Development of a Book Recommendation System Using Artificial Intelligence Technology via the LINE Official Account of Thammasat University Library
Article Sidebar
Main Article Content
Abstract
A book recommendation system using artificial intelligence (AI) was developed at Thammasat University Library to enhance information resource services by providing personalized recommendations matching individual user interests. The development team applied the cross-industry standard process for data mining (CRISP-DM), supporting systematic and structured data analysis, to design and implement the AI-powered book recommendation system. It is integrated with, and delivered by, the Thammasat University Library LINE account (TULIB LINE Official Account: @lifonline), a communication channel accessible to all library patrons.
The system comprises two main modes: (1) automatic, using machine learning techniques, specifically Word2Vec and LightFM, to analyze relationships between books and borrowing behavior to generate suitable recommendations; and (2) interactive, allowing readers to manually select preferred book categories, boosting engagement and recommendation relevance. Results were that user satisfaction with the system was 85.91%, demonstrating that the system efficiently responds to personalized user requirements and interests.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
พงศกร สุกันยา และปานใจ ธารทัศนวงศ์. (2566). การค้นหากฎความสัมพันธ์ของการใช้หนังสือด้วยเทคนิคเหมืองข้อมูล กรณีศึกษาห้องสมุด ศูนย์การแพทย์ปัญญานันทภิกขุ ชลประทาน มหาวิทยาลัยศรีนครินทรวิโรฒ. วารสารห้องสมุด, 67(2), 127–145. https://so06.tci-thaijo.org/index.php/tla_bulletin/article/view/264939
หอสมุดแห่งมหาวิทยาลัยธรรมศาสตร์. (2568). Dashboard ผลสำรวจความพึงพอใจผู้ใช้บริการหอสมุดฯ ปีงบประมาณ 2568. https://library.tu.ac.th/bbs/content/94_475
Hasoon, A. N., Abdulateef, S. K., Abdulameer, R. S., & Shuwandy, M. L. (2025). An intelligent hybrid ai course recommendation framework integrating bert embeddings and random forest classification. Computers, 14(9), 353. https://www.mdpi.com/2073-431X/14/9/353
Liu, X., & Wang, B. (2024). Personalized recommendation system for university digital libraries based on deep neural networks. Proceedings of the 7th International Conference on Computer Information Science and Artificial Intelligence (CISAI 2024). ACM. https://doi.org/10.1145/3703187.3703195
Okon, E. U., Eke, B. O., & Asagba, P. O. (2018). An improved online book recommender system using collaborative filtering algorithm. International Journal of Computer Applications, 179(46), 41-48. https://doi.org/10.5120/ijca2018917193
Pradana, M. A., & Wibowo, A. T. (2024). Movie recommendation system using hybrid filtering with word2vec and restricted boltzmann machines. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 9(1), 231-241. https://doi.org/10.29100/jipi.v9i1.4306
Schröer, C., Kruse, F., & Gómez, J. M. (2021). A systematic literature review on applying CRISP-DM process model. Procedia Computer Science, 181, 526-534. https://doi.org/https://doi.org/10.1016/j.procs.2021.01.199
T, M., Prathap, G., Tanu, A., S, F., & Hurshan, T. (2025). Netflix user engagement analysis. In Future frontiers: mastering the latest in computer technology (pp. 26-35). QTanalytics® India. https://doi.org/10.48001/978-81-980647-0-7-3
Thapanee Boonchob. (20 กันยายน 2563). เข้าใจ CRISP-DM ฉบับเร่งรัด. Medium. https://kamboonchob.medium.com
Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a Standard Process Model for Data Mining. http://cs.unibo.it/~danilo.montesi/CBD/Beatriz/10.1.1.198.5133.pdf
Zhang, J., Wang, S., Lyu, M., Hou, S., & Kim, K.-M. (2025). AI recommendation system attributes: impact mechanisms on user satisfaction and usage intentions in the China market. Journal of East Asia Management, 6(1), 51-79. https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiOrteView.kci?sereArticleSearchBean.artiId=ART003183842
