Erkan Er
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Erkan Er has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Yannis Dimitriadis
Universidad de Valladolid
8 shared publications - Gökhan Akçapınar
Hacettepe University
7 shared publications - Alejandro Ortega-Arranz
Universidad de Valladolid
4 shared publications Ali Arifoglu
METU Informatics Institute, Turkey
4 shared publications- Paraskevi Topali
NOLAI | National Education Lab AI, Behavioural Science Institute, Radboud University, Nijmegen, Netherlands
4 shared publications - Alejandra Martínez-Monés
Universidad de Valladolid, Valladolid, Spain
3 shared publications
Latest Publications
- 10 November 2026
- Published by Taylor & Francis in Applied Measurement in Education
- p. 1-16
A Psychometric Evaluation of AI-Generated Vs. Human-Authored Programming Questions
1. Tests are fundamental to educational assessment, yet developing high-quality items is a process that is known to be costly, time-consuming, and expertise-demanding (Haladyna & Rodriguez, 2013). ...
- 10 November 2026
- Published by Taylor & Francis in Applied Measurement in Education
- p. 1-16
A Psychometric Evaluation of AI-Generated Vs. Human-Authored Programming Questions
1. Tests are fundamental to educational assessment, yet developing high-quality items is a process that is known to be costly, time-consuming, and expertise-demanding (Haladyna & Rodriguez, 2013). ...
- 27 June 2026
- Published by Springer Nature
- p. 326-331
AI and Human Peer Feedback in Introductory Programming: A Mixed Methods Study
- 27 June 2026
- Published by Springer Nature
- p. 326-331
AI and Human Peer Feedback in Introductory Programming: A Mixed Methods Study
- 27 February 2026
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 42 (2)
Hybrid Intelligence Feedback: A Model Proposal and Preliminary Study
Background: Although existing studies suggest that AI chatbots hold potential as feedback tools in educational settings, there remains a significant gap in the literature regarding pedagogically grounded frameworks or guidelines for their effective implementation. Therefore, there is very little experimental research on how to use an AI chatbot based on a pedagogical approach. Objectives: This study proposed a conceptual framework grounded in a hybrid intelligence feedback model for the use of AI chatbots as pedagogical feedback tools and aimed to examine its applicability and effectiveness within a higher education programming course. Method: An experimental pre‐test/post‐test study involving 36 undergraduate students was conducted to evaluate the effectiveness of the proposed model and its underlying design principles for integrating AI chatbots as pedagogically grounded feedback tools in educational settings. Results and Conclusions: Theory‐grounded AI chatbots based on the proposed hybrid intelligence feedback model and its design principles significantly improved learning more than the general‐purpose AI chatbot in programming class. Theory‐grounded AI chatbots can be an effective feedback tool in improving students' skills in self‐evaluation, critical thinking, and regulating learning strategies. General‐purpose AI chatbot feedback may cause “metacognitive laziness,” harming learning performance. Implications: The article indicates the need for further research and validation to ensure effective implementation and address challenges associated with AI's potential inaccuracies.
- 27 February 2026
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 42 (2)
Hybrid Intelligence Feedback: A Model Proposal and Preliminary Study
Background: Although existing studies suggest that AI chatbots hold potential as feedback tools in educational settings, there remains a significant gap in the literature regarding pedagogically grounded frameworks or guidelines for their effective implementation. Therefore, there is very little experimental research on how to use an AI chatbot based on a pedagogical approach. Objectives: This study proposed a conceptual framework grounded in a hybrid intelligence feedback model for the use of AI chatbots as pedagogical feedback tools and aimed to examine its applicability and effectiveness within a higher education programming course. Method: An experimental pre‐test/post‐test study involving 36 undergraduate students was conducted to evaluate the effectiveness of the proposed model and its underlying design principles for integrating AI chatbots as pedagogically grounded feedback tools in educational settings. Results and Conclusions: Theory‐grounded AI chatbots based on the proposed hybrid intelligence feedback model and its design principles significantly improved learning more than the general‐purpose AI chatbot in programming class. Theory‐grounded AI chatbots can be an effective feedback tool in improving students' skills in self‐evaluation, critical thinking, and regulating learning strategies. General‐purpose AI chatbot feedback may cause “metacognitive laziness,” harming learning performance. Implications: The article indicates the need for further research and validation to ensure effective implementation and address challenges associated with AI's potential inaccuracies.
