Research Article
BibTex RIS Cite

HYBRID BOOK RECOMMENDATION SYSTEM

Year 2025, Volume: 28 Issue: 4, 1886 - 1901, 03.12.2025

Neslihan Çoban , Fahriye Gemci

https://doi.org/10.17780/ksujes.1733196
https://izlik.org/JA47JC28NK

Abstract

This study aims to develop a hybrid book recommendation system that provides personalized suggestions for books added by users to their personal libraries. The system is built on the Flask microframework, and the book data added by users is stored in a SQLite database managed via SQLAlchemy ORM. The recommendation engine operates using a content-based filtering method, where book titles, authors, summaries, and tags are transformed into text-based feature vectors using the TF-IDF vectorization technique. Similarity between books is calculated using the cosine similarity metric, and the most similar books are recommended to the user. To address the cold start problem, a metadata-based baseline recommendation mechanism is integrated into the system. Experimental evaluations demonstrate that the system performs effectively and efficiently on user data. This study presents a practical framework for developing recommendation systems optimized specifically for personal book collections.

Keywords

Personalized recommendation system hybrid filtering Flask SQLAlchemy cosine similarity

References

  • Carbonell, J., & Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 335–336. Melbourne, Australia. https://doi.org/10.1145/290941.291025
  • Chen, L. (2023). AI applications in book recommendation systems. *IEEE Intelligent Systems, 38*(2), 45–58.
  • Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171–4186. Minneapolis, MN. https://doi.org/10.18653/v1/N19-1423
  • Grinberg, M. (2018). Flask web development: Developing web applications with Python (2nd ed.). O’Reilly Media.
  • Johnson, A. R. (2021). Personalized recommendation systems in the digital age. *Artificial Intelligence Review, 12*(4), 567–589.
  • Jones, K. S. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1), 11–21. https://doi.org/10.1108/eb026526
  • Koren, Y. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30–37. https://doi.org/10.1109/MC.2009.263
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
  • Lops, P., de Gemmis, M., & Semeraro, G. (2011). Content-based recommender systems: State of the art and trends. In F. Ricci, L. Rokach, B. Shapira, & P. B. Kantor (Eds.), Recommender systems handbook (pp. 73–105). Springer. https://doi.org/10.1007/978-0-387-85820-3_3
  • Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. *arXiv preprint*, arXiv:1301.3781.
  • Open Library. (2023). Open Library API documentation. https://openlibrary.org/developers/api Park, Y., Park, S., & Jung, W. (2023). Cold start solutions for recommendation systems: A comprehensive review. *Information Processing & Management, 60*(1), 103141. https://doi.org/10.1016/j.ipm.2023.103141
  • Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In P. Brusilovsky, A. Kobsa, & W. Nejdl (Eds.), The adaptive web (pp. 325–341). Springer. https://doi.org/10.1007/978-3-540-72079-9_10
  • Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1997). GroupLens: An open architecture for collaborative filtering of netnews. Proceedings of the ACM Conference on Computer Supported Cooperative Work, 175–186. https://doi.org/10.1145/266714.266717
  • Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender systems: Introduction and challenges. In F. Ricci, L. Rokach, & B. Shapira (Eds.), *Recommender systems handbook* (2nd ed., pp. 1–34). Springer. https://doi.org/10.1007/978-1-4899-7637-6_1
  • Schein, A. I., Popescul, A., Ungar, L. H., & Pennock, D. M. (2002). Methods and metrics for cold-start recommendations. Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 253–260. https://doi.org/10.1145/564376.564421
  • Smith, J., Anderson, B., & Clark, D. (2022). Digital transformation of information access: Trends and implications. Journal of Information Science, 45(3), 123–145. https://doi.org/10.1177/01655515211045678
  • Son, J. W. (2020). Hybrid approaches for cold start recommendation problems. *Expert Systems with Applications, 147*, 113234. https://doi.org/10.1016/j.eswa.2020.113234
  • Wang, H., Wang, N., & Yeung, D.-Y. (2021). Hybrid book recommendation systems: A comprehensive survey. *Knowledge-Based Systems, 214*, 106732. https://doi.org/10.1016/j.knosys.2021.106732
  • Zhang, S., Yao, L., Sun, A., & Tay, Y. (2022). Deep learning-based recommender systems: A survey and new perspectives. *Journal of the Association for Information Science and Technology (JASIST), 73*(5), 712–728. https://doi.org/10.1002/asi.24579

