Generative AI in teacher education: Using AI-enhanced methods to explore teacher educators’ perceptions

Abstract

The release of ChatGPT in November 2022 has sparked discussions about integrating Generative Artificial Intelligence (GenAI) into teacher education. Teacher educators, as key facilitators of pre-service teachers, play a critical role in determining the successful adoption of GenAI. Their perceptions guide curriculum redesign, define best practices, and shape pre-service teachers’ experiences with GenAI, potentially multiplying its impact across future classrooms. This mixed-methods study explored Danish teacher educators’ perceptions of GenAI (n = 91), focusing on its transformative potential, challenges, and the knowledge pre-service teachers need to acquire. The study employed innovative methods, including GenAI-enhanced thematic analysis and Natural Language Processing, to analyze qualitative and quantitative data. Results highlight diverse perceptions, ranging from enthusiasm for fostering innovative teaching practices (AI didactics) to concerns about ethical implications, assessment challenges (AI assessment), and safeguarding basic skill acquisition. Teacher educators emphasized the need for pre-service teachers to acquire AI literacies—AI as a teaching tool, content, and learning tool—framed within ethical, cultural, and democratic boundaries. Mediation analyses revealed that intrinsic motivation and confidence significantly predicted teacher educators’ use of GenAI, fully mediating their perceptions of its potential. Findings highlight the importance of professional development initiatives that offer hands-on GenAI experiences and informal, collaborative opportunities to address its rapid development. This study highlights GenAI’s transformative potential for teacher education and the complex skillset pre-service teachers need to engage critically and responsibly, ensuring its integration aligns with educational and societal values.

Full text

Generative AI in teacher education:
Using AI-enhanced methods to explore teacher educators’ perceptions
Christopher Neil Prilop1, Dana-Kristin Mah2, Lucas Jasper Jacobsen3, Rasmus R. Hansen4, Kira Elena
Weber5, Fabian Hoya6
Abstract
The release of ChatGPT in November 2022 has sparked discussions about integrating Generative
Artificial Intelligence (GenAI) into teacher education. Teacher educators, as key facilitators of pre-
service teachers, play a critical role in determining the successful adoption of GenAI. Their perceptions
guide curriculum redesign, define best practices, and shape pre-service teachers’ experiences with
GenAI, potentially multiplying its impact across future classrooms. This mixed-methods study explored
Danish teacher educators’ perceptions of GenAI (n = 91), focusing on its transformative potential,
challenges, and the knowledge pre-service teachers need to acquire. The study employed innovative
methods, including GenAI-enhanced thematic analysis and Natural Language Processing, to analyze
qualitative and quantitative data. Results highlight diverse perceptions, ranging from enthusiasm for
fostering innovative teaching practices (AI didactics) to concerns about ethical implications, assessment
challenges (AI assessment), and safeguarding basic skill acquisition. Teacher educators emphasized the
need for pre-service teachers to acquire AI literacies—AI as a teaching tool, content, and learning tool—
framed within ethical, cultural, and democratic boundaries. Mediation analyses revealed that intrinsic
motivation and confidence significantly predicted teacher educators’ use of GenAI, fully mediating their
perceptions of its potential. Findings highlight the importance of professional development initiatives
that offer hands-on GenAI experiences and informal, collaborative opportunities to address its rapid
development. This study highlights GenAI’s transformative potential for teacher education and the
complex skillset pre-service teachers need to engage critically and responsibly, ensuring its integration
aligns with educational and societal values.
Keywords: Generative Artificial Intelligence, Teacher Educators, AI Literacy, Mixed-Methods
Research, Teacher Education, AI in Education, AI Usage Behavior, Intrinsic Motivation
1 Centre for Educational Development, Aarhus University, Aarhus, Denmark, e-mail: cnp@au.dk, ORCID: 0000-0001-9629-
4127
2 Institute of Educational Science, Leuphana University, Lueneburg, Germany, e-mail: dana-kristin.mah@leuphana.de,
ORCID: 0009-0004-2106-2216
3 Institute of Educational Science, Leuphana University, Lueneburg, Germany, e-mail: lucas.jacobsen@leuphana.de, ORCID:
0009-0001-6967-3751
4 Centre for Educational Development, Aarhus University, Aarhus, Denmark, e-mail: rasmushansen@au.dk, ORCID: 0009-
0003-5390-6092
5 Institute for Vocational Training and Lifelong Learning, University of Hamburg, Hamburg, Germany, e-mail:
kira.weber@uni-hamburg.de, ORCID: 0000-0002-6564-9578
6 Institute for Primary Education and Learning Development, University College of Teacher Education Vorarlberg,
Feldkirch, Austria, e-mail: fabian.hoya@ph-vorarlberg.ac.at, ORCID: 0000-0003-4077-0635

1. Introduction
With the release of ChatGPT in November 2022, teacher education institutions and educators have been
discussing how to incorporate Generative Artificial Intelligence (GenAI) into their educational programs.
Teacher educators' perceptions of GenAI's role in teacher education will guide curriculum redesign,
define the best practices they promote, and shape how they support pre-service teachers' early
experiences with GenAI in teaching practice (Korthagen, 2016; Moorhouse & Kohnke, 2024). As teacher
educators play a crucial role in determining the practices and beliefs of pre-service teachers (Bai &
Ertmer, 2008), their integration of GenAI into teacher education is likely to have a multiplying effect.
After teacher education, pre-service teachers will transfer their educational experiences to future
classrooms, impacting school students. Hence, teacher educators’ perceptions of GenAI in teacher
education play a significant role in determining its successful adoption both at teacher education
institutions and at schools.
In general, research shows that higher education teachers are slow to adopt new technologies (Liu
et al., 2020). However, GenAI, such as ChatGPT or Claude, differ from prior educational technology
concerning its accessibility, versatility, and pervasive nature in society in general (Kasneci et al., 2023).
Due to their capabilities, GenAI tools are seen as a disruptor of the status quo in education but also a
catalyst for rethinking learning and teaching (Jensen et al., 2024). Researchers attest GenAI potential to
positively impact education, however, also harm student learning (Abbas et al., 2024; Hansen et al., 2024;
Kasneci et al., 2023). Consequently, educators acknowledge that they have to adapt rapidly to the
opportunities and challenges brought on by GenAI (e.g., McGrath et al., 2023; Moorhouse & Kohnke,
2024). Despite their crucial role, teacher educators’ perceptions are underexplored. To date, only
Moorhouse and Kohnke (2024) have examined English language teacher educators' perceptions of
GenAI, focusing on the early months following ChatGPT's release, a time when institutions and
educators were just beginning to adapt to this emerging technology.
This study therefore examined teacher educators' perceptions of the potential impact of AI on
teacher education and the essential knowledge pre-service teachers need to acquire. To better understand
the factors shaping teacher educators' perceptions, the study also investigated the roles of confidence,
intrinsic motivation, and teacher educators’ use of AI in teaching. Using a mixed-methods approach, the
study collected both qualitative and quantitative data from teacher educators teaching at all Danish

teacher education institutions. In addition to traditional methods, the research incorporated innovative
techniques, such as Natural Language Processing and GenAI-enhanced thematic analysis.
Consequently, this study sheds light on teacher educators’ perceptions of AI in teacher education
and factors shaping these. It offers insights into reimagining teaching and learning in the GenAI era and
outlines the skills that teacher educators believe pre-service teachers must develop. Based on this, the
study thus highlights key areas for professional development and identifies essential components of AI
literacy for teacher education programs. Furthermore, it provides insights into how Natural Language
Processing and GenAI can assist qualitative and quantitative-qualitative data analysis in educational
research.
2. Literature review
2.1 Opportunities and challenges of GenAI in education
GenAI tools are based on large language models trained on massive amounts of data and have impacted
the educational landscape due to their accessibility and diverse applications. In response to prompts (e.g.,
instructions, questions) they generate new, human-like content (e.g., images, text) and imitate human
abilities and skills, such as identifying patterns or making decisions (Kasneci et al., 2023; Sheikh et al.,
2023). This technical capability presents significant opportunities in education, for enhancing student
learning and reducing teacher workload. From a learner perspective, key benefits of GenAI tools in
educational contexts include tailored support for individual learning needs, personalized feedback, or
creating new learning situations with artificial conversation partners (Kasneci et al., 2023; Wu & Zu,
2023). While these capabilities can promote student learning, they also require educators to rethink
teaching, learning, and assessment (Mah et al., 2023; Dawson et al., 2024; Jensen et al., 2024). From an
educator's perspective, a professional use of GenAI tools can also be beneficial to their work. GenAI
tools can assist with organizational tasks, lesson planning, materials preparation, and assessment,
allowing for a more focused approach to individual student support (Celik et al., 2022; Jensen et al.,
2024)
However, despite the potential outlined, the integration of GenAI tools in education is not without
its pitfalls. Increased reliance on GenAI tools could risk limiting a person’s ability to solve problems
independently as well as their critical thinking, interpersonal competencies, and retention of core
academic skills (Farrokhnia et al, 2023; Kasneci et al., 2023). Furthermore, users need to be capable to

evaluate GenAI output to detect misinformation generated by GenAI tools (Ng et al., 2023). In addition,
the integration of GenAI is challenging traditional assessment practices. GenAI tools make it difficult to
verify independent authorship in student work. Hence, the educational community is currently debating
when GenAI should be integrated into assessments tasks (Dawson et al., 2024; Lodge et al., 2023).
2.2 The need for AI literacy in education
Given GenAI's transformative potential in education, educators need to be enabled to use AI tools
effectively to harness its benefits while mitigating its risks. Hence, educators need to acquire AI literacy.
A notable definition of AI literacy, as proposed by Long and Magerko (2020), characterizes it as "a set
of competencies that enable individuals to critically evaluate AI technologies, communicate and
collaborate effectively with AI, and use AI as a tool online, at home, and in the workplace" (p. 2). This
definition has evolved to differentiate between generic AI literacy, a fundamental understanding of AI,
and domain-specific AI literacy, which pertains to AI applications in specific fields such as medicine or
education (Mah & Groß, 2024; Knoth et al., 2024; Ng et al., 2021).
In education, AI literacy represents a significant challenge for educators and students (Bond et
al., 2023; Ifenthaler et al., 2024). Emotional and motivational barriers, such as anxiety and discomfort,
further complicate AI literacy adoption (Yang et al., 2025). In light of the recent advances and rise of
generative AI, a number of institutions have begun providing guidelines and developing frameworks to
enhance AI literacy for both educators and students (Celik, 2023a; Chiu et al., 2024; Wang & Lester,
2023). For instance, the TPACK framework has been adapted to the GenAI era (Mishra & Koehler, 2006;
Mishra et al., 2023). TPACK consists of three major components of teacher knowledge: content (CK),
pedagogy (PK), and technology (TK) with their intersections of pedagogical content knowledge (PCK),
technological pedagogical knowledge (TPK), and technological content knowledge (TCK) (Mishra &
Koehler, 2006). Celik (2023b) extended the TPACK framework with the knowledge of ethical aspects
and proposed the Intelligent TPACK framework. UNESCO (2024) introduced a global AI competency
framework for educators, highlighting competencies such as human-centered mindset, AI ethics, and AI
pedagogy. Concerning AI pedagogy, educators require the “capacity to critically adapt and creativity
explore innovative practices in the context of advancing capabilities of emerging AI iterations” (p. 23).

