More Like this

1. The Effects of Open Self-Explanation Prompting During Source Code Comprehension

   Tamang, L.J. (January 2020, In Proceedings of the Thirty-Third International FLAIRS Conference (FLAIRS-33))

   This paper reports the findings of an empirical study on the effects and nature of self explanation during source code comprehension learning activities in the context of learning computer programming language Java. Our study shows that self explanation helps learning and there is a strong positive correlation between the volume of self-explanation students produce and how much they learn. Furthermore, selfexplanations as an instructional strategy has no discrepancy based on student’s prior knowledge. We found that participants explain target code examples using a combination of language, code references, and mathematical expressions. This is not surprising given the nature of the target item, a computer program, but this indicates that automatically evaluating such self-explanations may require novel techniques compared to self-explanations of narrative or scientific texts. 

   more » « less
2. The Effects of Open Self-Explanation Prompting During Source Code Comprehension

   Tamang, Lasang J.; Alshaikh, Zeyad; Ait-Khayi, Nisrine; Rus, Vasile (April 2020, The Thirty-Third International Florida Artificial Intelligence Research Society Conference (FLAIRS-32))

   This paper reports the findings of an empirical study on the effects and nature of self explanation during source code comprehension learning activities in the context of learning computer programming language Java. Our study shows that self explanation helps learning and there is a strong positive correlation between the volume of self-explanation students produce and how much they learn. Furthermore, selfexplanations as an instructional strategy has no discrepancy based on student’s prior knowledge. We found that participants explain target code examples using a combination of language, code references, and mathematical expressions. This is not surprising given the nature of the target item, a computer program, but this indicates that automatically evaluating such self-explanations may require novel techniques compared to self-explanations of narrative or scientific texts. 

   more » « less
3. Exploring The Effectiveness of Reading vs. Tutoring For Enhancing Code Comprehension For Novices

   https://doi.org/10.1145/3605098.3636007  

   Oli, Priti; Banjade, Rabin; Lekshmi_Narayanan, Arun Balajiee; Brusilovsky, Peter; Rus, Vasile (April 2024, ACM Symposium on Applied Computing, SAC 2024)

   This paper presents a comparison of two instructional strategies meant to help learners better comprehend code and learn programming concepts: reading code examples annotated with expert explanation (worked-out examples) versus scaffolded self-explanation of code examples using an automated system (Intelligent Tutoring System). A randomized controlled trial study was conducted with 90 university students who were assigned to either the control group (reading worked-out examples, a passive strategy) or the experimental group where participants were asked to self-explain and received help, if needed, in the form of questions from the tutoring system( scaffolded self-explanation, an interactive strategy). We found that students with low prior knowledge in the experimental condition had significantly higher learning gains than students with high prior knowledge. However, in the control condition, this distinction in learning outcomes based on prior knowledge was not observed. We also analyzed the effect of self-efficacy on learning gains and the nature of self-explanation. Low self-efficacy students learn almost twice as much in the interactive condition versus the passive condition although the difference was not significant probably because of low sample size. We also found that high self-efficacy students tend to provide more relational explanations whereas low self-efficacy students provide more multi-structural or line-by-line explanations. 

   more » « less
4. The Behavior of Large Language Models When Prompted to Generate Code Explanations.

   Oli, P. (December 2023, Proceedings of The workshop on Generative AI for Education (GAIED): Advances, Opportunities, and Challenges, The Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023))

   This paper systematically explores how Large Language Models (LLMs) generate explanations of code examples of the type used in intro-to-programming courses. As we show, the nature of code explanations generated by LLMs varies considerably based on the wording of the prompt, the target code examples being explained, the programming language, the temperature parameter, and the version of the LLM. Nevertheless, they are consistent in two major respects for Java and Python: the readability level, which hovers around 7-8 grade, and lexical density, i.e., the relative size of the meaninful words with respect to the total explanation size. Furthermore, the explanations score very high in correctness but less on three other metrics: completeness, conciseness, and contextualization. 

   more » « less
5. Self-Explanation of worked examples integrated in an intelligent tutoring system enhances problem solving and efficiency in algebra

   Vest, N. A.:; Bartel, A. N.; Nagashima, T.; Aleven, V.; Alibali, M. W. (July 2022, Proceedings of the 44th Annual Conference of the Cognitive Science Society)

   Culbertson, J.; Perfors, A.; Rabagliati, H.; Ramenzoni, V. (Ed.)

   One pedagogical technique that promotes conceptual understanding in mathematics learners is self-explanation integrated with worked examples (e.g.,Rittle-Johnson et al., 2017). In this work, we implemented self-explanations with worked examples (correct and erroneous) in a software-based Intelligent Tutoring System (ITS) for learning algebra. We developed an approach to eliciting self-explanations in which the ITS guided students to select explanations that were conceptually rich in nature. Students who used the ITS with self-explanations scored higher on a posttest that included items tapping both conceptual and procedural knowledge than did students who used a version of the ITS that included only traditional problem-solving practice. This study replicates previous findings that self-explanation and worked examples in an ITS can foster algebra learning (Booth et al., 2013). Further, this study extends prior work to show that guiding students towards conceptual explanations is beneficial. 

   more » « less