]. By classifying 40 chatbots in a cluster analysis, this study has identified three archetypal structures prevailing in B2B customer service chatbot usage.
Article
Chatbots have been around for years and have been used in many areas such as medicine or commerce. Our focus is on the development and current uses of chatbots in the field of education, where they can function as service assistants or as educational agents. In this research paper, we attempt to make a systematic review of the literature on educational chatbots that address various issues. From 485 sources, 80 studies on chatbots and their application in education were selected through a step‐by‐step procedure based on the guidelines of the PRISMA framework, using a set of predefined criteria. The results obtained demonstrate the existence of different types of educational chatbots currently in use that affect student learning or improve services in various areas. This paper also examines the type of technology used to unravel the learning outcome that can be obtained from each type of chatbots. Finally, our results identify instances where a chatbot can assist in learning under conditions similar to those of a human tutor, while exploring other possibilities and techniques for assessing the quality of chatbots. Our analysis details these findings and can provide a solid framework for research and development of chatbots for the educational field.
Chapter
In the present study, we developed a chatbot service termed ‘CiSA’ (Chatbot for International Students and Academics) to enable international students and academics to effectively acquire essential information regarding their academic and campus life. To investigate the pain points and needs of our target user group, user research consisting of interviews and surveys was conducted. Based on the key findings from qualitative analysis, the concept was further refined. A flowchart was constructed to illustrate the designed conversations, while the user interface components were determined to express the responses of the chatbot. The design was further prototyped using Google’s DialogFlow, and implemented in Facebook Messenger. Finally, the interviews with the target users were conducted to verify the effectiveness, satisfaction, and extensibility of the service. The outcome of this study provides a powerful way to support the facilitation of communication and social inclusion by using this conversational agent. Furthermore, by focusing on enhancing the accessibility, the research contributes towards the practical understanding of the investigation of its service design for chatbot aimed at inclusivity.
Chapter
Recently, it is often considered that chatbots can reduce customer service costs and handle a number of customers at the same time and thus, they have been widely used for administrative work. In this study, we developed a chatbot for Frequently Asked Questions (FAQs) in a college and deployed it to students and department offices. We then conducted an experiment with two offices, with and without chatbot, to analyze whether the introduction of chatbot affects the administrative workload. Office workers’ workloads were measured using the National Aeronautics and Space Administration Task Load Index (NASA-TLX) questionnaire in addition to observations and the log data of chatbot usage. This report contains our findings and analysis of how the introduction of chatbot influenced the administrative work patterns and the workers’ perceived workload.
Conference Paper
Advances in conversational AI have the potential to enable more engaging and effective ways to teach factual knowledge. To investigate this hypothesis, we created QuizBot, a dialogue-based agent that helps students learn factual knowledge in science, safety, and English vocabulary. We evaluated QuizBot with 76 students through two within-subject studies against a flashcard app, the traditional medium for learning factual knowledge. Though both systems used the same algorithm for sequencing materials, QuizBot led to students recognizing (and recalling) over 20% more correct answers than when students used the flashcard app. Using a conversational agent is more time consuming to practice with, but in a second study, of their own volition, students spent 2.6x more time learning with QuizBot than with flashcards and reported preferring it strongly for casual learning. Our results in this second study showed QuizBot yielded improved learning gains over flashcards on recall. These results suggest that educational chatbot systems may have beneficial use, particularly for learning outside of traditional settings.
Conference Paper
The application of automatic conversational system (chatbot) in learning foreign language is still limited. In this study, we built a chatbot dedicated to English learners. The system is named English Practice is installed on the mobile devices to interact with users through a window chat. Chatbot is able to automatically remind learners to study and suggest some answers to multiple choice questions. It also has the ability to help users in learning vocabulary and new lessons. The result shows that most of the basic functions of the system are used by the users and this this promises to be applied widely in the future.
Conference Paper
Elective course selection often challenges students to make decisions concerning their academic interests and other practical issues such as graduation plan, class scheduling, and difficulty of course content. Conversations with academic advisors and peers are usually considered as a useful process for obtaining official and informal information, rearranging priorities, and making compromise in the decision. The paper describes the design and development of a conversational agent called EASElective for elective course selection. EASElective is designed to complement existing academic advising services with an online natural language interactive interface that will support a conversation on topics from basic official course data to informal students’ opinions. The major design components of EASElective include intent detection, routines for conversation management, dialogue design, sustainable students’ opinion collection and analysis, and course information management. The paper also describes a study on the perceived usefulness of EASElective. The findings were found to be largely positive and EASElective has unique functions and characteristics when compared to other conventional academic advising services.
Chapter
This work presents some initial results of our research about the design and implementation of “LiSA” (Link Student Assistant), a chatbot intended to help students in their campus life, through information and services. The focus of our research is to understand which kind of information and services are better accessed through this kind of touch point, how the chatbot personality influences the user experience and the interaction and which level of intelligence should be implemented. After an analysis of the state of the art in the considered application domain we investigated, through a survey, the users’ needs and their inclination to the use of a chatbot for this specific purpose. A chatbot was created to deliver the survey, allowing to understand both the users’ needs and their behavior while using the tool.
Article
Dialogue systems have attracted more and more attention. Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as computer vision, natural language processing, and recommender systems. For dialogue systems, deep learning can leverage a massive amount of data to learn meaningful feature representations and response generation strategies, while requiring a minimum amount of hand-crafting. In this article, we give an overview to these recent advances on dialogue systems from various perspectives and discuss some possible research directions. In particular, we generally di- vide existing dialogue systems into task-oriented and non- task-oriented models, then detail how deep learning techniques help them with representative algorithms and finally discuss some appealing research directions that can bring the dialogue system research into a new frontier.
Conference Paper
A conversational agent also referred to as chatbot is a computer program which tries to generate human like responses during a conversation. Earlier chatbots employed much simpler retrieval based pattern matching design techniques. However, with time a number of new chatbots evolved with an aim to make it more human like and hence to pass the Turing test. Now, most of the chatbots employ generative knowledge based techniques. This paper will discuss about various chatbot design techniques, classification of chatbot and discussion on how the modern chatbots have evolved from simple pattern matching, retrieval based model to modern complex knowledge based models. A table of major conversational agents in chronological order along with their design techniques is also provided at the end of the paper.
Conference Paper
Since distance education creates new opportunities for learners, the enrollment in online courses has been sharply increasing in higher education. However, the higher attrition rate is one of the more significant concerns in this field. Educational researchers have found that meaningful interactions play a significant role in learner persistence in online courses. Still, it is challenging for an individual instructor to promote learners’ positive interaction experiences. The expectation of improved learners’ interaction with conversational agent systems has received attention in the distance education field. Few conversational agent systems have been developed for educational purposes, and few systems are used in real online learning settings. This study aims at designing and developing a conversational agent system to promote the learner’s meaningful interaction in online courses, and also exploring the feasibility of human interaction with the conversational agent system, or chatbot, in online courses in higher education. The primary findings of this study show that instant, content-related, and quality interactions between the learner and the conversational agent system is applicable to graduate-level online courses. Implications and future research are discussed.