2.3 The role of teacher educators in AI adoption
In teacher education, teacher educators can be assumed to have significant impact on how pre-service
teachers acquire AI literacy and, as a result, how GenAI is implemented in pre-service teachers’ future
classrooms (Moorhouse & Kohnke, 2024). Teacher educators bridge theory and practice by
demonstrating professional teaching through explicit methods, such as lectures and tutorials, while
implicitly modeling reflective and innovative teaching practices. Furthermore, they help pre-service
teachers integrate theoretical knowledge with practical learning opportunities (European Commission,
2013). Beyond their teaching role, teacher educators contribute significantly to curriculum development.
They delineate learning outcomes, guide pre-service teachers, and assess their progress (Korthagen,
2016; Moorhouse & Kohnke, 2024).
Teacher educators’ perceptions guide their educational practices (Pajares, 1992). Perceptions are the
opinions, beliefs, and attitudes that individuals hold about particular topics or issues. They reflect how
individuals perceive, interpret, and respond to their environment (Abel et al., 2022; Zhai, 2024).
Educators’ perceptions are formed by their experiences (Pajares, 1992). Perceptions are influenced by,
for example, a person’s intrinsic motivation or confidence to engage with educational technology
(Ayanwale et al., 2022; Deci & Ryan, 2000; Ertmer, 2005). In the context of teacher education, intrinsic
motivation and confidence may lead teacher educators to use GenAI tools themselves and alter their
perception of the value of these tools for teacher education. Hence, understanding teacher educators’
perceptions of GenAI and factors contributing to them is essential for addressing potential
misconceptions and equipping them to integrate GenAI effectively into educational practices. However,
to date, there has only been one study (Moorhouse & Kohnke, 2024) focusing specifically on teacher
educators’ perceptions of AI from the first months of ChatGPT availability (April 2023). Moorhouse and
Kohnke interviewed thirteen teacher educators at universities in Hong Kong offering language education.
Their findings indicate that participants anticipate GenAI tools will have a significant impact on the
curriculum, instruction, and assessment. Participants believed they could play a crucial role in modeling
the use of GenAI tools, but felt they lacked guidance concerning assessment in a GenAI world. The
majority of participants expressed concerns about their own AI literacy in effectively addressing the
challenges and opportunities posed by these tools.
Research regarding technology in general and not focusing on teacher education exclusively, offers
additional insights. Concerning technology in general, research consistently indicates that higher

education teachers tend to adopt new technologies at a slow pace (Liu et al., 2020). Teacher educators,
at times, struggle to recognize the rationale for integrating technology (Ngao et al., 2022). Contributing
factors include educators' anxiety about adopting new technologies (Zimmerman, 2006) and a tendency
to remain within their comfort zones, relying on familiar materials and methodologies (Tallvid, 2016).
Educators who view GenAI as tools that enhance their instructional practices are more inclined to adopt
its use in the classroom (Kaplan-Rakowski et al., 2023). In general, GenAI may lead to a different
response. Moorhouse and Kohnke (2024) found that teacher educators perceived GenAI as a
”fundamentally different technology from other technological advances” (p. 8). This is supported by
findings from the general higher education field. Ofosu-Ampong (2024) found that a large amount of
higher education teachers expressed willingness to accept AI integration. Furthermore, Mah & Groß
(2024) found that higher education faculty saw greater equity in education as the biggest benefit of AI,
while the lack of AI literacy among students and faculty was among the greatest challenges. In addition,
faculty members were highly interested in pursuing professional development opportunities in the field
of AI. McGrath et al. (2023) found participants assessed their AI literacy and the impact on equity
differently. Higher education teachers reported concerns about AI adoption, including fears and
skepticism regarding its fairness and ethical implications, as well as a lack of knowledge and resources
needed to integrate AI effectively into teaching practices.
3. Research questions
Against this background, this article investigates the following research questions:
a) What are teacher educators’ perceptions of the potential of AI for teacher education?
b) How do intrinsic motivation, confidence, and the use of AI in teaching influence teacher
educators’ perceptions about the potential of AI in teacher education?
c) Which AI knowledge do teacher educators perceive as crucial for pre-service teachers?
4. Method
4.1 Sample and procedure
Participants from all university colleges in Denmark were invited to participate in the study. Data were
collected between May and June 2024. E-mails with a link to the survey on SurveyXact were sent to
publicly available e-mail addresses of teacher educators listed on the respective institutions' websites.

In total, 91 teacher educators (59.3% female, 38.9% male, 1.1% no disclosure) completed the
survey. They were largely from the age groups 50-59 (36.3%) and 60-69 (34.1%) (30-39 years old -
3.3%, 40-49 – 9.9%, 70 or older – 15.4%, no disclosure – 1.1%) and had a large variation of teaching
experience at university college (3-6 years – 25.3%, 7-9 – 12.1%, 10-19 – 13.2%, 20-29 – 25.3%, 30-39
– 20.9%, 40 or more – 3.3%). Most participants were either associate professors (64.8%) or assistant
professors (26.4%) and employed at one of the VIA university colleges (33%) (Absalon – 7.7%,
Copenhagen - 11%, Lillebælt – 9.9%, Nordjylland – 11%, Syd – 11%, no disclosure – 16.5%). The
response rate of 13.13% (693 teacher educators invited) was comparable to similar open survey studies
(e.g., Byman et al., 2020).
Ethical approval for the study was obtained from the Ethics Review Board at [blinded for peer
review] ([ethics approval number]). All participants received written information detailing their rights,
the study's purpose, its procedures, and provided active consent before participation.
4.2 Instruments
Participants completed subscales on intrinsic motivation for learning about AI and confidence of using
AI from the AI literacy questionnaire developed by Ng et al. (2023). The scale on intrinsic motivation
consists of four items (e.g., I am curious about discovering new AI technologies.). Teacher educators'
confidence of using AI was assessed with five items (e.g., I can make good use of AI related tools.).
Teacher educators were asked to judge the statements on a 6-point Likert scale, ranging from “strongly
disagree” to “strongly agree”. Internal consistency coefficients (Cronbach’s αintrinsic motivation = .82,
αconfidence = .85) were good.
To assess teacher educators’ use of AI for teaching, we developed items based on a recent AI study
(von Garrel et al., 2023). The scale consists of eleven items focusing on different uses of AI in the
teaching context (e.g., In the context of my teaching, I use AI for creating teaching materials for myself.;
In the context of my teaching, I use AI to generate feedback for students.). Teacher educators rated the
statements on a 5-point Likert scale, ranging from “not at all” to “very often”. Cronbach’s α showed
excellent internal consistency, α = .91.

4.3 Teacher educators’ perceptions
The survey contained two open-ended questions. The questions were based on previous studies
(Antonenko & Abramowitz, 2023; Moorhouse & Kohnke, 2024) that explored educators’ perceptions of
AI in education. Teacher educators were asked, "What do you think about the potential of AI to influence
teacher education?” and “What do you think is important for student teachers to understand about AI?”.
While answers to both questions were analyzed using thematic analysis (for details see below), sentiment
analysis was conducted on answers to the first question to be able to analyze the qualitative data in
combination with the quantitative data. For sentiment analysis (Falcon & Leon, 2023) it was important
to use an open-ended question that allows participants to consider both positive and negative possibilities,
enabling them to explore both benefits and drawbacks of AI’s impact on teacher education.
The sentiment analysis was conducted using the pre-trained model provided by Asent. It utilizes
natural language processing methods, like tokenization, to extract features from textual data. Hence, it
divides the text into units of analysis called tokens. Applying mathematical algorithms to comprehend
the context and meaning of the text, it classifies the units of analysis into different sentiments. Asent
utilizes a weighted lexicon of word sentiments and uses a rules-based approach to calculate the impact
of syntactical variables such as negation and amplifiers (Enevoldsen, 2022).
4.4 Data analysis
4.4.1 Quantitative analyses
Due to the limited sample size and insufficient statistical power for structural equation modeling, we
decided to work solely with manifest variables. The statistical analysis was conducted using IBM SPSS
Statistics 29. Missing data were handled using multiple imputation (5 imputations) to ensure a more
robust analysis. Pooled data was used for subsequent analyses.
To analyze the relationships between teacher educators' confidence in using AI, intrinsic
motivation for learning about AI, use of AI for teaching, and their perceptions, Pearson correlation
analyses were performed. The significance level was set at .05 for all analyses.
Two mediation analyses were conducted employing the IBM SPSS PROCESS 4.3.1 macro
(Hayes, 2022; Model 4). As preliminary diagnostics showed a violation of linearity, the dependent
variable (teacher educators’ perceptions) was log-transformed to meet the assumption of linearity for

