This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Shiraj Ahmad,
Savyasachi Mishra,
Anish Das,
Naveen Chaurasia,
Mohit Kumar Saha,
- Assistant Professor, Greater Noida Institute of Technology, Greater Noida,, Uttar Pradesh, India
- Student, Noida Institute of Technology, Knowledge Park, Greater Noida,, Uttar Pradesh, India
- Student, Noida Institute of Technology, Knowledge Park, Greater Noida,, Uttar Pradesh, India
- Student, Noida Institute of Technology, Knowledge Park, Greater Noida,, Uttar Pradesh, India
- Student, Noida Institute of Technology, Knowledge Park, Greater Noida,, Uttar Pradesh, India
Abstract
The rapid evolution of the software industry has significantly transformed the expectations placed on modern developers. In today’s competitive environment, employers increasingly value practical problem-solving ability, debugging proficiency, logical reasoning, and architectural thinking more than traditional academic grades alone. While academic performance still plays a role, it often fails to reflect how effectively a student can approach real- world programming challenges. Most current educational evaluation systems rely on exam scores or assignment submissions, which provide only a limited understanding of a learner’s true coding capabilities. These methods rarely capture the behavioural patterns that reveal how a student thinks, plans, and iterates while solving programming problems. The Student Skill Tracker platform introduces a telemetry-driven programming education framework designed to analyse real coding behaviour and measure skill development over time. Instead of evaluating only the final code output, the platform observes the entire programming process. It collects behavioural signals such as planning latency before writing code, compiler failure streaks during development, and debugging recovery velocity when resolving errors. These signals help construct a detailed behavioural profile that reflects a learner’s programming cognition and development patterns. To support this system, the platform uses a modern full-stack architecture including Angular dashboards for visualisation, Spring Boot microservices for backend logic, PostgreSQL for persistent data storage, and Redis for high-speed telemetry caching. Additionally, an autonomous pedagogical agent powered by the LangChain4j framework continuously monitors telemetry streams and provides intelligent mentorship interventions when inefficient learning behaviours are detected.
Keywords: Student Skill Tracker, Behavioural Learning Analytics, Programming Cognition, Debugging Behaviour Analysis, Compiler Failure Patterns, Autonomous Pedagogical Agents, LangChain4j, Learning Analytics, Full-Stack Educational Platforms.
References
[1] Kahneman D. Thinking, fast and slow. Farrar, Straus and Giroux. 2011. [2] Woźniak P, Gorzelańczyk E. Optimization of repetition spacing in the practice of learning. Acta neurobiologiae experimentalis. 1994 Mar 31;54(1):59-62. [3] Jadud MC. Methods and tools for exploring novice compilation behaviour. InProceedings of the second international workshop on Computing education research 2006 Sep 9 (pp. 73-84). [4] VanLehn K. The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational psychologist. 2011 Oct 1;46(4):197-221. [5] Pressler R, Bateman A. JEP 444: Virtual Threads. OpenJDK. 2023. [6] LangChain4j Contributors. LangChain4j: an idiomatic Java library for building LLM-powered applications on the JVM [Internet]. GitHub; 2024 [cited 2026 Oct 12]. Available from: https://github.com/langchain4j/langchain4j [7] Al-Obaydi LH, Pikhart M. The use of Copilot, Gemini and ChatGPT in the context of foreign language learning and teaching: An academic technology review. Contemporary Educational Technology. 2026 Mar 9;18(2):ep640. [8] Fan X, Zhou X, Jin C, Nottingham K, Zhu H, Sap M. Somi-tom: Evaluating multi-perspective theory of mind in embodied social interactions. Advances in Neural Information Processing Systems. 