Human and Information Interaction

Prediction of Users' Movie Genre Preferences Based on Their Personality and Demographic Features

Articles in Press

Document Type : Original Article

Authors

Mahsa Rezaei 1
Marjan Kaedi 2

1 Master’s Student, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran

2 Associate Professor, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran

https://doi.org/10.22034/hii.2026.115620.0
Abstract
Purpose: Online movie streaming platforms provide access to a wide range of content and have changed the way audiences select and watch movies. Predicting users’ preferences for different movie genres can improve personalization and the performance of movie recommender systems. Given the significant relationship between users’ personality traits and their preferences for movie genres, this study aims to investigate the effectiveness of using personality and demographic characteristics to predict users’ genre preferences.
Method: In this study, movies were characterized according to 18 main genres, while users were represented by personality traits based on the Five-Factor Model, including conscientiousness, extraversion, agreeableness, neuroticism, and openness to experience, along with demographic characteristics including age, gender, and location. Various machine learning models, including Support Vector Regression and Random Forest Regression, were trained separately for each genre to learn the relationship between user characteristics and their genre preferences. The models were evaluated on a version of the MovieLens dataset using Mean Absolute Error (MAE) as the primary evaluation metric.
Findings: The results showed that the models for predicting preferences for drama, action, and crime achieved the best performance, with MAE values of 0.18, 0.21, and 0.22, respectively. In contrast, the models for musical and fantasy genres obtained the highest error values, with MAEs of 0.34 and 0.33, respectively.
Conclusion: The findings indicate that combining personality and demographic characteristics can effectively predict users’ genre preferences and can provide useful information for improving personalization and the performance of movie recommender systems.

Methods: In this study, movies were characterized according to 18 main genres, while users were represented by personality traits based on the Five-Factor Model, including conscientiousness, extraversion, agreeableness, neuroticism, and openness to experience, along with demographic characteristics including age, gender, and location. Various machine learning models, including Support Vector Regression and Random Forest Regression, were trained separately for each genre to learn the relationship between user characteristics and their genre preferences. The models were evaluated on a version of the MovieLens dataset using Mean Absolute Error (MAE) as the primary evaluation metric.

Findings: The results showed that the models for predicting preferences for drama, action, and crime achieved the best performance, with MAE values of 0.18, 0.21, and 0.22, respectively. In contrast, the models for musical and fantasy genres obtained the highest error values, with MAEs of 0.34 and 0.33, respectively.

Conclusion: The findings indicate that combining personality and demographic characteristics can effectively predict users’ genre preferences and can provide useful information for improving personalization and the performance of movie recommender systems.