regression analysis. Following this procedure, all necessary assumptions (linearity, normality,
homoscedasticity, multicollinearity) for mediation analysis were met. Mediation analyses were
performed using bootstrapping with 5000 samples to generate 95% confidence intervals for the indirect
effect. The first mediation analysis assessed whether the relationship between teacher educators’ intrinsic
motivation for learning about AI and their perceptions is mediated by their use of AI for teaching
(mediator variable). The second mediation analysis tested whether the association between teacher
educators’ confidence of using AI and their perceptions is mediated by their use of AI for teaching
(mediator variable).
4.4.2 Qualitative analyses
Teacher educators’ answers to the open-ended questions, “What do you think about the potential of AI to
influence teacher education?” and “What do you think is important for student teachers to understand
about AI?”, were analyzed thematically following Braun and Clarke (2006). The thematic analysis was
enhanced by incorporating GenAI into the process (Morgan, 2023).
4.4.2.1 Procedure
Themes and sub-themes were identified applying a six-step coding procedure. Two of the authors
conducted the thematic analysis. First, the authors read and reread teacher educators’ answers to the
questions to gain an overview of the data. Second, the authors generated a first set of codes, formulated
themes and sub-themes, and cross-checked the codes and (sub-)themes for consistency. Third, the authors
used GenAI (for a detailed description see below) to conduct an additional thematic analysis. An
additional GenAI analysis can be used as a type of balance to possible researcher bias, i.e., themes
prevalent in researchers’ conceptions due to the deep involvement in the research field, to identify
overlooked themes (Moorhouse & Kohnke, 2024). Fourth, the authors reviewed and discussed the initial
(sub-)themes and the GenAI (sub-)themes. This was concluded by clarifying, combining, refining, and
agreeing on the (sub-)themes. Fifth, the entire data set was re-read, coding relevant sections of teacher
educators’ answers to each (sub-)theme. No new themes emerged at this stage. Sixth, after completing
the coding procedure, the authors generated conclusions from the material. The authors presented and
defended their individual conclusions and agreed or challenged the conclusions of each other (Peterson
& Irving, 2008).

4.4.2.2 GenAI-support of the thematic analysis
The thematic analysis was supported by GenAI. The researchers worked with an Ollama User
Interface, hosted through the High Performance Computing service Ucloud, allowing GDPR-compliant
computational services for Danish researchers. The Ollama provided a chatbot interface in which the
researchers could interact with the LLM (Llama 3.1 8b model; benchmarked above GPT 3.5-turbo and
slightly below GPT 4o).
In the following the procedure of the first thematic analysis is exemplified. The researchers used
the GenAI chatbot to identify any themes that were overlooked in the material. In the second step of the
thematic analysis, the researchers identified the themes AI literacy, AI didactics, and AI assessment in
the material. The researchers then prompted the chatbot to analyze the material in the third step: “Use
inductive thematic analysis following Braun and Clarke’s (2006) approach. Identify themes in this data
set. The data consists of answers to an open-ended survey question posed to teacher educators. The
teacher educators were asked: What do you think about the potential of AI for teacher education?”
(See Appendix 1 for the GenAI output). As the GenAI themes did not match the researchers’ coding (see
Figure 1), the GenAI themes lead the researchers to reconsider their themes and discuss possible
alterations. The GenAI analysis identified overarching valence themes (awareness and acceptance,
challenges and concerns) that the researchers perceived as sub-themes of AI literacy, didactics, and
assessment. The valence themes could also be expected due to the phrasing of the open-ended question.
Furthermore, it identified the theme integration and professional development, which seemed to combine
multiple themes. Therefore, the researchers prompted the chatbot again to produce a more detailed
analysis of this theme (prompt: “Theme 3 (Integration and professional development) is very broad.
Please analyze if this theme can be divided into more specific themes.”). The second iteration of the
GenAI analysis supported the researchers’ initial thematic analysis with the theme AI-enhanced teaching
practices combining AI didactics and assessment. The theme teacher education and professional
development fit the researchers’ AI literacy theme in scope. After considering the GenAI analysis, the
researchers again decided to keep AI assessment a separate theme as teacher educators indicated more
urgency regarding assessment in comparison to didactics. Concerning the researchers’ AI literacy theme
and the GenAI theme, teacher education and professional development made apparent a difference in
focus between the analyses. The GenAI analysis focused on what teacher educators require for AI
literacy, while the researchers emphasize AI literacy as a theme with professional development as a

supporting factor. However, the GenAI analysis also highlighted collaboration and knowledge-sharing
that the researchers had overlooked. Due to the rapid developments in the field of AI, formal professional
development may not suffice and make informal collaboration and knowledge-sharing necessary.
Therefore, the researchers incorporated this component into the AI literacy theme. Though the GenAI
analysis had definite shortcomings by focusing stronger on surface features or providing excerpts that
did not fully fit themes it had generated, the researchers considered supporting the thematic analysis with
GenAI as extremely beneficial as it forced them to question their themes and defend them in light of the
GenAI themes. Hence, this analytical step increases the rigor and objectiveness of the thematic analysis
making it more trustworthy (Morgan, 2023).
Figure 1. Comparison of themes identified by the researchers and GenAI.
5 Results
5.1 Quantitative analyses
Descriptive statistics (see Table 1) for teacher educators showed, that they have a medium to high degree
of intrinsic motivation for learning about AI, are fairly confidence of using AI, have slightly positive

perceptions of AI in teacher education, but seldomly make use of AI for teaching. The correlation matrix
indicates significant positive correlations between the variables of the study (see Table 1).
Table 1: Means (M), standard deviations (SD) and bivariate Pearson correlations of variables
M
SD
1.
2.
3.
1. Intrinsic motivation for learning about AI
3.79
0.92
2. Confidence of using AI
4.17
0.84
.60**
3. Perceptions of the potential of AI for teacher education
0.14
0.27
.18
.21
4. Use of AI for teaching
1.92
0.87
.51**
.35*
.30**
Note: Intrinsic motivation/ confidence of using, Min = 1, Max = 6, perceptions, Min = -1, Max = 1; use of AI,
Min = 1, Max = 6, *p < .01, **p < .001.
The first mediation analysis (see Figure 2) with intrinsic motivation as independent variable showed that
intrinsic motivation significantly predicted teacher educators’ use of AI for teaching, with the model
accounting for 25.75% of the variance, R2=.2575, F(1,91)=177.87, p<.001. Intrinsic motivation had a
significant positive effect on teacher educators’ use of AI, b=.4817, t(91)=13.34, p<.001, 95% CI [.4107,
.5526]. Teacher educators’ use of AI mediated the association between intrinsic motivation and
perceptions of the potential of AI. The model explained 7.14% of the variance, R2=.0714, F (2,90)=19.70,
p<.001. While the use of AI had a significant positive effect on perceptions, b=.0990, t(90)=5.90, p<.001,
95% CI [.0661, .1320], the direct effect of intrinsic motivation did not reach significance level, b=.0183,
t(90)=-1.15, p=.25, 95% CI [.0496, .0130]. As the indirect effect was significant, b=.0477,
BootSE=.0080, 95% CI [.0319, .0636], this indicates that intrinsic motivation indirectly impacts teacher
educators’ perceptions of the potential of AI through increased use of AI for teaching.
Figure 2: Standardized regression coefficients for the relationship between intrinsic motivation and teacher
educators’ perceptions mediated by use of AI. Significant relationships marked with *, n.s. = not significant.

The second mediation analysis (see Figure 3) with confidence of using AI as independent variable
showed that confidence significantly predicted use of AI, explaining 20.66% of the variance, R2=.2066,
F(1,91)=133.56, p<.001. Confidence had a significant positive effect on teacher educators’ use of AI,
b=.4737, t(91)=11.56, p<.001, 95% CI [.3932, .5543]. As in the first mediation analysis, teacher
educators’ use of AI mediated the relationship between confidence and perceptions of the potential of
AI. The model accounted for 7.03% of the variance, R2=.0703, F(2,90)=19.35, p<.001. The direct effect
of confidence was not significant, b=-.0140, t(90)=-824, p=.41, 95% CI [.0472, .0193]. However, the use
of AI had a significant positive effect on perceptions, b=.0953, t(90)=5.87, p<.001, 95% CI [.0634,
.1272]. The significant indirect effect, b=.0451, BootSE=.0079, 95% CI [.0300, .0614], suggests that
confidence indirectly influences teacher educators’ perceptions of the potential of AI through increased
use of AI for teaching.
Figure 3: Standardized regression coefficients for the relationship between confidence and teacher educators’
perceptions mediated by use of AI. Significant relationships marked with *, n.s. = not significant.
5.2 Qualitative analyses
5.2.1 Perceptions of the potential of AI for teacher education
The first thematic analysis revealed three distinct themes: AI literacy, AI didactics, and AI assessment.
In general, teacher educators’ perceptions ranged between extremely negative views, neutral acceptance,
and positive assertions. When commenting on AI in teacher education, participants expressed mixed
emotions stating that they were “curious and concerned” or find it “interesting and scary”. Other teacher
educators view it clearly negative emphasizing that AI “should be avoided as far as possible” or that they
are “concerned about AI's dumbing down of education - that it becomes a ‘sausage factory’, where AI

churns out generic texts, lesson plans, and analyses”. On the contrary, some educators show positive
anticipation stating that “It will be exciting how AI can support and challenge education”. However,
teacher educators acknowledge that AI will impact teacher education and, therefore, needs to be
thoughtfully implemented or as one educator stated:
AI affects all societal practices, including education and especially teacher education. It is unavoidable
and already happening, so for me, the influence is not potential; it is already there. We must be clear about
which parts of our profession are essential to "safeguard" from AI and which parts can appropriately meet
the profession in particularly planned ways. We must understand AI both as an Ed-tech and as a Tech-ed
phenomenon.
Overall, these assertions suggest that teacher educators are still in the early stages of navigating how to
integrate AI into teacher education, and that this process is ongoing and evolving.
The thematic analysis reflected this concerning the three themes. Teacher educators perceive
different areas of teacher education (literacy, didactics, assessment) impacted to varying degree by AI.
AI literacy was perceived as a necessary base to adjust teacher education programs to the AI age,
however, was focused on less than AI didactics and AI assessment. Teacher educators perceived that
they are forced to take AI into account concerning assessment but not necessarily regarding didactics.
AI literacy
It became evident from teacher educators’ answers that they perceive AI literacy as a central element of
future teacher education, both for pre-service teachers and teacher educators. As one teacher educator
highlighted, “AI has great potential, and both I and the students need to learn to relate to and use AI
where it makes sense. It is necessary to maintain a critical view of AI for both me and my students.”. The
ability to critically interact with AI tools is a common theme across teacher educators’ responses and is
directly linked to AI didactics. ”Integrating AI into education (which I certainly think we should) places
great demands on how we organize teaching and learning so that students do not just put a prompt into
ChatGPT to answer a teacher-set task. So critical use of AI is essential.” Teacher educators also
highlighted the need to “collaborate on AI in teacher education” and to “have an open and inclusive
culture in teacher education, so we can approach AI critically and share knowledge”. Hence, AI tools are
constantly evolving making an informal knowledge-sharing culture necessary so that teacher educators
stay up to date. A teacher educator also emphasized that pre-service teachers need to be AI literate to
responsibly take on their roles as future multipliers of knowledge:

In a democratic society where AI (probably) will play a big role, all elementary school students should
learn to interact with AI in a constructive and critical way that supports their deep learning and
opportunities to express themselves personally, appropriately, and creatively. This requires teacher
students to work critically with the technology - to experience AI's possibilities and limitations.
AI didactics
In their responses, teacher educators often touched upon how teacher education needs to rethink its
approach to teaching and learning. Teacher educators ascribed AI a transformative power. As one teacher
educator highlighted, “People are rushing around and are afraid of cheating in exams, but it requires a
completely different focus to educate students”. Hence, while the focus for many educators lies on areas
such as assessment that are directly affected by the possibilities of AI tools, teacher education will need
to adjust as a whole. As one teacher educator states, “There is a great need for us to develop a didactic
approach to using AI”. However, teacher educators see that AI tools already enable new ways of learning
by using them to aid in developing teaching ideas, function as sparring or dialogue partners in planning
teaching, or “create learning experiences where teacher students can practice classroom scenarios and
gain practical experience in a ‘playful’ environment”. Yet, teacher educators also perceive negative
aspects of AI integration. They emphasize that it challenges the traditional understanding of learning and
“accelerates the movement away from basic skills”. Thus, teacher educators need to develop new ways
to ensure basic skills are acquired despite pre-service teachers engaging with AI tools. While most see a
need in rethinking teacher education didactics, one teacher educator stated that they “do not think it has
much impact yet. It is on the periphery […]”.
AI assessment
Teacher educators felt most strongly about the impact AI has on assessment practices partially
questioning the future of written exams entirely. “How should we construct written exams in the future
(if we should continue having them at all) so that they are meaningful?” While it is a common theme in
teacher educators’ responses that they “need to rethink some of the ‘old-fashioned’ assignment and exam
formats”, two distinct approaches to this process of rethinking can be observed. Some teacher educators
consider designing exams in a way that exclude the possibility of AI use or testing pre-service teachers’
knowledge acquisition differently. Others encourage the use of AI and think there is “a need to
incorporate it into exams in the future”, possibly as an “active collaborator” in the assessment task.

5.2.2 Teacher educators’ perceptions of essential AI knowledge for pre-service teachers
The second thematic analysis revealed that teacher educators concentrated on two overarching AI literacy
domains but also mentioned a third. Dominant themes were AI literacy for teaching with AI tools (AI as
a teaching tool) and AI literacy for teaching about AI (AI as teaching content). A third theme emerged
that focuses on pre-service teachers’ requiring AI literacy to anticipate the unintended use of AI tools by
students (AI as a learning tool).
In their responses, teacher educators often touched upon that pre-service teachers require
knowledge on how AI tools work that enables them to use it for their own teaching but also to teach their
students about proper usage. Hence, teacher educators often drew on the interplay between knowledge
components concerning AI as a teaching tool, as content, and as a learning tool. This shows how the
integration of AI into education differs from most prior technologies. At the same time, teachers need to
use it for their own teaching, anticipate student use, and be able to teach about it.
AI as a teaching tool and AI as teaching content
First and foremost, teacher educators assessed that technological knowledge about how AI tools work is
a prerequisite for technological pedagogical knowledge, i.e., knowledge about how AI tools can support
teaching and learning. As one teacher educator emphasized, “My students [pre-service teachers] must
understand what AI can do, what it cannot, and how to best use it in their work as teachers.” This involves
not only knowledge about the functionality of AI tools and the effective integration into teaching, but
also taking the broader societal and democratic context into consideration. Hence, pre-service teachers
need to be aware that their use of AI tools in the classroom will also have impact outside the educational
sphere.
The interplay of knowledge components in relation to society is, for example, highlighted by a
teacher educator writing:
It is most important to understand the challenges that AI brings. It is crucial for future professional
bachelor students to understand and take care of what AI can be beneficially used for and what it should
not be used for, such as in a learning context. AI will eventually become a democratic issue, and
professional bachelors will have significant influence on how this democratic issue is managed in their
professions.
Therefore, a large number of teacher educators emphasizes that future teachers require critical thinking
skills concerning ethical challenges. As a teacher educator phrases it, “Teacher students should be

educated in the ethical use of AI in educational environments, including handling privacy, bias, and
security issues.”, pre-service teachers need to develop “a critical-constructive mindset when encountering
AI” or be critical and take into account “ethical considerations about its cultural significance”.
When teachers need to educate their students concerning AI, their technological knowledge shifts
to content knowledge about AI. This content knowledge is required to guide students to “work creatively
and constructively with AI”. As one teacher educator warns, pre-service teachers will need to “teach
students to use it [AI tools] correctly – we must not end up with another ‘digital natives’ fiasco where
we fail to address technology and do not provide children with the skills to navigate it”.
However, appropriate integration of AI into teaching does not only require knowledge about AI.
Teacher educators also highlighted that strong content knowledge of their teaching subjects is crucial to
interact with AI tools and judge the quality of their output. “They have no control over AI’s output – they
must always be able to assess it by relying on their professionalism. They must still know all the subject-
specific and pedagogical theories and be able to apply them in practice.” Pre-service teachers need to be
able to “evaluate whether the output a machine provides is ethically and professionally sound”.
AI as a learning tool
Although only few teacher educators touch on it, some emphasize that pre-service teachers require AI
literacy because they “will enter a school context where students use AI”. Therefore, they need to be
prepared to “navigate a world where students can also use” AI tools. These responses indicate that future
teachers need to take into account that students may use AI tools in their school tasks although they were
not implemented in the task by the teacher or have not been taught to use and assess the tools by the
teacher. Thus, AI literacy is needed to anticipate the unintended or possible use of AI tools by students.
6 Discussion
The study explored teacher educators’ perceptions of the potential impact of AI on teacher education and
their perceptions of what knowledge pre-service teachers required. Additionally, factors (intrinsic
motivation, confidence, use of AI for teaching) contributing to their perceptions of the potential of AI
were analyzed. Thematic analysis revealed distinct themes concerning the potential impact (AI literacy,
AI didactics, AI assessment) and AI literacy domains (AI as a teaching tool, AI as a learning tool, AI as

teaching content). Furthermore, teacher educators’ use of AI for teaching was a crucial mediating factor
in their perceptions of the potential impact of AI.
Concerning the potential impact of AI on teacher education, our results indicate that teacher
educators' views of AI range from extremely negative, to neutral, to positive. This is consistent with
research showing four distinct profiles of higher education teachers’ perceptions of the benefits and
challenges of AI-based tools for teaching and learning: optimistic, critical, critically reflective, and
neutral (Mah & Groß, 2024). However, Mah & Groß’ (2024) study analyzed higher education teachers’
perceptions across disciplines, while our study focuses on teacher educators. Furthermore, this supports
Moorhouse and Kohnke’s (2024) finding that teacher educators in general acknowledge that GenAI will
have a significant impact on teacher education.
The mediation analyses revealed that intrinsic motivation and confidence significantly predicted
teacher educators’ use of AI for teaching. The use of AI for teaching fully mediated the relationship
between intrinsic motivation or confidence and teacher educators’ perceptions. These findings concur
with prior research that shows that educators’ attitudes toward AI are influenced by their familiarity with
and understanding of its functionalities (Zhai, 2024; Kaplan-Rakowski et al., 2023). Deci and Ryan
(2000) underline the importance of intrinsic motivation to foster engagement and curiosity. Our results
are in line with this, as they show, that educators are more likely to use AI when they hold more intrinsic
motivation for learning about AI. Furthermore, studies show that institutional support and educators’
confidence play crucial roles in AI acceptance and integration (Mah & Groß, 2024; Ofosu-Ampong,
2024; Moorhouse & Kohnke, 2024). Our study extends these findings, indicating that educators who are
confident in using AI tools not only adopt them more readily but also develop a more positive perception
of their educational potential. As there is evidence that a lack of knowledge and resources hinders AI
integration (McGrath et al., 2023), our findings emphasize that institutions should promote professional
development courses concerning AI. Educators who have worked with AI tools often gain practical
insights into their capabilities, enabling them to overcome initial concerns (Zimmerman, 2006). Hence,
our findings support that professional development courses should offer hands-on experiences in trying
out AI tools for classroom practice and at the same time foster teacher educators’ intrinsic motivation
and enhance their confidence. However, results from the first thematic analysis also indicate that teacher
educators’ see a need for informal learning opportunities for knowledge-sharing on AI. Building AI
literacy in a collaborative manner can serve to mitigate the negative impact of anxiety and discomfort in

