Personalized programming support in higher education via emotion-guided prompt generation and GenAI
DOI:
https://doi.org/10.65746/jbrha124Keywords:
emotion recognition; generative AI; intelligent tutoring systems; personalized programming support; prompt generation; ResNet-50Abstract
Personalized programming supports learners by incorporating their emotional states into an Artificial Intelligence (AI) system. However, existing systems face challenges, including a scarcity of emotion-adaptive tutors, limited generative AI tools for recognizing emotions, and a lack of prompt engineering techniques. This study proposes a personalized emotion-aware AI programming assistant that detects the user’s facial emotions and generates code explanations using generative AI. We develop a hybrid facial emotion recognition model using ResNet-50 to capture spatial features and LSTM to capture temporal patterns. The model classifies the learner’s emotions, which then informs emotion-guided prompt engineering to adjust programming queries based on detected emotions. The modified prompt is processed by a generative language model, displayed to the learner in a supportive and adaptive format. The model is tested in real-time with students. Experimental results show that the emotion-aware AI improved both learning performance and motivation in real-time classroom use, confirming its effectiveness in fostering engagement and better outcomes compared to a normal AI tutor.
References
1. Gamage G, De Silva D, Mills N, et al. Emotion AWARE: An artificial intelligence framework for adaptable, robust, explainable, and multi-granular emotion analysis. Journal of Big Data. 2024; 11(1): 93. doi: 10.1186/s40537-024-00953-2
2. Gu Z, He K. Affective prompt-tuning-based language model for semantic-based emotional text generation. International Journal on Semantic Web and Information Systems (IJSWIS). 2024; 20(1): 1–19. doi: 10.4018/IJSWIS.339187
3. Lee JP, Jang H, Jang Y, et al. Encoding of multi-modal emotional information via personalized skin-integrated wireless facial interface. Nature Communications. 2024; 15(1): 530. doi: 10.1038/s41467-023-44673-2
4. Lai T, Zeng X, Xu B, et al. The application of artificial intelligence technology in education influences Chinese adolescent’s emotional perception. Current Psychology. 2024; 43(6): 5309–5317. doi: 10.1007/s12144-023-04727-6
5. Govea J, Navarro AM, Sánchez-Viteri S, et al. Implementation of deep reinforcement learning models for emotion detection and personalization of learning in hybrid educational environments. Frontiers in Artificial Intelligence. 2024; 7: 1458230. doi: 10.3389/frai.2024.1458230
6. Atman Uslu N, Onan A. Exploring students’ emotions towards programming: Analysing sentiments using concurrent conversion mixed methods. Education and Information Technologies. 2025; 30(14): 19879–19909. doi: 10.1007/s10639-025-13482-z
7. Vinay R, Spitale G, Biller-Andorno N, et al. Emotional prompting amplifies disinformation generation in AI large language models. Frontiers in Artificial Intelligence. 2025; 8: 1543603. doi: 10.3389/frai.2025.1543603
8. Xu Y, Lin YS, Zhou X, et al. Utilizing emotion recognition technology to enhance user experience in real-time. Computing and Artificial Intelligence. 2024; 2(1): 1388–1388.
9. Cambria E, Zhang X, Mao R, et al. SenticNet 8: Fusing emotion AI and commonsense AI for interpretable, trustworthy, and explainable affective computing. In: International Conference on Human-Computer Interaction. 2024. pp. 197–216. doi: 10.1007/978-3-031-76827-9_11
10. Zheng J, Li S, Wang T, et al. Unveiling emotion dynamics in problem-solving: a comprehensive analysis with an intelligent tutoring system using facial expressions and electrodermal activities. International Journal of Educational Technology in Higher Education. 2024; 21(1): 33. doi: 10.1186/s41239-024-00462-5
11. Narimisaei J, Naeim M, Imannezhad S, et al. Exploring emotional intelligence in artificial intelligence systems: A comprehensive analysis of emotion recognition and response mechanisms. Annals of Medicine and Surgery. 2024; 86(8): 4657–4663. doi: 10.1097/ms9.0000000000002315
12. Sargazi Moghadam T, Darejeh A, Delaramifar M, et al. Toward an artificial intelligence-based decision framework for developing adaptive e-learning systems to impact learners’ emotions. Interactive Learning Environments. 2024; 32(7): 3665–3685. doi: 10.1080/10494820.2023.2188398
13. Khediri N, Ben Ammar M, Kherallah M, et al. A real-time multimodal intelligent tutoring emotion recognition system (MITERS). Multimedia Tools and Applications. 2024; 83(19): 57759–57783. doi: 10.1007/s11042-023-16424-4
14. Boughida A, Kouahla MN, Lafifi Y, et al. emoLearnAdapt: A new approach for an emotion-based adaptation in e-learning environments. Education and Information Technologies. 2024; 29(12): 15269–15323. doi: 10.1007/s10639-023-12429-6
15. Maddu RBR, Murugappan S. Online learners’ engagement detection via facial emotion recognition in online learning context using hybrid classification model. Social Network Analysis and Mining. 2024; 14(1): 43. doi: 10.1007/s13278-023-01181-x
16. Ul Huda N, Sahito SF, Gilal AR, et al. Impact of Contradicting Subtle Emotion Cues on Large Language Models with Various Prompting Techniques. International Journal of Advanced Computer Science & Applications. 2024; 15(4). doi: 10.14569/IJACSA.2024.0150442
17. Xu W, Yang LY, Liu X, et al. Examining the effects of different forms of teacher feedback intervention for learners’ cognitive and emotional interaction in online collaborative discussion: A visualization method for process mining based on text automatic analysis. Education and Information Technologies. 2024, 29(6): 6525–6551.
18. Garg A, Soodhani KN, Rajendran R, et al. Enhancing data analysis and programming skills through structured prompt training: The impact of generative AI in engineering education. Computers and Education: Artificial Intelligence. 2025; 8: 100380. doi: 10.1016/j.caeai.2025.100380
19. Boitel E, Mohasseb A, Haig E, et al. MIST: Multimodal emotion recognition using DeBERTa for text, Semi-CNN for speech, ResNet-50 for facial, and 3D-CNN for motion analysis. Expert Systems with Applications. 2025; 270: 126236. doi: 10.1016/j.eswa.2024.126236
20. Pourmirzaei M, Montazer GA, Mousavi E, et al. ATTENDEE: An AffecTive Tutoring system based on facial EmotioN recognition and heaD posE Estimation to personalize e-learning environment. Journal of Computers in Education. 2025; 12(1): 65–92. doi: 10.1007/s40692-023-00303-w
21. Kohnke L, Moorhouse BL. Enhancing the emotional aspects of language education through generative artificial intelligence (GenAI): A qualitative investigation. Computers in Human Behavior. 2025; 167: 108600. doi: 10.1016/j.chb.2025.108600
22. Shi L. The integration of advanced AI-enabled emotion detection and adaptive learning systems for improved emotional regulation. Journal of Educational Computing Research. 2025; 63(1): 173–201. doi: 10.1177/07356331241296890
23. Livingstone Steven R, Russo Frank A. The Ryerson audio-visual database of emotional speech and song (RAVDESS). 2018. Available online: https://zenodo.org/records/1188976 (accessed on 12 January 2026).
24. Umar MA, Chen Z, Shuaib K, et al. Effects of feature selection and normalization on network intrusion detection. Data Science and Management. 2025; 8(1): 23–39. doi: 10.1016/j.dsm.2024.08.001
Downloads
Published
Issue
Section
License
Copyright (c) 2026 A.V. Geetha, T. Mala (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