HİBRİT KİTAP ÖNERİ SİSTEMİ

Year 2025, Volume: 28 Issue: 4, 1886 - 1901, 03.12.2025

Neslihan Çoban , Fahriye Gemci

https://doi.org/10.17780/ksujes.1733196
https://izlik.org/JA47JC28NK

Abstract

Bu çalışma, kullanıcıların kendi kütüphanelerine eklediği kitaplar için kişiselleştirilmiş öneriler sunan hibrit bir kitap öneri sistemi geliştirmeyi amaçlamaktadır. Sistem, Flask mikroyapı çatısı üzerine inşa edilmiş olup, kullanıcıların eklediği kitap verileri SQLAlchemy ORM ile yönetilen bir SQLite veritabanında tutulmaktadır. Öneri motoru, içerik tabanlı filtreleme yöntemiyle çalışmakta ve kitapların başlık, yazar, özet ve etiket bilgileri TF-IDF vektörleştirme tekniği kullanılarak metin tabanlı bir öznitelik vektörüne dönüştürülmektedir. Kitaplar arasındaki benzerlik cosine benzerliği metriği ile hesaplanmakta ve kullanıcıya en benzer kitaplar önerilmektedir. Soğuk başlangıç problemini çözmek için meta veri tabanlı bir baseline öneri mekanizması entegre edilmiştir. Deneysel değerlendirmeler, sistemin kullanıcı verileri üzerinde etkili ve hızlı çalıştığını göstermiştir. Bu çalışma, özellikle kişisel kitap kütüphaneleri için optimize edilmiş öneri sistemlerinin geliştirilmesine yönelik pratik bir çerçeve sunmaktadır.

Keywords

Kişiselleştirilmiş öneri sistemi hibrit filtreleme Flask SQLAlchemy cosine benzerliği

Thanks

Kahramanmaraş Sütçü İmam Üniversitesine teşekkür ederiz.

References

  • Carbonell, J., & Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 335–336. Melbourne, Australia. https://doi.org/10.1145/290941.291025
  • Chen, L. (2023). AI applications in book recommendation systems. *IEEE Intelligent Systems, 38*(2), 45–58.
  • Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171–4186. Minneapolis, MN. https://doi.org/10.18653/v1/N19-1423
  • Grinberg, M. (2018). Flask web development: Developing web applications with Python (2nd ed.). O’Reilly Media.
  • Johnson, A. R. (2021). Personalized recommendation systems in the digital age. *Artificial Intelligence Review, 12*(4), 567–589.
  • Jones, K. S. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1), 11–21. https://doi.org/10.1108/eb026526
  • Koren, Y. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30–37. https://doi.org/10.1109/MC.2009.263
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
  • Lops, P., de Gemmis, M., & Semeraro, G. (2011). Content-based recommender systems: State of the art and trends. In F. Ricci, L. Rokach, B. Shapira, & P. B. Kantor (Eds.), Recommender systems handbook (pp. 73–105). Springer. https://doi.org/10.1007/978-0-387-85820-3_3
  • Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. *arXiv preprint*, arXiv:1301.3781.
  • Open Library. (2023). Open Library API documentation. https://openlibrary.org/developers/api Park, Y., Park, S., & Jung, W. (2023). Cold start solutions for recommendation systems: A comprehensive review. *Information Processing & Management, 60*(1), 103141. https://doi.org/10.1016/j.ipm.2023.103141
  • Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In P. Brusilovsky, A. Kobsa, & W. Nejdl (Eds.), The adaptive web (pp. 325–341). Springer. https://doi.org/10.1007/978-3-540-72079-9_10
  • Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1997). GroupLens: An open architecture for collaborative filtering of netnews. Proceedings of the ACM Conference on Computer Supported Cooperative Work, 175–186. https://doi.org/10.1145/266714.266717
  • Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender systems: Introduction and challenges. In F. Ricci, L. Rokach, & B. Shapira (Eds.), *Recommender systems handbook* (2nd ed., pp. 1–34). Springer. https://doi.org/10.1007/978-1-4899-7637-6_1
  • Schein, A. I., Popescul, A., Ungar, L. H., & Pennock, D. M. (2002). Methods and metrics for cold-start recommendations. Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 253–260. https://doi.org/10.1145/564376.564421
  • Smith, J., Anderson, B., & Clark, D. (2022). Digital transformation of information access: Trends and implications. Journal of Information Science, 45(3), 123–145. https://doi.org/10.1177/01655515211045678
  • Son, J. W. (2020). Hybrid approaches for cold start recommendation problems. *Expert Systems with Applications, 147*, 113234. https://doi.org/10.1016/j.eswa.2020.113234
  • Wang, H., Wang, N., & Yeung, D.-Y. (2021). Hybrid book recommendation systems: A comprehensive survey. *Knowledge-Based Systems, 214*, 106732. https://doi.org/10.1016/j.knosys.2021.106732
  • Zhang, S., Yao, L., Sun, A., & Tay, Y. (2022). Deep learning-based recommender systems: A survey and new perspectives. *Journal of the Association for Information Science and Technology (JASIST), 73*(5), 712–728. https://doi.org/10.1002/asi.24579
There are 19 citations in total.

Details

Primary Language Turkish
Subjects Natural Language Processing
Journal Section Research Article
Authors

Neslihan Çoban 0009-0007-9044-7592

Fahriye Gemci 0000-0003-0961-5266

Submission Date July 3, 2025
Acceptance Date September 16, 2025
Publication Date December 3, 2025
DOI https://doi.org/10.17780/ksujes.1733196
IZ https://izlik.org/JA47JC28NK
Published in Issue Year 2025 Volume: 28 Issue: 4

Cite

APA Çoban, N., & Gemci, F. (2025). HİBRİT KİTAP ÖNERİ SİSTEMİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(4), 1886-1901. https://doi.org/10.17780/ksujes.1733196