2026 Apr 23;38. [9] Framework S. Spring Boot Reference Documentation. Recuperado de: https://spring. io/projects/spring- boot. 2024. [10] Vrbka J. Low-Code Test Automation Studio (Doctoral dissertation, Masarykova univerzita, Fakulta informatiky). [11] Späth P, Cosmina I, Harrop R, Schaefer C. Spring WebSocket Support. InPro Spring 6 with Kotlin: An In-depth Guide to Using Kotlin APIs in Spring Framework 6 2023 Sep 10 (pp. 829-853). Berkeley, CA: Apress. [12] Amardeep R, Soumya HS, Raghavendra HS, Gowda SS, Jain YR. Advancement in Health Monitoring Through IOT and PostgreSQL Analytics. In2024 International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS) 2024 Apr 22 (pp. 1-5). IEEE. [13] Siemens G. Learning analytics: The emergence of a discipline. American behavioral scientist. 2013 Oct;57(10):1380-400. [14] Baker RS, Yacef K. The state of educational data mining in 2009: A review and future visions. Journal of educational data mining. 2009 Oct 1;1(1):3-17. [15] Sweller J. Cognitive load during problem solving: Effects on learning. Cognitive science. 1988 Apr 1;12(2):257-85. [16] Deterding S, Dixon D, Khaled R, Nacke L. From game design elements to gamefulness: defining” gamification”. InProceedings of the 15th international academic MindTrek conference: Envisioning future media environments 2011 Sep 28 (pp. 9-15). [17] Blikstein P. Using learning analytics to assess students’ behavior in open-ended programming tasks. InProceedings of the 1st international conference on learning analytics and knowledge 2011 Feb 27 (pp. 110-116). [18] Keuning H, Jeuring J, Heeren B. A systematic literature review of automated feedback generation for programming exercises. ACM Transactions on Computing Education (TOCE). 2018 Sep 28;19(1):1- 43. [19] Denny P, Leinonen J, Prather J, Luxton-Reilly A, Amarouche T, Becker BA, Reeves BN. Promptly: Using prompt problems to teach learners how to effectively utilize ai code generators. arXiv preprint arXiv:2307.16364. 2023 Jul 31. [20] Leinonen J, Hellas A, Sarsa S, Reeves B, Denny P, Prather J, Becker BA. Using large language models to enhance programming error messages. InProceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1 2023 Mar 2 (pp. 563-569). [21] Jimenez Calderon VG. Sistema de autenticación biométrica dinámica para la gestión de contraseñas utilizando inteligencia artificial: plugin de generación de contraseñas seguras con inteligencia artificial para acceso a redes sociales. [22] Biryukov A, Dinu D, Khovratovich D. Argon2: new generation of memory-hard functions for password hashing and other applications. In2016 IEEE European Symposium on Security and Privacy (EuroS&P) 2016 Mar 21 (pp. 292-302). IEEE. [23] Corbett AT, Anderson JR. Knowledge tracing: Modeling the acquisition of procedural knowledge. User modeling and user-adapted interaction. 1994 Dec;4(4):253-78. [24] Bloom BS. The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational researcher. 1984 Jun;13(6):4-16. [25] Boberski M. The ten most critical Web application security risks. Techique Report, OWASP Foundation. 2010. [26] Lendvaj M. web aplikacija za upravljanje financijskim resursima i projektima u timovima (Master’s thesis, Sveučilište Josipa Jurja Strossmayera u Osijeku, Sveučilište Josipa Jurja Strossmayera u Osijeku, Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek, Zavod za računalno inženjerstvo i inteligentne sustave). [27] Prather J, Denny P, Leinonen J, Becker BA, Albluwi I, Craig M, Keuning H, Kiesler N, Kohn T, Luxton-Reilly A, MacNeil S. The robots are here: Navigating the generative ai revolution in computing education. InProceedings of the 2023 working group reports on innovation and technology in computer science education 2023 Dec 22 (pp. 108-159). [28] Tabanao ES, Rodrigo MM, Jadud MC. Predicting at-risk novice Java programmers through the analysis of online protocols. InProceedings of the seventh international workshop on Computing education research 2011 Aug 8 (pp. 85-92). [29] Vygotsky LS, Cole M, John-Steiner V, Scribner S, Souberman E. The development of higher psychological processes. [30] Ihantola P, Ahoniemi T, Karavirta V, Seppälä O. Review of recent systems for automatic assessment of programming assignments. InProceedings of the 10th Koli calling international conference on computing education research 2010 Oct 28 (pp. 86-93).
Journal of Software Engineering Tools & Technology Trends
| Volume | 13 | |
| 03 | ||
| Received | 23/07/2026 | |
| Accepted | 30/07/2026 | |
| Published | 17/10/2026 | |
| Publication Time | 86 Days |