- Top Cited PapersOpen Access
- 15 January 2025
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (9) , 12681-12707
AI in the classroom: Exploring students’ interaction with ChatGPT in programming learning
As being more prevalent in educational settings, understanding the impact of artificial intelligence tools on student behaviors and interactions has become crucial. In this regard, this study investigates the dynamic interactions between students and ChatGPT in programming learning, focusing on how different instructional interventions influence their learning and AI-interaction. Conducted over three sessions, students were allowed to use ChatGPT to complete programming tasks. The first session had no guidance, the second included hands-on training in prompt writing and effective ChatGPT use, and the third provided a lab guide with sample prompts. After each session, students took a post-test on the activity’s subject. Analyzing students’ prompting behaviors, five AI interaction profiles were identified: AI-Reliant Code Generators, AI-Reliant Code Generator & Refiners, AI-Collaborative Coders, AI-Assisted Code Refiners, and AI-Independent Coders. These profiles were examined to understand their evolution across interventions and their relationship with students’ learning performance. Findings revealed significant changes in profile distribution across interventions, and a notable difference between students’ post-test scores and their AI interaction profiles. Besides, training in prompting skills and effective use of AI significantly impacted students’ interactions with AI. These insights can contribute to the knowledge of integrating generative AI tools in education, highlighting how AI can enhance teaching practices. Understanding student-AI interaction dynamics can allow educators to tailor instructional strategies for optimal learning. This study also underscores the importance of guidance on effective AI use and prompting skills, which can lead students to use AI more meaningfully for their learning.
- 15 January 2025
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (9) , 12681-12707
Top Cited PapersOpen AccessAI in the classroom: Exploring students’ interaction with ChatGPT in programming learning
As being more prevalent in educational settings, understanding the impact of artificial intelligence tools on student behaviors and interactions has become crucial. In this regard, this study investigates the dynamic interactions between students and ChatGPT in programming learning, focusing on how different instructional interventions influence their learning and AI-interaction. Conducted over three sessions, students were allowed to use ChatGPT to complete programming tasks. The first session had no guidance, the second included hands-on training in prompt writing and effective ChatGPT use, and the third provided a lab guide with sample prompts. After each session, students took a post-test on the activity’s subject. Analyzing students’ prompting behaviors, five AI interaction profiles were identified: AI-Reliant Code Generators, AI-Reliant Code Generator & Refiners, AI-Collaborative Coders, AI-Assisted Code Refiners, and AI-Independent Coders. These profiles were examined to understand their evolution across interventions and their relationship with students’ learning performance. Findings revealed significant changes in profile distribution across interventions, and a notable difference between students’ post-test scores and their AI interaction profiles. Besides, training in prompting skills and effective use of AI significantly impacted students’ interactions with AI. These insights can contribute to the knowledge of integrating generative AI tools in education, highlighting how AI can enhance teaching practices. Understanding student-AI interaction dynamics can allow educators to tailor instructional strategies for optimal learning. This study also underscores the importance of guidance on effective AI use and prompting skills, which can lead students to use AI more meaningfully for their learning.
- Top Cited Papers
- 27 December 2024
- Published by Wiley in British Journal of Educational Technology
- Vol. 56 (3) , 1074-1091
Assessing student perceptions and use of instructor versus AI ‐generated feedback
Despite the growing research interest in the use of large language models for feedback provision, it still remains unknown how students perceive and use AI‐generated feedback compared to instructor feedback in authentic settings. To address this gap, this study compared instructor and AI‐generated feedback in a Java programming course through an experimental research design where students were randomly assigned to either condition. Both feedback providers used the same assessment rubric, and students were asked to improve their work based on the feedback. The feedback perceptions scale and students' laboratory assignment scores were compared in both conditions. Results showed that students perceived instructor feedback as significantly more useful than AI feedback. While instructor feedback was also perceived as more fair, developmental and encouraging, these differences were not statistically significant. Importantly, students receiving instructor feedback showed significantly greater improvements in their lab scores compared to those receiving AI feedback, even after controlling for their initial knowledge levels. Based on the findings, we posit that AI models potentially need to be trained on data specific to educational contexts and hybrid feedback models that combine AI's and instructors' strengths should be considered for effective feedback practices. Practitioner notes: What is already known about this topic Feedback is crucial for student learning in programming education. Providing detailed personalised feedback is challenging for instructors. AI‐powered solutions like ChatGPT can be effective in feedback provision. Existing research is limited and shows mixed results about AI‐generated feedback. What this paper adds The effectiveness of AI‐generated feedback was compared to instructor feedback. Both feedback types received positive perceptions, but instructor feedback was seen as more useful. Instructor feedback led to greater score improvements in the programming task. Implications for practice and/or policy AI should not be the sole source of feedback, as human expertise is crucial. AI models should be trained on context‐specific data to improve feedback actionability. Hybrid feedback models should be considered for a scalable and effective approach.
