More Like this

1. SelfCode 2.0: An Annotated Corpus of Student and Expert Line-by-Line Explanations of Code Examples for Automated Assessment

   https://doi.org/10.32473/flairs.38.1.138727  

   Chapagain, Jeevan; Lekshmi, Arun Balajiee; Akhuseyinoglu, Kamil; Brusilovsky, Peter; Rus, Vasile (May 2025, The International FLAIRS Conference Proceedings)

   Assessing student responses is a critical task in adaptive educational systems. More specifically, automatically evaluating students' self-explanations contributes to understanding their knowledge state which is needed for personalized instruction, the crux of adaptive educational systems. To facilitate the development of Artificial Intelligence (AI) and Machine Learning models for automated assessment of learners' self-explanations, annotated datasets are essential. In response to this need, we developed the SelfCode2.0 corpus, which consists of 3,019 pairs of student and expert explanations of Java code snippets, each annotated with semantic similarity, correctness, and completeness scores provided by experts. Alongside the dataset, we also provide performance results obtained with several baseline models based on TF-IDF and Sentence-BERT vectorial representations. This work aims to enhance the effectiveness of automated assessment tools in programming education and contribute to a better understanding and supporting student learning of programming. 

   more » « less
2. A Case Study with an Intelligent Tutoring System for Active Study of Worked Examples in Introductory JAVA Programming

   https://doi.org/10.1007/978-3-032-29794-5_71  

   Narayanan, Arun_Balajiee Lekshmi; Hassany, Mohammad; Hendrawan, Rully; Akhuseyinoglu, Kamil; Brusilovsky, Peter (January 2026, Springer Nature Switzerland)

   Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. We could magnify the power of worked examples by combining them with self-explanations, a strategy in which students explain each problem-solving step rather than passively studying it. In this work, we improve an existing system for automatically assessing student explanations to support the active study of worked examples. In particular, we use LLMs to address the limitations of semantic similarity methods for automatically assessing student explanations. We compare several methods based on semantic similarity with directly prompting LLMs. We showed that LLMs achieve an F1 score of 0.98, outperforming all semantic similarity baselines (F1 = 0.94). Our proposed work will improve the automated assessment and evaluate the system in a user study. 

   more » « less
3. Improving Code Comprehension Through Scaffolded Self-explanations

   Priti Oli; Rabin Banjade; Lekshmi Narayanan, Arun Balajiee; Jeevan Chapagain; Lasang Jimba Tamang; Peter Brusilovsky; Vasile Rus (July 2023, Proceedings of 24th International Conference on Artificial Intelligence in Education, AIED 2023, Part 2)

   Self-explanations could increase student’s comprehension in complex domains; however, it works most efficiently with a human tutor who could provide corrections and scaffolding. In this paper, we present our attempt to scale up the use of self-explanations in learning programming by delegating assessment and scaffolding of explanations to an intelligent tutor. To assess our approach, we performed a randomized control trial experiment that measured the impact of automatic assessment and scaffolding of self-explanations on code comprehension and learning. The study results indicate that low-prior knowledge students in the experimental condition learn more compared to high-prior knowledge in the same condition but such difference is not observed in a similar grouping of students based on prior knowledge in the control condition. 

   more » « less
4. Improving Code Comprehension Through Scaffolded Self-explanations

   Oli, P. (June 2023, Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky. AIED 2023. Communications in Computer and Information Science, vol 1831. Springer, Cham.)

   Wang, N.; Rebolledo-Mendez; G., Dimitrova; V., Matsuda; Santos, O.C. (Ed.)

   Self-explanations could increase student’s comprehension in complex domains; however, it works most efficiently with a human tutor who could provide corrections and scaffolding. In this paper, we present our attempt to scale up the use of self-explanations in learning programming by delegating assessment and scaffolding of explanations to an intelligent tutor. To assess our approach, we performed a randomized control trial experiment that measured the impact of automatic assessment and scaffolding of self-explanations on code comprehension and learning. The study results indicate that low-prior knowledge students in the experimental condition learn more compared to high-prior knowledge in the same condition but such difference is not observed in a similar grouping of students based on prior knowledge in the control condition. 

   more » « less
5. Improving Code Comprehension Through Scaffolded Self-explanations

   Oli, P. (July 2023, Proceedings of 24th International Conference on Artificial Intelligence in Education, AIED 2023, Part 2)

   N. Wang, G. Rebolledo-Mendez (Ed.)

   Self-explanations could increase student’s comprehension in complex domains; however, it works most efficiently with a human tutor who could provide corrections and scaffolding. In this paper, we present our attempt to scale up the use of self-explanations in learning program- ming by delegating assessment and scaffolding of explanations to an intel- ligent tutor. To assess our approach, we performed a randomized control trial experiment that measured the impact of automatic assessment and scaffolding of self-explanations on code comprehension and learning. The study results indicate that low-prior knowledge students in the experi- mental condition learn more compared to high-prior knowledge in the same condition but such difference is not observed in a similar grouping of students based on prior knowledge in the control condition. 

   more » « less