LLM Inferred Personality Traits for Calibrated Music Recommendation

• Yuvisa Quispe Palomino USP
• Paul Atauchi USP
• Luan Soares de Souza USP
• Dietmar Jannach University of Klagenfurt
• Marcelo Garcia Manzato USP

DOI: https://doi.org/10.5753/webmedia.2026.31039

Resumo

Recommender Systems (RS) help manage information overload by generating personalized recommendations from user data. However, feedback loops can introduce and amplify biases, such as popularity and exposure bias, systematically favoring certain items or groups. Calibration has been proposed as a post-processing strategy to align recommendation lists with user preferences while improving beyond-accuracy objectives such as diversity and fairness. In this work, we investigate personality-aware calibration for music recommendation when explicit personality traits are unavailable. We infer users’ Big Five personality traits from music-consumption signals using Large Language Models (LLMs), specifically GPT-4.1-mini and Gemini-2.5-flash, and compare them with questionnaire-based personality data. Our results show that LLMs can approximate personality traits better than random and permutation baselines, with the best performance achieved by GPT using summarized profiles enriched with lyrical semantic and emotional features. Experiments in the music domain further show that the proposed approach can improve diversity and fairness in several configurations while maintaining competitive accuracy. Although gains are not uniform across all algorithms and calibration settings, the results suggest that LLM-inferred personality traits can provide useful signals for calibrated recommendation when explicit personality information is unavailable.

Palavras-chave: Personality Traits, Inferred Personality Traits, Big Five, Calibration, Fairness, Large Language Models (LLMs)

Referências

Himan Abdollahpouri, Masoud Mansoury, Robin Burke, Bamshad Mobasher, and Edward C. Malthouse. 2021. User-centered Evaluation of Popularity Bias in Recommender Systems. In Proceedings of the 29th ACM Conference UMAP 2021, Utrecht. ACM, 119–129. DOI: 10.1145/3450613.3456821

Somdeep Acharyya and Nargis Pervin. 2025. Enhancing cross-domain recommendations: Leveraging personality-based transfer learning with probabilistic matrix factorization. Expert Systems with Applications 263 (2025), 125667.

Charu C Aggarwal et al. 2016. Recommender systems. Vol. 1. Springer.

Gabrielle Alves, Dietmar Jannach, Luan Soares de Souza, and Marcelo Garcia Manzato. 2025. Towards Personality-Aware Explanations for Music Recommendations Using Generative AI. In Proceedings of the Nineteenth ACM Conference on Recommender Systems. 684–689.

Ian Anderson, Santiago Gil, Clay Gibson, Scott Wolf, Will Shapiro, Oguz Semerci, and David M Greenberg. 2021. “Just the way you are”: Linking music listening on Spotify and personality. Social Psychological and Personality Science 12, 4 (2021), 561–572.

Henry I Braun, Douglas N Jackson, and David E Wiley. 2001. Socially desirable responding: The evolution of a construct. In The role of constructs in psychological and educational measurement. Routledge, 61–84.

Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2023. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems 41, 3 (2023), 1–39.

Arthur Da Costa, Eduardo Fressato, Fernando Neto, Marcelo Manzato, and Ricardo Campello. 2018. Case recommender: a flexible and extensible python framework for recommender systems. In Proceedings of the 12th ACM Conference on Recommender Systems. 494–495.

Diego da Silva and Dietmar Jannach. 2026. Calibrated recommendations: Survey and future directions. ACM Transactions on Recommender Systems 4, 3 (2026), 1–32.

Sahraoui Dhelim, Nyothiri Aung, Mohammed Amine Bouras, Huansheng Ning, and Erik Cambria. 2022. A survey on personality-aware recommendation systems. Artificial Intelligence Review 55, 3 (2022), 2409–2454.

John M Digman. 1990. Personality structure: Emergence of the five-factor model. Annual review of psychology 41, 1 (1990), 417–440.

Ethan Fast, Binbin Chen, and Michael S Bernstein. 2016. Empath: Understanding topic signals in large-scale text. In Proceedings of the 2016 CHI conference on human factors in computing systems. 4647–4657.

Raghav Pavan Karumur, Tien T Nguyen, and Joseph A Konstan. 2018. Personality, user preferences and behavior in recommender systems. Information Systems Frontiers 20, 6 (2018), 1241–1265.

Mohammadmehdi Naghiaei, Mahdi Dehghan, Hossein A Rahmani, Javad Azizi, and Mohammad Aliannejadi. 2024. Personalized beyond-accuracy calibration in recommendation. In Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval. 107–116.

Huansheng Ning, Sahraoui Dhelim, and Nyothiri Aung. 2019. PersoNet: Friend recommendation system based on big-five personality traits and hybrid filtering. IEEE Transactions on Computational Social Systems 6, 3 (2019), 394–402.

Yuvisa Quispe Palomino, Rodrigo Ferrari de Souza, Paul Dany Flores Atauchi, and Marcelo Garcia Manzato. 2026. Calibration of Personality-Based Recommender Systems: Balancing Relevance and Diversity. In Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing. 2118–2126.

Lin Qiu, Jiayu Chen, Jonathan Ramsay, and Jiahui Lu. 2019. Personality predicts words in favorite songs. Journal of Research in Personality 78 (2019), 25–35.

Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (Montreal, Quebec, Canada) (UAI ’09). AUAI Press, Arlington, Virginia, USA, 452–461.

Francesco Ricci, Lior Rokach, and Bracha Shapira (Eds.). 2022. Recommender Systems Handbook. Springer US. DOI: 10.1007/978-1-0716-2197-4

Andre Sacilotti, Rodrigo Souza, and Marcelo G. Manzato. 2023. Counteracting Popularity-Bias and Improving Diversity Through Calibrated Recommendations. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS. INSTICC, SciTePress, 709–720. DOI: 10.5220/0011846000003467

Rafael Santos and Giovanni Comarela. 2025. FaDeRS: Fairness and Depolarization in Recommender Systems. In Brazilian Symposium on Multimedia and the Web (WebMedia). SBC, 248–257.

Rodrigo Souza and Marcelo Manzato. 2024. A two-stage calibration approach for mitigating bias and fairness in recommender systems. In Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing. 1659–1661.

Harald Steck. 2018. Calibrated recommendations. In Proceedings of the 12th ACM conference on recommender systems. 154–162.

Hsin-Chang Yang and Zi-Rui Huang. 2019. Mining personality traits from social messages for game recommender systems. Knowledge-Based Systems 165 (2019), 157–168.

Yuying Zhao, Yu Wang, Yunchao Liu, Xueqi Cheng, Charu C. Aggarwal, and Tyler Derr. 2025. Fairness and Diversity in Recommender Systems: A Survey. ACM Trans. Intell. Syst. Technol. 16, 1, Article 2 (Jan. 2025), 28 pages. DOI: 10.1145/3664928