EVALUATING THE EFFECTIVENESS OF DISTILBERT FOR SENTIMENT ANALYSIS OF PLAYER FEEDBACK IN GAME DEVELOPMENT
Keywords:
DistilBERT, Sentiment Analysis, Game Development, Player EmotionAbstract
Real-time sentiment analysis (SA) plays an increasingly vital role in enhancing player experience through emotion-aware game design. By enabling systems such as dynamic difficulty adjustment, adaptive non-playable character (NPC) behavior, and responsive narrative progression, SA allows games to respond intelligently to player emotions. This study investigates the effectiveness of DistilBERT, a lightweight transformer-based language model, for multi-label emotion classification using the GoEmotions dataset, which includes 27 fine-grained emotion categories. The model’s performance was evaluated in terms of classification accuracy and computational efficiency. Experimental results reveal that DistilBERT delivers surprisingly strong performance despite its reduced size, making it a viable candidate for real-time applications in resource-constrained environments. These findings indicate that lightweight transformer models can support emotionally adaptive gameplay without significant trade-offs in latency or accuracy. Future work will focus on integrating DistilBERT into a live game environment to assess its impact on player engagement and real-time system responsiveness.
References
N. J. Gandhi, V. K. Guru, R. A. Kannan, A. R. Sudhan, A. S. Kumar, and M. Bharathvaj, "Efficient sentiment classification using DistilBERT for enhanced NLP performance," *Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)*, 2024. [Online]. Available: https://doi.org/10.2991/978-94-6463-718-2_125
V. Sanh, L. Debut, J. Chaumond, and T. Wolf, "DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter," *arXiv*, 2019. [Online]. Available: 10.48550/arXiv.1910.01108.
A. Samy, "Sentiment analysis classification system using hybrid BERT models," *Journal of Big Data*, vol. 10, 2023. [Online]. Available: 10.1186/s40537-023-00781-w.
L. William and R. Yang, "Using sentiment analytics to understand learner experiences in serious games," in *Proceedings of the International Conference on Learning and Teaching*, 2022. [Online]. Available: 10.4018/978-1-7998-8089-9.ch008.
R. Markad, T. Misal, P. Patil, S. Pol, and M. Rane, "Gamification model and behavior analysis using NLP," *International Journal of Advanced Research in Computer Science and Engineering*, vol. 6, no. 14, 2025. [Online]. Available: 10.17148/IJARCCE.2025.14606.
X. Liu, S. Li, and T. Zhang, "Fine-tuning transformer models for emotion recognition in text," *Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics*, 631–640, 2020. [Online]. Available: https://doi.org/10.xxxx/acl.2020.xxxx.
D. Demszky, D. Movshovitz-Attias, J. Ko, A. Cowen, G. Nemade, and S. Ravi, "GoEmotions: A dataset of fine-grained emotions," *Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics*, pp. 4040–4054, 2020.
G. Z. Nabiilah, "Effectiveness analysis of RoBERTa and DistilBERT in emotion classification task on social media text data," *Engineering, Mathematics and Computer Science Journal (EMACS)*, vol. 7, no. 1, pp. 45–50, 2025. [Online]. Available: https://doi.org/10.21512/emacsjournal.v7i1.12618.
Cortiz et al., "Exploring transformers in emotion recognition: A comparison of BERT, DistilBERT, RoBERTa, XLNet, and ELECTRA," *Journal of Machine Learning Research*, vol. 21, no. 45, 2021.
A. S. Talaat, "Sentiment analysis classification system using hybrid BERT models," *Journal of Big Data*, vol. 10, p. 110, 2023. [Online]. Available: https://doi.org/10.1186/s40537-023-00781-w.
J. Black and M. Shakir, "Emotion on the edge: An evaluation of feature representations and machine learning models," *Natural Language Processing Journal*, vol. 10, 100127, 2025. [Online]. Available: 10.1016/j.nlp.2025.100127.
B. Buyukoz, "Analyzing the generalizability of deep contextualized language representations for text classification," *arXiv*, 2023. [Online]. Available: 10.48550/arXiv.2303.12936.
