Introductory programming courses are widely known for their difficulty among students. Success in courses is commonly measured in the form of final grades, which might not capture the challenges students face during their learning process. In this paper, we predict students’ success and their future compiler errors based on previously made errors. Furthermore, we examine the effect of applying two clustering techniques before making the predictions and identify key weeks and errors that have the greatest impact on predictions. Experimental results show that students’ compiler errors observed through the semester are an important predictor of students’ achievement and future struggles. Predictions are further improved using sentence encoder-generated embeddings with K-Means algorithm. Our study suggests that students’ errors, particularly the most recent ones, enable meaningful clustering that enhances performance prediction after only three weeks of the semester.

Introductory programming courses present significant challenges for novice learners, often leading to frustration and difficulty in identifying learning gaps. This research aims to develop an AI-driven tool that provides personalized guidance, moving beyond traditional "one-size-fits-all" approaches. Recognizing the limitations of relying solely on digital interaction logs in the era of generative AI, we explore the integration of student personal characteristics and fine-grained programming interactions to predict learning behavior and performance. We will investigate how to accurately predict student outcomes early in the semester, analyze the dynamics of learning behaviors, and design an AI-assisted tool to recommend tailored learning materials and feedback. Our goal is to foster effective learning and mitigate the risks associated with over-reliance on general-purpose AI, ultimately enhancing knowledge retention and problem-solving skills.

Understanding how students perceive and utilize Large Language Models (LLMs) and how these interactions relate to their learning behavior and individual differences is crucial for optimizing educational process and outcomes. This paper introduces a novel dataset comprising weekly self-reported data from students in an introductory programming course, i.e., students’ AI tool usage, perceived difficulty of weekly subject areas, personality traits, preferred learning styles, and general attitudes toward AI. We present a descriptive overview of the collected data and conduct a correlation analysis to gain first insights into the students’ individual differences and their learning outcomes, frequency of AI tools usage, as well as their attitudes toward AI. The findings reveal that while individual student characteristics did not show significant correlations with final performance or frequency of AI tool usage, the combination of students’ expectations for success and their perceived value of the task (constructs of expectancy theory) were significantly associated with both course outcomes and how often they used the AI tool. Additionally, motivational factors may be the key to fostering positive attitudes toward AI, while personality traits, particularly those related to negative emotionality, may play a more significant role in shaping resistance. This initial analysis lays the groundwork for future investigations on the prospects of AI in support of the students’ learning process.

The integration of technology in education has become indispensable in acquiring new skills, knowledge, and competencies. This paper addresses the issue of analyzing and predicting the learning behavior of Computer Science students. Specifically, we present a dataset of compiler errors made by students during the first semester of an Introduction to Programming course where they learn the C programming language. We approach the problem of predicting the number of student errors as a missing data imputation problem, utilizing several prediction methods including Singular Value Decomposition, Polynomial Regression via Latent Tensor Reconstruction, Neural Network-based method, and Gradient Boosting. Our experimental results demonstrate high accuracy in predicting student learning behaviors over time, which can be leveraged to enhance personalized learning for individual students.