AI integration and can help teacher educators continuously gain knowledge in a constantly evolving
environment (Yang et al., 2025).
As teacher educators play a crucial role as multipliers, their perceptions could have significant
influence on how future teacher education, and consequently, teaching in schools develops (Korthagen,
2016; Moorhouse & Kohnke, 2024). The thematic analyses revealed what professional development
initiatives could focus on to enable teacher educators to take on their role as multipliers responsibly.
In our study, teacher educators saw a need to acquire sufficient knowledge and skills to critically
interact with AI tools (AI literacy), both for teacher educators and pre-service teachers. This critical
stance reflects teacher educators’ concerns of the educational and ethical implications voiced by
participants in McGrath et al.’s (2023) study but also that teacher educators see how GenAI can enhance
educational practices (e.g., Kasneci et al., 2023). It echoes Long and Magerko’s (2020) definition of AI
literacy as "a set of competencies that enable individuals to critically evaluate AI technologies” (p. 2).
As mentioned above, concurring with prior research (Mah & Groß, 2024; McGrath et al., 2023), teacher
educators see a need for professional development. Specifically, they see a need for informal forms of
professional development, focusing on collaboration and knowledge-sharing, to keep up with the rapid
development and changes in the field of GenAI. Hence, research should investigate how teacher
educators engage with informal learning opportunities or how such opportunities can be supported, for
example, with digital GenAI courses (Mah & Hense, 2021). Concurring with the literature (e.g., Jensen
et al., 2024; Kasneci et al., 2023; Moorhouse & Kohnke, 2024), teacher educators see transformative
potential in GenAI integration into their teaching (AI didactics) by creating new learning experiences for
pre-service teachers. However, they also recognize the need to develop strategies for ensuring basic
skills, reflecting concerns about students becoming overly dependent on GenAI tools (Bozkurt et al.,
2024; Tlili et al., 2023). Contrary to Moorhouse and Kohnke (2024), teacher educators did not seem fully
aware of how their didactical approaches play an important modeling role for pre-service teachers. This
may be due to teacher educators perceiving a stronger urgency to reconceptualize assessments. Thus, the
modeling effect of teacher educators should be emphasized in professional development initiatives.
Regarding assessment (AI assessment), two distinct approaches – GenAI inclusion and GenAI exclusion
– were identified. Teacher educators seemed to perceive the strongest immediate impact of GenAI in this
area. Moorhouse and Kohnke (2024) made similar findings. However, it remains uncertain whether
teacher educators have made significant progress in reconceptualizing assessment, as they still appear to

lack clear guidelines even two years after the introduction of ChatGPT. Moorhouse and Kohnke (2023)
reported this finding for data collected in April 2023, whereas our data collection occurred a year later.
This shows that clear guidelines are required for assessment in the age of artificial intelligence (e.g.,
Lodge et al., 2023). However, the prevalent focus on assessment and not teaching (AI didactics) reveals
that teacher educators do not think of teaching and assessment as intertwined. This can lead to teacher
educators concentrating too much on assessment, without taking the need to rethink their teaching into
account. This could lead to teaching that is detached from students' reality in a world where GenAI is
omnipresent. Hence, teacher education institutions need to define when assessment with or without
artificial intelligence is applicable (Dawson et al., 2024).
Teacher educators’ perceptions of required AI knowledge for pre-service teachers are likely to
impact future teacher education curricula and which components concerning AI literacy they will
integrate into their teaching. The thematic analysis revealed that teacher educators grasp the complexity
of AI literacy for future teachers. Three AI literacy themes emerged: AI as a teaching tool, AI as teaching
content, and AI as a learning tool. This triadic perspective highlights the multifaceted challenges pre-
service teachers face in the GenAI era (see Figure 2). Hence, AI literacy is not just teaching-specific but
teaching situation-specific.

Figure 2: The triadic nature of AI literacy in the teaching profession. (The original TPACK image was adapted for
our figure. Reproduced by permission of the publisher, © 2012 by tpack.org).
The individual themes incorporated knowledge components of the TPACK model (Mishra &
Koehler, 2006) to different extents. The AI as a teaching tool theme mostly reproduces the components
of the original TPACK model. By building on technological knowledge, technological pedagogical
knowledge, and technological content knowledge, pre-service teachers need to acquire technological
pedagogical content knowledge (TPACK) to effectively apply GenAI for teaching purposes. However,
the content knowledge component diverges from Mishra and Koehler’s original conceptualization by
being a necessary prerequisite to judge the quality of GenAI tool outputs. In the context of GenAI, teacher
educators also highlighted that pre-service teachers need to be able to master AI as teaching content.
Hence, the critical-constructive mindset that teachers must develop for effectively using AI as a teaching
tool should also be instilled in their students. From this perspective on teachers’ AI literacy, technological
knowledge shifts to content knowledge. Content knowledge about GenAI becomes the primary focus
supported by technological content knowledge and pedagogical content knowledge. The AI literacy focus
changes again when AI is used as a learning tool by students. From this perspective teachers’ pedagogical
knowledge becomes most important in combination with technological pedagogical knowledge and
pedagogical content knowledge. Given the accessibility, versatility, and widespread use of GenAI,

teachers must anticipate that students may use GenAI tools even when the tasks assigned do not explicitly
call for them. Consequently, pre-service teachers need to develop the skills to either design learning
environments that render the use of GenAI unnecessary or implement strategies to mitigate potential
negative impacts of GenAI use in educational contexts. However, this AI literacy perspective was only
mentioned by few teacher educators. Yet, this is an important perspective to take into account and needs
to be highlighted for pre-service teachers in professional development courses. Otherwise, this could
result in a negative impact at school level, if future teachers believe they do not require any AI literacy
because they do not use or teach AI tools themselves (e.g., AI as a teaching tool, AI as content). The AI
as a learning tool perspective emphasizes the necessity of AI literacy for all teachers.
All three perspectives on AI literacy in the teaching profession (teaching tool, teaching content,
learning tool) are framed by ethical, cultural, democratic context. This aligns and extends Celik’s (2023b)
intelligent TPACK model. While Celik focuses on the ethical dimension, teacher educators additionally
highlighted the cultural and democratic dimensions that need to be included in a critical stance on GenAI.
Hence, these contextual knowledge components need to guide all GenAI teaching and learning in the
classroom. In sum, the findings highlight the complexity of AI literacy in the teaching profession and the
necessity to take all perspectives into account to prepare pre-service teachers for the challenges posed by
GenAI in education. While most teacher educators recognize the need for pre-service teachers to acquire
AI literacy regarding AI as a teaching tool and content, AI literacy concerning AI as a learning tool must
also become a key focus on teacher educators’ agenda. Contrary to the UNESCO (2024) competency
framework, this especially includes AI literacy to anticipate the unintended use of GenAI tools by
students in the learning process.
6.1 Limitations & Future Research
While this study offers valuable contributions, it also has several limitations that future research should
consider. First, the sample size, though representative of all Danish university colleges offering teacher
education, was small. Although our response rate is comparable to similar open survey studies (e.g.,
Byman et al., 2020), response bias might have led to an overrepresentation of educators with strong
opinions about AI – whether positive or negative – potentially skewing the results. Second, while the
cross-sectional design allows for examining correlations, it inherently limits causal inferences and does
not capture changes over time. Nevertheless, at this exploratory stage of educational GenAI research, we

deem this approach appropriate for providing a broad overview of teacher educators’ perceptions,
offering valuable baseline insights. Future studies employing longitudinal designs could build on these
findings to explore how perceptions of (Gen)AI evolve dynamically over time. Third, the use of broad
open-ended questions facilitated the capture of diverse perspectives in the qualitative part of the study.
While we perceive it a key strength offering a comprehensive understanding of the landscape at this
early-stage, future studies could adopt more extensive qualitative approaches (e.g., semi-structured
interviews) to explore specific themes in greater depth, even if this requires focusing on a smaller number
of educators. Such a progression would complement the broader insights gained here. Finally, this study
was conducted exclusively within Danish teacher education institutions, which operate in a highly
digitalized socio-cultural and educational context. While this focus may limit the generalizability of the
findings to countries with differing educational systems, it is interesting to note that our results echo the
findings from other educational contexts (e.g., general higher education). By addressing these limitations,
future research can refine and build on the insights presented, contributing to a deeper and more
comprehensive understanding of teacher educators’ engagement with AI.
6.2 Conclusion
This study contributes to the understanding of teacher educators’ perceptions of AI in education.
We employed a mixed-method design including the use of GenAI-enhanced thematic analysis to
investigate the perceptions of teacher educators. We found that incorporating AI enhanced support was
beneficial in terms of encouraging self-reflection on the analysis results. However, it is essential to note
that AI-enhanced methods should be used as a supplementary tool, rather than as a substitute for the
expertise of researchers (Ullman et al. 2023; Park et al., 2024).
Our findings highlight the diverse perceptions of teacher educators on GenAI, ranging from
enthusiasm for its transformative potential to apprehension regarding its challenges and implications.
Our findings align with prior research, highlighting the need to build teacher educators’ AI literacy (e.g.,
McGrath et al., 2023; Moorhouse & Kohnke, 2024). The mediation analyses revealed the importance of
teacher educators personal use of GenAI in teaching. Therefore, teacher education institutions should
focus on professional development courses that offer hands-on experiences with AI tools (Rampelt et al.,
in press). However, beyond formal training, teacher education institutions must also explore strategies to
implement informal, collaborative knowledge-sharing opportunities. These are necessary for

continuously fostering critical, ethical, and reflective engagement with GenAI (AI literacy). Our findings
further indicate that teacher educators recognize GenAI’s potential to transform teaching practices (AI
didactics) by creating innovative learning opportunities. However, they also emphasize the importance
of safeguarding basic skill acquisition. Furthermore, the urgent need to reconceptualize assessments
emerged as a key theme (AI assessment). Hence, teacher education institutions need to provide clear
guidelines for the use of GenAI in assessments to prevent a disconnect between teaching practices and
the learning realities of students in the GenAI-era (Lodge et al., 2023; Dawson et al., 2024).
Finally, this study emphasizes the multifaceted nature of AI literacy. Extending on the
conceptualizations of Mishra et al. (2006) and Celik (2023b), teacher educators indicated that pre-service
teachers need to acquire multiple AI literacies – AI as a teaching tool, AI as content, and AI as a learning
tool – all framed within ethical, cultural, democratic boundaries. Especially the possibly unintended use
of GenAI by students highlights the necessity of AI literacy for all teachers, regardless of their
willingness to implement GenAI in their classrooms. By addressing these interconnected dimensions,
institutions can prepare both teacher educators and pre-service teachers to critically and confidently
engage with GenAI, ensuring its integration aligns with educational and societal values (Bećirović &
Mattoš, 2024; Ifenthaler et al., 2024).

