Jomsri Pijitra, Prangchumpol Dulyawit, Poonsilp Kittiya, Panityakul Thammarat
Suan Sunandha Rajabhat University, Dusit, Bangkok, 10300, Thailand.
Prince of Songkla University, Hat Yai, Songkhla, 90110, Thailand.
F1000Res. 2024 Nov 18;12:1140. doi: 10.12688/f1000research.133013.3. eCollection 2023.
The demand for online education promotion platforms has increased. In addition, the digital library system is one of the many systems that support teaching and learning. However, most digital library systems store books in the form of libraries that were developed or purchased exclusively by the library, without connecting data with different agencies in the same system.
A hybrid recommender system model for digital libraries, developed from multiple online publishers, has created a prototype digital library system that connects various important knowledge sources from multiple digital libraries and online publishers to create an index and recommend e-books. The developed system utilizes an API-based linking process to connect various important sources of knowledge from multiple data sources such as e-books on education from educational institutions, e-books from government agencies, and e-books from religious organizations are stored separately. Then, a hybrid recommender system suitable for users was developed using Collaborative Filtering (CF) model together with Content-Based Filtering. This research proposed the hybrid recommender system model, which took into account the factors of book category, reading habits of users, and sources of information. The evaluation of the experiments involved soliciting feedback from system users and comparing the results with conventional recommendation methods.
A comparison of NDCG scores, and Precision scores were conducted for Hybrid Score 50:50, Hybrid Score 20:80, Hybrid Score 80:20, CF-score and CB-score. The experimental result was found that the Hybrid Score 80:20 method had the highest average NDCG score.
Using a hybrid recommender system model that combines 80% Collaborative Filtering, and 20% Content-Based Filtering can improve the recommender method, leading to better referral efficiency and greater overall efficiency compared to traditional approaches.
在线教育推广平台的需求不断增加。此外，数字图书馆系统是支持教学的众多系统之一。然而，大多数数字图书馆系统以图书馆独自开发或购买的图书馆形式存储书籍，未在同一系统中与不同机构的数据建立连接。
一个由多个在线出版商开发的数字图书馆混合推荐系统模型，创建了一个原型数字图书馆系统，该系统连接多个数字图书馆和在线出版商的各种重要知识源，以创建索引并推荐电子书。所开发的系统利用基于应用程序编程接口（API）的链接过程，连接来自多个数据源的各种重要知识源，如教育机构的教育类电子书、政府机构的电子书以及宗教组织的电子书，这些电子书分别存储。然后，结合协同过滤（CF）模型和基于内容的过滤，开发了一个适合用户的混合推荐系统。本研究提出了混合推荐系统模型，该模型考虑了书籍类别、用户阅读习惯和信息来源等因素。实验评估包括征求系统用户的反馈，并将结果与传统推荐方法进行比较。
对混合评分50:50、混合评分20:80、混合评分80:20、CF评分和CB评分进行了归一化折损累计增益（NDCG）分数和精准度分数的比较。实验结果发现，混合评分80:20方法的平均NDCG分数最高。
使用结合80%协同过滤和20%基于内容过滤的混合推荐系统模型，可以改进推荐方法，与传统方法相比，能带来更好的推荐效率和更高的整体效率。