- 27 December 2024
- Published by Wiley in British Journal of Educational Technology
- Vol. 56 (3) , 1074-1091
Top Cited PapersAssessing student perceptions and use of instructor versus AI ‐generated feedback
Despite the growing research interest in the use of large language models for feedback provision, it still remains unknown how students perceive and use AI‐generated feedback compared to instructor feedback in authentic settings. To address this gap, this study compared instructor and AI‐generated feedback in a Java programming course through an experimental research design where students were randomly assigned to either condition. Both feedback providers used the same assessment rubric, and students were asked to improve their work based on the feedback. The feedback perceptions scale and students' laboratory assignment scores were compared in both conditions. Results showed that students perceived instructor feedback as significantly more useful than AI feedback. While instructor feedback was also perceived as more fair, developmental and encouraging, these differences were not statistically significant. Importantly, students receiving instructor feedback showed significantly greater improvements in their lab scores compared to those receiving AI feedback, even after controlling for their initial knowledge levels. Based on the findings, we posit that AI models potentially need to be trained on data specific to educational contexts and hybrid feedback models that combine AI's and instructors' strengths should be considered for effective feedback practices. Practitioner notes: What is already known about this topic Feedback is crucial for student learning in programming education. Providing detailed personalised feedback is challenging for instructors. AI‐powered solutions like ChatGPT can be effective in feedback provision. Existing research is limited and shows mixed results about AI‐generated feedback. What this paper adds The effectiveness of AI‐generated feedback was compared to instructor feedback. Both feedback types received positive perceptions, but instructor feedback was seen as more useful. Instructor feedback led to greater score improvements in the programming task. Implications for practice and/or policy AI should not be the sole source of feedback, as human expertise is crucial. AI models should be trained on context‐specific data to improve feedback actionability. Hybrid feedback models should be considered for a scalable and effective approach.
- 5 August 2024
- Published by Springer Nature
- p. 810-819
How a Learning Analytics Dashboard Intervention Influences the Dynamics of Students’ Learning Behavior
- 5 August 2024
- Published by Springer Nature
- p. 810-819
How a Learning Analytics Dashboard Intervention Influences the Dynamics of Students’ Learning Behavior
- Open Access
- 26 July 2024
- Published by Education Technology Theory and Practice in Eğitim Teknolojisi Kuram ve Uygulama
- Vol. 14 (2) , 198-217
IDENTIFYING BEHAVIORAL PATTERNS IN MOOC VIDEO ENGAGEMENT USING CLUSTERING APPROACH
Videos are the core components of MOOCs for delivering course content and teaching the core concepts effectively. While the literature provided strong and consistent evidence regarding the link between video engagement and the success in MOOCs, the research on video engagement behavior is still emerging and in demand of further research. This research aims to contribute to the literature by identifying behavioral patterns of video engagement in a MOOC and reveal the association of these patterns with success and failure. In particular, we employed simple video engagement metrics with an attempt to identify clusters of behavioral patterns that can be applied to different contexts. Acknowledging that students may exhibit varied engagement behaviors across study sessions, a session-level clustering analysis was performed, differently from previous research. After applying K-Means clustering algorithm, three clusters of behavioral patterns were identified: static viewing (the most predominant behavior), in which students viewed videos with minimal interactions; engaged viewing, involving high frequency of play and pause events; and focused viewing (the least frequent pattern), which involved mainly seeking the video for specific information. While video sessions with static viewing were very common among both high and low achieving students, most engaged-viewing sessions or focused-viewing sessions consistently belonged to the successful students. In addition, successful students were found to demonstrate multiple viewing behaviors, suggesting their effort in using multiple strategies while watching videos. Based on the findings, the paper discusses implications for the design of MOOCs and other online learning platforms that support video-based learning.