Declaration of generative AI and AI-assisted technologies in the writing process
During the preparation of this work the authors used ChatGPT 4o in order to improve readability and
language of the work. After using this tool, the authors reviewed and edited the content as needed and
take full responsibility for the content of the publication.
References
Abbas, M., Jam, F. A., & Khan, T. I. (2024). Is it harmful or helpful? Examining the causes and
consequences of generative AI usage among university students. International Journal of
Educational Technology in Higher Education, 21(1). https://doi.org/10.1186/s41239-024-00444-7
Abel, V., Tondeur, J. & Sang, G. (2022). Teacher Perceptions about ICT Integration into Classroom
Instruction. Education Sciences, 12, 609. https://doi.org/10.3390/educsci12090609
Almatrafi, O., Johri, A., & Lee, H. (2024). A systematic review of AI literacy conceptualization,
constructs, and implementation and assessment efforts (2019–2023). Computers and Education
Open, 6. https://doi.org/10.1016/J.CAEO.2024.100173
Ayanwale, M. A., Sanusi, I. T., Adelana, O. P., Aruleba, K. D., & Oyelere, S. S. (2022). Teachers’
readiness and intention to teach artificial intelligence in schools. Computers and Education:
Artificial Intelligence, 3, 100099.
Antonenko, P. & Abramowitz, B. (2023) In-service teachers’ (mis)conceptions of artificial intelligence
in K-12 science education. Journal of Research on Technology in Education, 55(1), 64-78.
https://doi.org/10.1080/15391523.2022.2119450
Bai, H., & Ertmer, P.A. (2008). Teacher educators’ beliefs and technology uses as predictors of
preservice teachers’ beliefs and technology attitudes. Journal of Technology and Teacher
Education, 16(1), 93-112.
Bećirović, S. (2023). Digital Pedagogy. The Use of Digital Technologies in Contemporary Education.
Springer Nature Singapore. https://doi.org/10.1007/978-981-99-0444-0
Bećirović, S., & Mattoš, B. (2024), "Artificial Intelligence in the Transformation of Higher Education:
Threats, Promises and Implementation Strategies", Lytras, M.D., Serban, A.C., Alkhaldi, A., Malik,
S., & Aldosemani, T. (Ed.) Digital Transformation in Higher Education, Part A (Emerald Studies

in Active and Transformative Learning in Higher Education), Emerald Publishing Limited, Leeds,
pp. 23-43. https://doi.org/10.1108/978-1-83549-480-620241002
Bond, M., Khosravi, H., De Laat, M., Bergdahl, N., Negrea, V., Oxley, E., Pham, P., Chong, S. W., &
Siemens, G. (2023). A meta systematic review of artificial intelligence in higher education: A call
for increased ethics, collaboration, and rigour. International Journal of Educational Technology in
Higher Education, 21(1), 4. https://doi.org/10.1186/s41239-023-00436-z
Bozkurt, A., Xiao, J., Farrow, R., Bai, J. Y. H., Nerantzi, C., Moore, S., Dron, J., Stracke, C. M.,
Hrastinksi, S., Garcia, M. B., Singh, L., Crompton, H., Koutropoulos, A., Terentev, E., Pazurek,
A., Nichols, M., Sidorkin, A. M., Costello, E., Watson, S., … Asino, T. I. (2024). The Manifesto
for Teaching and Learning in a Time of Generative AI: A Critical Collective Stance to Better
Navigate the Future. Open Praxis, 16(4), 487. https://doi.org/10.55982/openpraxis.16.4.777
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in
Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Byman, R., Jyrhämä, R., Stenberg, K., Maaranen, K., Sintonen, S., & Kynäslahti, H. (2020). Finnish
teacher educators’ preferences for their professional development – quantitative
exploration. European Journal of Teacher Education, 44(4), 432–451.
https://doi.org/10.1080/02619768.2020.1793952
Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The Promises and Challenges of Artificial
Intelligence for Teachers: a Systematic Review of Research. TechTrends, 66(4), 616–630.
https://doi.org/10.1007/s11528-022-00715-y
Celik, I. (2023a). Exploring the Determinants of Artificial Intelligence (AI) Literacy: Digital Divide,
Computational Thinking, Cognitive Absorption. Telematics and Informatics, 83.
https://doi.org/10.1016/J.TELE.2023.102026
Celik, I. (2023b). Towards Intelligent-TPACK: An empirical study on teachers’ professional knowledge
to ethically integrate artificial intelligence (AI)-based tools into education. Computers in Human
Behavior, 138. https://doi.org/10.1016/j.chb.2022.107468
Chan, C. K. Y., & Hu, W. (2023). Students’ voices on generative AI: perceptions, benefits, and
challenges in higher education. International Journal of Educational Technology in Higher
Education, 20(1). https://doi.org/10.1186/S41239-023-00411-8/TABLES/5

Chiu, T. K. F., Ahmad, Z., Ismailov, M., & Sanusi, I. T. (2024). What are artificial intelligence literacy
and competency? A comprehensive framework to support them. Computers and Education Open,
6. https://doi.org/10.1016/J.CAEO.2024.100171
Davis, F. D. (1986). A technology acceptance model for empirically testing new end-user information
systems: Theory and results. Doctoral dissertation. MIT Sloan School of Management.
https://dspace.mit.edu/handle/1721.1/15192
Davis, F. D., & Granić, A. (2024). The Technology Acceptance Model: 30 Years of TAM.
SpringerBriefs in Human-Computer Interaction. Springer. https://doi.org/10.1007/978-3-030-
45274-2
Dawson, P., Bearman, M., Dollinger, M. & Boud, D. (2024) Validity matters more than cheating,
Assessment & Evaluation in Higher Education, 49:7, 1005-1016,
https://doi.org/10.1080/02602938.2024.2386662
Deci, E. L., & Ryan, R. M. (2000). The “What” and “Why” of Goal Pursuits: Human Needs and the
Self-Determination of Behavior. Psychological Inquiry, 11(4), 227–268.
https://doi.org/10.1207/S15327965PLI1104_01
Delcker, J., Heil, J., Ifenthaler, D., Seufert, S., & Spirgi, L. (2024). First-year students AI-competence
as a predictor for intended and de facto use of AI-tools for supporting learning processes in higher
education. International Journal of Educational Technology in Higher Education, 21(1), 1–13.
https://doi.org/10.1186/S41239-024-00452-7
Deng, G., & Zhang, J. (2023). Technological pedagogical content ethical knowledge (TPCEK): The
development of an assessment instrument for pre-service teachers. Computers & Education, 197.
https://doi.org/10.1016/J.COMPEDU.2023.104740
Enevoldsen, K. (2022). Asent: Fast, flexible and transparent sentiment analysis (Version 0.4.0)
[Computer software]. Retrieved December 2, 2024 from
https://github.com/KennethEnevoldsen/asent
Ertmer, P.A. (2005. Teacher pedagogical beliefs: The final frontier in our quest for technology
integration?. Educational Technology Research & Development, 53, 25–39.
https://doi.org/10.1007/BF02504683

European Commission. (2013). Supporting teacher educators for better learning outcomes. Thematic
Working Group ‘Teacher Professional Development. Retrieved December 2, 2024 from
http://ec.europa.eu/education/school-education/teacher-cluster_en.htm
Falcon, S., & Leon, J. (2023). How do teachers engaging messages affect students? A sentiment
analysis. Educational Technology Research and Development, 71, 1503–1523.
https://doi.org/10.1007/s11423-023-10230-3
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, 61(3), 460–474. https://doi.org/10.1080/14703297.2023.2195846
Fengchun, M., & Homes, W. (2023). Guidance for generative AI in education and research. UNESCO.
Retrieved December 2, 2024 from https://unesdoc.unesco.org/ark:/48223/pf0000386693
Fraillon, J., Ainley, J., Schulz, W., Friedman, T., & Duckworth, D. (2020). Preparing for life in a digital
world: IEA international computer and information literacy study 2018 international report.
Preparing for Life in a Digital World: IEA International Computer and Information Literacy Study
2018 International Report, 1–297. https://doi.org/10.1007/978-3-030-38781-5/COVER
Fraillon, J. (2024). An International Perspective on Digital Literacy. Results from ICILS 2023. IEA.
https://www.iea.nl/sites/default/files/2024-11/ICILS_2023_International_Report_0.pdf
Galindo-Dominguez, H., Delgado, N., Losada, D., & Etxabe, J.-M. (2024). An analysis of the use of
artificial intelligence in education in Spain: The in-service teacher's perspective. Journal of Digital
Learning in Teacher Education, 40(1), 41-56. https://doi.org/10.1080/21532974.2023.2284726
von Garrel, J., & Mayer, J. (2023). Artificial Intelligence in studies—use of ChatGPT and AI-based tools
among students in Germany. Humanities and Social Sciences Communications, 10, 799 (2023).
https://doi.org/10.1057/s41599-023-02304-7
Gimpel, H., Hall, K., Decker, S., Eymann, T., Lämmermann, L., Mädche, A., Rödlinger, M., Ruiner, C.,
Schoch, M., Schoop, M., Urbach, N., & Vandrik, S. (2023). Unlocking the Power of Generative AI
Models and Systems such as GPT-4 and ChatGPT for Higher Education: A Guide for Students and
Lecturers (p. 47). University of Hohenheim. Retrieved December 2, 2024 from https://digital.uni-
hohenheim.de/fileadmin/einrichtungen/digital/Generative_AI_and_ChatGPT_in_Higher_Educatio
n.pdf