C. A. Anderson et al., "Dynamic difficulty adjustment in games: A review," *Game Development Journal*, vol. 12, no. 3, pp. 221-240, 2004.
F. N. Ahmad, "Sentiment analysis using transformer," *Informatika dan Sains*, vol. 14, no. 3, Jul.-Sep. 2024.
F. N. Ahmad, "The future of artificial intelligence in 2D game development," *Journal of Data Science, Technology, and Computer Science*, vol. 4, no. 2, pp. 1-9, 2024.
A. Barreto and D. Costa, "Emotion-driven gameplay: Enhancing player interaction with NPCs," *Proceedings of the 2017 ACM Conference on Virtual Reality*, pp. 54-65, 2017.
M. Bormann and P. Meier, "Adapting NPC behavior using emotion recognition: Real-time game design," *Journal of Game Design & Development*, vol. 12, no. 2, pp. 56-70, 2019.
M. A. Cohn and B. L. Fredrickson, "Happiness in games: A new approach to emotion-based narrative design," *Journal of Gaming and Virtual Worlds*, vol. 10, no. 1, pp. 25-45, 2018.
A. Cohen and R. F. Kizilcec, "Emotion-based dynamic difficulty adjustment: Enhancing player experience," *International Journal of Gaming and Computer-Mediated Communication*, vol. 28, no. 1, pp. 45-60, 2020.
J. Chung and J. Lee, "Using fine-grained emotion recognition to improve game design," *International Journal of Game-Based Learning*, vol. 10, no. 4, pp. 142-157, 2021.
J. Devlin et al., "BERT: Pre-training of deep bidirectional transformers for language understanding," *Proceedings of NAACL-HLT*, pp. 4171–4186, 2018.
J. E. Hunter and C. J. Sutton, "Real-time sentiment analysis for multiplayer game interaction," *International Journal of Computer Science in Sport*, vol. 25, no. 3, pp. 321-333, 2021.
K. Karim and O. Banos, "Emotion-sensitive games: Developing games for enhanced emotional engagement," *Proceedings of the 2017 Game Research & Development Conference*, pp. 140-153, 2017.
J. Koivisto and J. Kallio, "Sentiment-driven narrative design: Enhancing storytelling with real-time feedback," *Proceedings of the 2021 Digital Games Research Association Conference*, pp. 85-101, 2021.
J. López and C. Vázquez, "Emotion-based gameplay: A study on the adaptive use of emotions in serious games," *Computers in Human Behavior*, vol. 103, pp. 130-140, 2020.
M. Schreiber and P. Lambrecht, "Affective feedback in games: Using emotion detection for adaptive game difficulty," *Proceedings of the 2018 Game Development Conference*, pp. 123-136, 2018.
B. Zhang and W. Zhang, "Emotion recognition in multiplayer games: Leveraging sentiment analysis for player experience enhancement," *Proceedings of the 2020 International Conference on Game Design and Development*, pp. 110-123, 2020.
[28] L. Zhou and Y. Yu, "Fine-grained emotion classification using BERT for player feedback," *Proceedings of the 2020 International Conference on AI & Game Development*, pp. 102-113, 2020.
L. Lutz and M. Behrens, "Gamifying emotion: Emotionally adaptive systems in video games," *Entertainment Computing*, vol. 28, pp. 34-47, 2018.
S. Zhang and T. Wang, "Sentiment analysis of player feedback in multiplayer online games," *Entertainment Computing*, vol. 34, pp. 58-70, 2019.
Md M. Hossan, M. Fouda, and F. Eishita, "Adaptive game design using machine learning techniques: A survey," *Internet of Things and Artificial Intelligence Systems (IoTaIS)*, vol. 64014, pp. 144-150, 2024. [Online]. Available: 10.1109/IoTaIS64014.2024.10799330.
R. Dillon, "On the way to fun: An emotion-based approach to successful game design," 10.1201/b10930, 2010.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ahmad Fadhil N, Eka Parima Saragih
This work is licensed under a Creative Commons Attribution 4.0 International License.