Keywords

Genre preferences
Machine learning
Personality traits
Big-five personality traits
Modeling
Buseyne, S., Said-Metwaly, S., Van den Noortgate, W., Depaepe, F., & Raes, A. (2026). The relationship between personality and flow: A meta-analysis. Journal of Personality, 94(2), 333–350. https://doi.org/10.1111/jopy.70004
Chen, L., Wu, W., & He, L. (2016). Personality and recommendation diversity. In M. Tkalčič, B. De Carolis, M. de Gemmis, A. Odić, & A. Košir (Eds.), Emotions and Personality in Personalized Services: Models, Evaluation and Applications (pp. 201–225). Springer, Cham.  https://doi.org/10.1007/978-3-319-31413-6_11
Gao, Y., Zheng, H., & Cui, H. (2025). User preference modeling for movie recommendations based on deep learning. Scientific Reports, 15, Article 16592. https://doi.org/10.1038/s41598-025-00030-5
Golbeck, J., & Norris, E. (2013). Personality, movie preferences, and recommendations. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (pp. 1414–1415). Niagara Falls, ON, Canada: ACM. https://doi.org/10.1145/2492517.2492572
Golkar, I., & Kaedi, M. (2015). Developing a model for estimating the extraversion degree of social network members using the information extracted from the graph structure. Journal of Modeling in Engineering, 13(43), 91–106.
Gosling, S. D., Rentfrow, P. J., & Swann, W. B., Jr. (2003). A very brief measure of the Big-Five personality domains. Journal of Research in Personality, 37(6), 504–528.
GroupLens Research. (2017). MovieLens: Non-commercial, personalized movie recommendations. Retrieved April 20, 2017, from https://movielens.org/
Gupta, S., Adhikari, U., Varshney, S., & Choudhury, T. (2025). Computational analysis of genre effects on movie ratings using MLP algorithms. Journal of Computer Science, 21(4), 905–917. https://doi.org/10.3844/jcssp.2025.905.917
Hall, A. (2005). Audience personality and the selection of media and media genres. Media Psychology, 7(4), 377–398.
Harper, F. M., & Konstan, J. A. (2017). MovieLens 100K Dataset [Data set]. GroupLens Research, University of Minnesota. Retrieved April 20, 2017, from https://grouplens.org/datasets/movielens/100k/
Hwang, T.-G., Park, C.-S., Hong, J.-H., & Kim, S. K. (2016). An algorithm for movie classification and recommendation using genre correlation. Multimedia Tools and Applications, 75, 12843–12858.
Karumur, R. P., Nguyen, T. T., & Konstan, J. A. (2016). Exploring the value of personality in predicting rating behaviors: A study of category preferences on MovieLens. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys) (pp. 139–142). Boston, MA, USA: ACM. https://doi.org/10.1145/2959100.2959140
Kazeminia, M., Kaedi, M., & Ganji, B. (2019). Personality-based personalization of online store features using genetic programming: Analysis and experiment. Journal of Theoretical and Applied Electronic Commerce Research, 14(1), 16–29.
Khan, E. M., Mukta, M. S. H., Ali, M. E., & Mahmud, J. (2020). Predicting users’ movie preference and rating behavior from personality and values. ACM Transactions on Interactive Intelligent Systems, 10(3), Article 18.
Kim, J., Kim, J., & Choi, J. (2021). Sequential movie genre prediction using average transition probability with clustering. Applied Sciences, 11(24), Article 11841.
Mlika, F., & Karoui, W. (2020). Proposed model to intelligent recommendation system based on Markov chains and grouping of genres. Procedia Computer Science, 176, 868–877.
Mondal, P., Kapoor, P., Singh, S., Saha, S., Singh, J. P., & Singh, A. K. (2023). Genre effect toward developing a multi-modal movie recommendation system in Indian setting. IEEE Transactions on Consumer Electronics, 70(1), 2517–2526.
Nalmpantis, O., & Tjortjis, C. (2017). The 50/50 recommender: A method incorporating personality into movie recommender systems. In Engineering Applications of Neural Networks: 18th International Conference, EANN 2017, Athens, Greece, August 25–27, 2017, Proceedings (Communications in Computer and Information Science, Vol. 744, pp. 498–507). Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_42
Nave, G., Rentfrow, J., & Bhatia, S. (2020). We are what we watch: Movie plots predict the personalities of their fans. PsyArXiv. https://doi.org/10.31234/osf.io/wsdu8
Negaresh, F., Kaedi, M., & Zojaji, Z. (2023). Gender identification of mobile phone users based on internet usage pattern. International Journal of Engineering, 36(2), 335–347. https://doi.org/10.5829/ije.2023.36.02b.14
Nguyen, T. T., Maxwell Harper, F., Terveen, L., & Konstan, J. A. (2018). User personality and user satisfaction with recommender systems. Information Systems Frontiers, 20(6), 1173–1189.
Pal, A., Barigidad, A., & Mustafi, A. (2020). Identifying movie genre compositions using neural networks and introducing GenRec—a recommender system based on audience genre perception. In 2020 5th International Conference on Computing, Communication and Security (ICCCS) (pp. 1–7). Patna, India: IEEE. https://doi.org/10.1109/ICCCS49678.2020.9276893
Raj, S., Sharma, A., Saha, S., Singh, B., & Pedanekar, N. (2024). Transformative movie discovery: Large language models for recommendation and genre prediction. IEEE Access, 12, 186626-186638.
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 3982–3992). Hong Kong, China: Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1410
Ricci, F., Rokach, L., & Shapira, B. (2022). Recommender systems: Techniques, applications, and challenges. In Recommender Systems Handbook (2nd ed., pp. 1–35). Springer, New York, NY.
SadighZadeh, S., & Kaedi, M. (2022). Modeling user preferences in online stores based on user mouse behavior on page elements. Journal of Systems and Information Technology, 24(2), 112–130.
Salehi, H., Kaedi, M., & Sattari, M. (2025). Estimating the self-esteem of social network users based on their account information. Soft Computing Journal, 14(1), 122–133. https://doi.org/10.22052/scj.2024.254082.1210
Seo, Y. D., Kim, Y. G., Lee, E., & Kim, H. (2021). Group recommender system based on genre preference focusing on reducing the clustering cost. Expert Systems with Applications, 183, Article 115396.
Shafiloo, R., Kaedi, M., & Pourmiri, A. (2024). Considering user dynamic preferences for mitigating negative effects of long-tail in recommender systems. Information Sciences, 669, Article 120558. https://doi.org/1010.1016/j.ins.2024.120558
Singh, A. (2021). IMDb Movies Dataset [Data set]. Kaggle. Retrieved April 20, 2024, from https://www.kaggle.com/datasets/ashpalsingh1525/imdb-movies-dataset
Wang, H. (2018). Utilizing imbalanced data and classification cost matrix to predict movie preferences. International Journal of Artificial Intelligence and Applications, 9(6), 1–12. https://doi.org/10.5121/ijaia.2018.9601
Wang, Z., Yang, Y., He, L., & Gu, J. (2014). User identification within a shared account: Improving IP-TV recommender performance. In Advances in Databases and Information Systems: 18th East European Conference (Lecture Notes in Computer Science, Vol. 8716, pp. 219–233). Ohrid, Macedonia: Springer.
Widiyaningtyas, T., Hidayah, I., & Adji, T. B. (2021). User profile correlation-based similarity (UPCSim) algorithm in movie recommendation system. Journal of Big Data, 8(1), Article 52.
Wu, W., & Chen, L. (2015). Implicit acquisition of user personality for augmenting movie recommendations. In Proceedings of the 23rd International Conference on User Modeling, Adaptation and Personalization (UMAP) (Vol. 9146, pp. 302–314). Dublin, Ireland: Springer.
Human and Information Interaction

Articles in Press, Accepted Manuscript
Available Online from 25 March 2026