Hansen, R. R., Hougaard, R. F., Lindberg, A. B., Møller, K. L., Nielsen, T. A., & Prilop, C. N. (2024,
September 2 - forthcoming). AI-prompted peer feedback: Can an AI feedback coach enhance peer
feedback quality?. https://doi.org/10.31219/osf.io/mq628
Hattie, J. (2023). Visible Learning: The Sequel (1st ed.). Routledge. ISBN: 978-1032462035
Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional process analysis.
(3rd Ed.). The Guilford Press.
Hébert, C., Jenson, J., & Terzopoulos, T. (2021). “Access to technology is the major challenge”: Teacher
perspectives on barriers to DGBL in K-12 classrooms. E-Learning and Digital Media, 18(3), 307-
324.
Ifenthaler, D., Majumdar, R., Gorissen, P., Judge, M., Mishra, S., Raffaghelli, J., & Shimada, A. (2024).
Artificial Intelligence in Education: Implications for Policymakers, Researchers, and Practitioners.
Technology, Knowledge and Learning. https://doi.org/10.1007/s10758-024-09747-0
Jensen, L.X., Buhl, A., Sharma, A. et al. (2024). Generative AI and higher education: a review of claims
from the first months of ChatGPT. Higher Education. https://doi.org/10.1007/s10734-024-01265-3
Johnston, H., Wells, R. F., Shanks, E. M., Boey, T., & Parsons, B. N. (2024). Student perspectives on
the use of generative artificial intelligence technologies in higher education. International Journal
for Educational Integrity, 20(1), 1–21. https://doi.org/10.1007/S40979-024-00149-4/TABLES/10
Kaban, A. L., and Ergul, I. B. (2020). Teachers’ attitudes towards the use of tablets in six EFL
classrooms. In Examining the Roles of Teachers and Students in Mastering New Technologies, ed.
P. Eva (Pennsylvania: IGI Global), 284–298. https://doi.org/10.4018/978-1-7998-2104-5.ch015
Kaplan-Rakowski, R., Grotewold, K., Hartwick, P., & Papin, K. (2023). Generative AI and teachers’
perspectives on its implementation in education. Journal of Interactive Learning Research, 34(2),
313-338. Retrieved December 2, 2024 from https://www.learntechlib.org/primary/p/222363/.
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G.,
Günnemann, S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J.,
Poquet, O., Sailer, M., Schmidt, A., Seidel, T., Stadler, M., & Kasneci, G. (2023). ChatGPT for
good? On opportunities and challenges of large language models for education. Learning and
Individual Differences, 103. https://doi.org/10.1016/j.lindif.2023.102274

Knoth, N., Decker, M., Laupichler, M. C., Pinski, M., Buchholtz, N., Bata, K., & Schultz, B. (2024).
Developing a holistic AI literacy assessment matrix – Bridging generic, domain-specific, and ethical
competencies. Computers and Education Open, 6. https://doi.org/10.1016/J.CAEO.2024.100177
Kolb, D. A. (2014). Experiential learning: Experience as the source of learning and development (2nd
ed.). Pearson FT Press. ISBN: 978-0-13-389250-5
Korthagen, F. (2016). Inconvenient truths about teacher learning: towards professional development
3.0. Teachers and Teaching, 23(4), 387–405. https://doi.org/10.1080/13540602.2016.1211523
Liu, Q., Geertshuis, S., & Grainger, R. (2020). Understanding academics' adoption of learning
technologies: A systematic review. Computers & Education, 151, 103857.
https://doi.org/10.1016/j.compedu.2020.103857
Lodge, J. M., S. Howard, M. Bearman, & P. Dawson (2023). Assessment Reform for the Age of Artificial
Intelligence. Canberra: Tertiary Education Quality and Standards Agency (TEQSA).
Long, D., & Magerko, B. (2020). What is AI Literacy? Competencies and Design Considerations.
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 1–16.
https://doi.org/10.1145/3313831.3376727
Lorenz, U., & Romeike, R. (2023). What Is AI-PACK? – Outline of AI Competencies for Teaching with
DPACK. SSEP 2023: Informatics in Schools. Beyond Bits and Bytes: Nurturing Informatics
Intelligence in Education, 13–25. https://doi.org/10.1007/978-3-031-44900-0_2
Lunenberg, M., Dengerink, J., & Korthagen, F. (2014). The professional teacher educator: Roles,
behaviour, and professional development of teacher educators. Rotterdam: Sense Publishers.
https://www.sensepublishers.com/
Mah, DK., Groß, N. Artificial intelligence in higher education: exploring faculty use, self-efficacy,
distinct profiles, and professional development needs. Int J Educ Technol High Educ 21, 58 (2024).
https://doi.org/10.1186/s41239-024-00490-1
Mah, D.-K., & Hense, J. (2021). Zukunftsfähige Formate für digitale Lernangebote – Innovative
didaktische Ansätze am Beispiel einer Lernplattform für Künstliche Intelligenz. In Hochschulforum
Digitalisierung (Hrsg.), Digitalisierung in Studium und Lehre gemeinsam gestalten: Innovative
Formate, Strategien und Netzwerke (S. 617–633). Springer VS. https://doi.org/10.1007/978-3-658-
32849-8_34

Mah, DK., Hense, J., Dufentester, C. (2023). Didaktische Impulse zum Lehren und Lernen mit und über
Künstliche Intelligenz. In: de Witt, C., Gloerfeld, C., Wrede, S.E. (eds) Künstliche Intelligenz in
der Bildung. Springer VS, Wiesbaden. https://doi.org/10.1007/978-3-658-40079-8_5
Martin, F., Zhuang, M. & Schaefer, D. (2024). Systematic review of research on artificial intelligence in
K-12 education (2017–2022). Computers and Education: Artificial Intelligence, 6, 1–18.
https://doi.org/10.1016/j.caeai.2023.100195
Masley, N., Fattorini, L., Perrault, R., Parli, V., Reuel, A., Brynjolfsson, E., Etchemendy, J., Ligett, K.,
Lyons, T., Manyika, J., Niebles, J. C., Shoham, Y., Wald, R., & Clark, J. (2024). The AI Index 2024
Annual Report. Stanford University. Retrieved December 2, 2024 from
https://aiindex.stanford.edu/wp-content/uploads/2024/04/HAI_AI-Index-Report-2024.pdf
McGrath, C., Pargman, T. C., Juth, N., & Palmgren, P. J. (2023). University teachers' perceptions of
responsibility and artificial intelligence in higher education-An experimental philosophical study.
Computers and Education: Artificial Intelligence, 4, 100139.
Mishra, P., & Koehler, M. J. (2006). Technological Pedagogical Content Knowledge: A Framework for
Teacher Knowledge. Teachers College Record: The Voice of Scholarship in Education, 108(6),
1017–1054. https://doi.org/10.1177/016146810610800610
Mishra, P., Warr, M., & Islam, R. (2023). TPACK in the age of ChatGPT and Generative AI. Journal of
Digital Learning in Teacher Education, 39(4), 235–251.
https://doi.org/10.1080/21532974.2023.2247480
Moorhouse, B., & Kohnke, L. (2024). The Effects of Generative AI on Initial Language Teacher
Education: The Perspectives of Teacher Educators. System, 122, 103290, 1-10.
https://doi.org/10.1016/j.system.2024.103290
Morgan, D. L. (2023). Exploring the use of artificial intelligence for qualitative data analysis: The case
of ChatGPT. International Journal of Qualitative Methods, 22, 1-10.
https://doi.org/10.1177/160940692312112
Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An
exploratory review. Computers and Education: Artificial Intelligence, 2.
https://doi.org/10.1016/j.caeai.2021.100041

Ng, D. T. K., Leung, J. K. L., Su, J., Ng, R. C. W. & Chu, S. K. W. (2023). Teachers’ AI digital
competencies and twenty-first century skills in the post-pandemic world. Cultural and Regional
Perspectives, 71, 137-162. https://doi.org/10.1007/s11423-023-10203-6
Ofosu-Ampong, K. (2024). Beyond the hype: exploring faculty perceptions and acceptability of AI in
teaching practices. Discover Educucation, 38(3). https://doi.org/10.1007/s44217-024-00128-4
Pajares, M. F. (1992). Teachers’ beliefs and educational research: Cleaning up a messy construct. Review
of Educational Research, 62(3), 307–332.
Park, J. S., Zou, C. Q., Shaw, A., Hill, B. M., Cai, C., Morris, M. R., ... & Bernstein, M. S. (2024).
Generative agent simulations of 1,000 people. arXiv preprint arXiv:2411.10109.
Peterson, E. R., & Irving, S. E. (2008). ‘Secondary students’ conceptions of assessment and feedback.
Learning and Instruction, 18, 238-250.
Pinski, M., & Benlian, A. (2024). AI literacy for users – A comprehensive review and future research
directions of learning methods, components, and effects. Computers in Human Behavior: Artificial
Humans, 2(1), 100062. https://doi.org/10.1016/J.CHBAH.2024.100062
Pratschke, B. M. (2024). Generative AI and Education. Digital Pedagogies, Teaching Innovation and
Learning Design. Springer Cham. https://doi.org/10.1007/978-3-031-67991-9
Rampelt, R., Ruppert, R., Schleiss, J., Mah, D.-K., Bata, K., & Egglofstein, M. (in press). How do AI
educators use Open Educational Resources? A cross-sectoral case study on OER for AI education.
Open Praxis.
Robert, J., & Muscanell, N. (2023). 2023 EDUCAUSE Horizon Action Plan: Generative AI. Retrieved
December 2, 2024 from https://library.educause.edu/-
/media/files/library/2023/9/2023horizonactplangenai.pdf
Ryan, R. M., & Deci, E. L. (2000). Self-determination theory and the facilitation of intrinsic motivation,
social development, and well-being. American Psychologist, 55(1), 68–78.
https://doi.org/10.1037/0003-066X.55.1.68
Sabzalieva, E., & Valentini, A. (2023). ChatGPT and Artificial Intelligence in Higher Education: Quick
Start Guide. https://www.iesalc.unesco.org/wp-content/uploads/2023/04/ChatGPT-and-Artificial-
Intelligence-in-higher-education-Quick-Start-guide_EN_FINAL.pdf
Southworth, J., Migliaccio, K., Glover, J., Glover, J., Reed, D., McCarty, C., Brendemuhl, J., & Thomas,
A. (2023). Developing a model for AI Across the curriculum: Transforming the higher education

