28, February 2025

A Cross-Domain Recommender System for Movies, Books, and News: Leveraging Content-Based Filtering and Similarity Computation

Author(s): Mihir Patel, Bhaskar Das, N. G. Suhans Raj, Sri Gouri Reddy, Shivkumar Suwarnkar

Authors Affiliations:

  1. Student, Department of CSE(DS), Hyderabad Institute of Technology and Management, Hyderabad, India
  2. Associate Professsor, Department of CSE(DS), Hyderabad Institute of Technology and Management, Hyderabad,India
  3. Student, Department of CSE(DS), Hyderabad Institute of Technology and Management, Hyderabad, India
  4. Student, Department of CSE(DS), Hyderabad Institute of Technology and Management, Hyderabad, India
  5. Student, Department of CSE(DS), Hyderabad Institute of Technology and Management, Hyderabad, India

 

DOIs:10.2015/IJIRMF/202502031     |     Paper ID: IJIRMF202502031


Abstract
Keywords
Cite this Article/Paper as
References

In an age of unprecedented digital content proliferation, users are often inundated with choices across various domains, such as movies, books, and news. The challenge lies in identifying and recommending relevant content that aligns with individual preferences while spanning multiple media types. To address this challenge, this research proposes a Cross-Domain Recommender System for Movies, Books, and News, which leverages advanced Natural Language Processing (NLP) techniques and content-based filtering to deliver cohesive and personalized recommendations. The system's objective is to break the siloed nature of traditional recommendation systems by enabling cross-domain content discovery. It begins by analyzing user preferences in one domain, such as movie genres or plot themes, and extrapolates this information to recommend similar or complementary content in other domains, including books and news. For instance, fans of dystopian films may receive recommendations for novels exploring similar themes or news articles on futuristic societal trends. This integration is achieved through the extraction and vectorization of features like genres, keywords, and summaries, enabling the computation of semantic similarities across domains. The methodology integrates vectorized representations, similarity metrics, and user profiling to establish a unified recommendation framework. Preliminary results highlight the system’s ability to enhance user engagement by fostering diverse content discovery. The findings demonstrate the feasibility of bridging domains through shared linguistic and thematic patterns, enriching the overall user experience. This study underscores the transformative potential of cross-domain recommender systems in personalizing content consumption. By employing NLP-driven techniques, the proposed system sets a foundation for intelligent, user-centric media navigation, paving the way for future innovations in recommendation technologies.

Cross-Domain Recommendation Systems, Natural Language Processing (NLP), Content-Based Filtering, , TF-IDF, Word Embeddings, Cross-Media Content Personalization

Mihir Patel, Bhaskar Das, N. G. Suhans Raj, Sri Gouri Reddy, Shivkumar Suwarnkar(2025); A Cross-Domain Recommender System for Movies, Books, and News: Leveraging Content-Based Filtering and Similarity Computation, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-11, Issue-2, Pp.199-208.          Available on –   https://www.ijirmf.com/

 

  1. Wayesa, F., Leranso, M., Asefa, G., & Kedir, A. (2023). Pattern-based hybrid book recommendation system using semantic relationships. Scientific Reports13(1), 3693.
  2. Ayyaz, S., Qamar, U., & Nawaz, R. (2018). HCF-CRS: A Hybrid Content based Fuzzy Conformal Recommender System for providing recommendations with confidence. PloS one13(10), e0204849.
  3. Dang, C. N., Moreno-García, M. N., & Prieta, F. D. L. (2021). An approach to integrating sentiment analysis into recommender systems. Sensors21(16), 5666.
  4. Uta, M., Felfernig, A., Le, V. M., Tran, T. N. T., Garber, D., Lubos, S., & Burgstaller, T. (2024). Knowledge-based recommender systems: overview and research directions. Frontiers in big Data7, 1304439.
  5. Zhong, S. T., Huang, L., Wang, C. D., Lai, J. H., & Philip, S. Y. (2020). An autoencoder framework with attention mechanism for cross-domain recommendation. IEEE Transactions on Cybernetics52(6), 5229-5241.
  6. Zhang, Q., Lu, J., Wu, D., & Zhang, G. (2018). A cross-domain recommender system with kernel-induced knowledge transfer for overlapping entities. IEEE transactions on neural networks and learning systems30(7), 1998-2012.
  7. Liang, R., Zhang, Q., Wang, J., & Lu, J. (2022). A hierarchical attention network for cross-domain group recommendation. IEEE transactions on neural networks and learning systems35(3), 3859-3873.
  8. Chen, J., Wang, C., Wang, J., Ying, X., & Wang, X. (2017). Learning the personalized intransitive preferences of images. IEEE Transactions on Image Processing26(9), 4139-4153.
  9. Hao, P., Zhang, G., Martinez, L., & Lu, J. (2017). Regularizing knowledge transfer in recommendation with tag-inferred correlation. IEEE transactions on cybernetics49(1), 83-96.
  10. Liao, W., Zhang, Q., Yuan, B., Zhang, G., & Lu, J. (2022). Heterogeneous multidomain recommender system through adversarial learning. IEEE Transactions on Neural Networks and Learning Systems34(11), 8965-8977.
  11. Xiong, W., & Zhang, Y. (2023). An intelligent film recommender system based on emotional analysis. PeerJ Computer Science9, e1243.
  12. Cui, P., Yin, B., & Xu, B. (2023). The application of social recommendation algorithm integrating attention model in movie recommendation. Scientific Reports13(1), 16938.
  13. The Movie Database. (n.d.). Popular movies. Retrieved from https://api.themoviedb.org/3/movie/popular
  14. (n.d.). *Goodreads API*. Retrieved from https://www.goodreads.com/api
  15. Lubos, S., Felfernig, A., & Tautschnig, M. (2023). An overview of video recommender systems: state-of-the-art and research issues. Frontiers in big Data6, 1281614.
  16. Fernández, D., Formoso, V., Cacheda, F., & Carneiro, V. (2019). High Order Profile Expansion to tackle the new user problem on recommender systems. PloS one14(11), e0224555.

Loading


Download Full Paper

Download PDF No. of Downloads:7 | No. of Views: 13