- 26 July 2024
- Published by Education Technology Theory and Practice in Eğitim Teknolojisi Kuram ve Uygulama
- Vol. 14 (2) , 198-217
Open AccessIDENTIFYING BEHAVIORAL PATTERNS IN MOOC VIDEO ENGAGEMENT USING CLUSTERING APPROACH
Videos are the core components of MOOCs for delivering course content and teaching the core concepts effectively. While the literature provided strong and consistent evidence regarding the link between video engagement and the success in MOOCs, the research on video engagement behavior is still emerging and in demand of further research. This research aims to contribute to the literature by identifying behavioral patterns of video engagement in a MOOC and reveal the association of these patterns with success and failure. In particular, we employed simple video engagement metrics with an attempt to identify clusters of behavioral patterns that can be applied to different contexts. Acknowledging that students may exhibit varied engagement behaviors across study sessions, a session-level clustering analysis was performed, differently from previous research. After applying K-Means clustering algorithm, three clusters of behavioral patterns were identified: static viewing (the most predominant behavior), in which students viewed videos with minimal interactions; engaged viewing, involving high frequency of play and pause events; and focused viewing (the least frequent pattern), which involved mainly seeking the video for specific information. While video sessions with static viewing were very common among both high and low achieving students, most engaged-viewing sessions or focused-viewing sessions consistently belonged to the successful students. In addition, successful students were found to demonstrate multiple viewing behaviors, suggesting their effort in using multiple strategies while watching videos. Based on the findings, the paper discusses implications for the design of MOOCs and other online learning platforms that support video-based learning.
- Open Access
- 16 May 2024
- Published by Athabasca University Press in The International Review of Research in Open and Distributed Learning
- Vol. 25 (2) , 94-113
Decoding Video Logs: Unveiling Student Engagement Patterns in Lecture Capture Videos
Lecture capture videos, a popular type of instructional content used by instructors to share course recordings online, play a significant role in educational settings. Compared to other educational videos, these recordings require minimal time and effort to produce, making them a preferred choice for disseminating course materials. Despite their numerous benefits, there exists a scarcity of data-driven evidence regarding students’ use of and engagement with lecture capture videos. Most existing studies rely on self-reported data, lacking comprehensive insights into students’ actual video engagement. This research endeavor sought to bridge this gap by investigating university students’ engagement patterns while watching lecture capture videos. To achieve this objective, we conducted an analysis of a large-scale dataset comprising over one million rows of video interaction logs. Leveraging clustering and process mining methodologies, we explored the data to reveal valuable insights into students’ video engagement behaviors. Our findings indicate that in approximately 60% of students’ video-watching sessions, only a small portion of the videos (an average of 7%) is watched. Our results also show that visiting the video page does not necessarily mean that the student watched it. This study may contribute to the existing literature by providing robust data-driven evidence on university students’ lecture capture video engagement patterns. It is also expected to contribute methodologically to capturing, preprocessing, and analyzing students’ video interactions in different contexts.
- 16 May 2024
- Published by Athabasca University Press in The International Review of Research in Open and Distributed Learning
- Vol. 25 (2) , 94-113
Open AccessDecoding Video Logs: Unveiling Student Engagement Patterns in Lecture Capture Videos
Lecture capture videos, a popular type of instructional content used by instructors to share course recordings online, play a significant role in educational settings. Compared to other educational videos, these recordings require minimal time and effort to produce, making them a preferred choice for disseminating course materials. Despite their numerous benefits, there exists a scarcity of data-driven evidence regarding students’ use of and engagement with lecture capture videos. Most existing studies rely on self-reported data, lacking comprehensive insights into students’ actual video engagement. This research endeavor sought to bridge this gap by investigating university students’ engagement patterns while watching lecture capture videos. To achieve this objective, we conducted an analysis of a large-scale dataset comprising over one million rows of video interaction logs. Leveraging clustering and process mining methodologies, we explored the data to reveal valuable insights into students’ video engagement behaviors. Our findings indicate that in approximately 60% of students’ video-watching sessions, only a small portion of the videos (an average of 7%) is watched. Our results also show that visiting the video page does not necessarily mean that the student watched it. This study may contribute to the existing literature by providing robust data-driven evidence on university students’ lecture capture video engagement patterns. It is also expected to contribute methodologically to capturing, preprocessing, and analyzing students’ video interactions in different contexts.
- Top Cited PapersOpen Access
- 24 April 2024
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 44 (5) , 1071-1098
Designing human-centered learning analytics and artificial intelligence in education solutions: a systematic literature review
- 24 April 2024
- Published by Taylor & Francis in Behaviour & Information Technology
- Vol. 44 (5) , 1071-1098
Top Cited PapersOpen AccessDesigning human-centered learning analytics and artificial intelligence in education solutions: a systematic literature review