landscape via innovation in AI literacy. Computers and Education: Artificial Intelligence, 4.
https://doi.org/10.1016/j.caeai.2023.100127
Sperling, K., Stenberg, C.-J., McGrath, C., Åkerfeldt, A., Heintz, F., & Stenliden, L. (2024). In search of
artificial intelligence (AI) literacy in teacher education: A scoping review. Computers and Education
Open, 6. https://doi.org/10.1016/J.CAEO.2024.100169
Stanford University. (2024). Introduction to the AI Index Report 2024. Retrieved December 2, 2024 from
https://aiindex.stanford.edu/wp-content/uploads/2024/04/HAI_AI-Index-Report-2024.pdf
Swennen, A., Jones, K., & Volman, M. (2010). Teacher educators: their identities, sub‐identities and
implications for professional development. Professional Development in Education, 36(1–2), 131-
148. https://doi.org/10.1080/19415250903457893
Tallvid, M. (2016). Understanding teachers’ reluctance to the pedagogical use of ICT in the 1:1
classroom. Education and Information Technologies, 21, 503–519. https://doi.org/10.1007/s10639-
014-9335-7
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), 1–24. https://doi.org/10.1186/S40561-023-00237-
X/FIGURES/13
Ullman, T.D. (2023). Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks.
ArXiv, abs/2302.08399.
UNESCO. (2024). AI competency framework for teachers. UNESCO.
https://doi.org/10.54675/ZJTE2084
Van der Klink, M., Kools, Q., Avissar, G., White, S., & Sakata, T. (2016). Professional development of
teacher educators: what do they do? Findings from an explorative international study. Professional
Development in Education, 43(2), 163–178. https://doi.org/10.1080/19415257.2015.1114506
von Garrel, J., & Mayer, J. (2023). Artificial Intelligence in studies—use of ChatGPT and AI-based tools
among students in Germany. Humanities and Social Sciences Communications, 10(1), 1–9.
https://doi.org/10.1057/s41599-023-02304-7
von Garrel, J., Mayer, J., & Mühlfeld, M. (2023). Künstliche Intelligenz im Studium Eine quantitative
Befragung von Studierenden zur Nutzung von ChatGPT & Co [Artificial Intelligence in Higher

Education: A Quantitative Survey of Students on the Use of ChatGPT & Co]. Hochschule
Darmstadt. https://doi.org/10.48444/h_docs-pub-395
Wang, B., Rau, P. L. P., & Yuan, T. (2023). Measuring user competence in using artificial intelligence:
validity and reliability of artificial intelligence literacy scale. Behaviour and Information
Technology, 42(9), 1324-1337. https://doi.org/10.1080/0144929X.2022.2072768
Wang, N., & Lester, J. (2023). K-12 Education in the Age of AI: A Call to Action for K-12 AI Literacy.
International Journal of Artificial Intelligence in Education, 33(2), 228-232.
https://doi.org/10.1007/S40593-023-00358-X/FIGURES/1
Webb, M. (2024, March 8). Our AI in Education Maturity Model - an update for 2024 - Artificial
intelligence. https://nationalcentreforai.jiscinvolve.org/wp/2024/03/08/our-ai-in-education-
maturity-model-an-update-for-2024/
Yang, Y., Xia, Q., Liu, C., & Chiu, T. K. F. (2025). The impact of TPACK on teachers’ willingness to
integrate generative artificial intelligence (GenAI): The moderating role of negative emotions and
the buffering effects of need satisfaction. Teaching and Teacher Education, 154.
https://doi.org/10.1016/J.TATE.2024.104877
Zhai, X. (2024). Transforming Teachers’ Roles and Agencies in the Era of Generative AI: Perceptions,
Acceptance, Knowledge, and Practices. Journal of Science Education and Technology.
https://doi.org/10.1007/s10956-024-10174-0
Zimmerman, J. (2006). Why some teachers resist change and what principals can do about it. NASSP
Bulletin. 90(3), 238-249. https://doi.org/10.1177/0192636506291521

Appendix 1
Thematic analysis 1
Screenshot of the GenAI interaction

Output:
Prompt 1:
Use inductive thematic analysis following Braun and Clarke’s (2006) approach. Identify themes in this
data set. The data consists of answers to an open ended survey question posed to teacher educators. The
teacher educators were asked: “What do you think about the potential of AI for teacher education?"
llama3:latest
Based on the provided context, I will use inductive thematic analysis following Braun and Clarke's
(2006) approach to identify themes in this data set.
After carefully reading through the answers, I identified three main themes:
Theme 1: Awareness and Acceptance
This theme is characterized by a sense of awareness and acceptance towards AI's potential impact on
teacher education. Respondents acknowledge that AI will have an effect on their profession and
express openness to exploring its possibilities. Examples from the data include:
• "AI påvirker os i alle andre sammenhænge, så selvfølgelig bør vi som læreruddannere også
forholde til det." (AI affects us in all other contexts, so of course we as teacher educators should
also be aware of it.)
• "Det er interessant, udfordrende og oplagt at undersøge, diskutere og forholde sig kritisk til på
læreruddannelsen." (It's interesting, challenging, and natural to investigate, discuss, and
approach critically on teacher education.)
Theme 2: Challenges and Concerns
This theme is marked by concerns about the potential challenges AI may bring to teacher education.
Respondents express worries about AI's impact on student learning, academic integrity, and teaching
practices. Examples from the data include:
• "Det bliver spændende at se indvirkningen nu her ift. eksamensperioden, hvor meget eller lidt
de har brugt AI." (It will be interesting to see the impact now during exam period, where much
or little they have used AI.)
• "Jeg er umiddelbart mest optaget af AI's påvirkning af skriftelige prøver og skriftlige opgaver
generelt." (I am immediately most concerned about AI's impact on written exams and general
written assignments.)

Theme 3: Integration and Professional Development
This theme is characterized by a desire to integrate AI into teacher education and professional
development. Respondents see AI as an opportunity for continuous learning, improved teaching
practices, and enhanced student engagement. Examples from the data include:
• "Det kan fx ændre på hvilke prøveformer man anvender - og det kan sagtens gå i en positiv
udvikling, så man anvender mere professionsrettede prøveformer." (It can change how we use
assessment forms - and it could go in a positive development, so we can use more profession-
oriented assessment forms.)
• "Jeg synes læreruddannelsen, dvs. læreruddannerne, bør lade AI være et værktøj til studiebrug,
som understøttes af læreruddannesen." (I think teacher education, i.e., teacher educators, should
allow AI to be a tool for study use, which is supported by teacher education.)
These three themes provide a comprehensive overview of the responses from the teacher educators
regarding the potential of AI for teacher education.
we identified the overall themes: AI literacy: Students and teachers knowledge and understanding of AI
AI didactics: The practice of teaching and learning with the emergence of AI in mind Assessment: The
change that AI imposes on exams.
Can you identify something that we have missed, that does not work within the three overall themes?
Prompt 2:
Your theme 3 (Integration and Professional Development), is very broad. Please analyze if this theme
can be sub-divided into more specific themes
llama3:latest
I'm glad you brought this up!
After re-analyzing the data, I think that Theme 3 (Integration and Professional Development) can
indeed be further sub-divided into more specific themes. Here's a possible breakdown:
Sub-theme 1: AI-enhanced Teaching Practices
• Examples from the data include:
o "Det kan fx ændre på hvilke prøveformer man anvender – og det kan sagtens gå i en
positiv udvikling, så man anvender mere professionsrettede prøveformer." (It can

change how we use assessment forms – and it could go in a positive development, so we
can use more profession-oriented assessment forms.)
o "Jeg synes læreruddannelsen, dvs. læreruddannerne, bør lade AI være et værktøj til
studiebrug, som understøttes af læreruddannesen." (I think teacher education, i.e.,
teacher educators, should allow AI to be a tool for study use, which is supported by
teacher education.)
This sub-theme explores the potential of AI to enhance teaching practices and improve student learning
outcomes.
Sub-theme 2: Teacher Education and Professional Development
• Examples from the data include:
o "Det er vigtigt at have en åben og inkluderende kultur i læreruddannelsen, så man kan
forholde sig kritisk til AI." (It's important to have an open and inclusive culture in
teacher education, so we can approach AI critically.)
o "Jeg tror, det er vigtigt at se på, hvordan vi kan bruge AI i læreruddannelsen, så vi kan
give studerende en bedre forståelse af, hvad AI er og hvordan de kan bruge det." (I think
it's important to look at how we can use AI in teacher education, so we can give students
a better understanding of what AI is and how they can use it.)
This sub-theme focuses on the importance of incorporating AI into teacher education and professional
development programs.
Sub-theme 3: Collaboration and Knowledge Sharing
• Examples from the data include:
o "Jeg tror, det er vigtigt at se på, hvordan vi kan samarbejde omkring AI i
læreruddannelsen." (I think it's important to look at how we can collaborate on AI in
teacher education.)
o "Det er vigtigt at have en åben og inkluderende kultur i læreruddannelsen, så man kan
forholde sig kritisk til AI og dele viden omkring AI." (It's important to have an open and
inclusive culture in teacher education, so we can approach AI critically and share
knowledge about AI.)
This sub-theme highlights the importance of collaboration, communication, and knowledge sharing
among teachers, educators, and other stakeholders when it comes to integrating AI into educational
settings.
Please let me know if you'd like me to further refine these sub-themes or explore any other aspects of
this theme!