中国邮电高校学报(英文版) ›› 2022, Vol. 29 ›› Issue (4): 89-105.doi: 10.19682/j.cnki.1005-8885.2022.2022

• Others • 上一篇    下一篇

Summary of research on recommendation system based on serendipity

Meng Wei, Wang Liting, Lu Meng   

  1. 1. School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
    2. Engineering Research Center for Forestry-oriented Intelligent Information Processing, National Forestry and
    Grassland Administration, Beijing 100083, China
  • 收稿日期:2021-07-02 修回日期:2021-08-18 接受日期:2021-11-14 出版日期:2022-08-31 发布日期:2022-08-31
  • 通讯作者: Meng Wei, E-mail: mnancy@bjfu.edu.cn E-mail:mnancy@bjfu.edu.cn

Summary of research on recommendation system based on serendipity

Meng Wei, Wang Liting, Lu Meng   

  1. 1. School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
    2. Engineering Research Center for Forestry-oriented Intelligent Information Processing, National Forestry and
    Grassland Administration, Beijing 100083, China
  • Received:2021-07-02 Revised:2021-08-18 Accepted:2021-11-14 Online:2022-08-31 Published:2022-08-31
  • Contact: Meng Wei, E-mail: mnancy@bjfu.edu.cn E-mail:mnancy@bjfu.edu.cn

摘要: Personalized recommender systems provide various personalized recommendations for different users through the analysis of their respective historical data. Currently, the problem of the “filter bubble" which has to do with over-specialization persists. Serendipity (SRDP), one of the evaluation indicators, can provide users with unexpected and useful recommendations, and help to successfully mitigate the filter bubble problem, and enhance users' satisfaction levels and provide them with diverse recommendations. Since SRDP is highly subjective and challenging to study, only a few studies have focused on it in recent years. In this study, the research results on SRDP were summarized, the various definitions of SRDP and its applications were discussed, the specific SRDP calculation process from qualitative to quantitative perspectives was presented, the challenges and the development directions were outlined to provide a framework for further research.

关键词: serendipity, recommended algorithm, recommended diversity, filter bubbles, evaluation indicators

Abstract: Personalized recommender systems provide various personalized recommendations for different users through the analysis of their respective historical data. Currently, the problem of the “filter bubble" which has to do with over-specialization persists. Serendipity (SRDP), one of the evaluation indicators, can provide users with unexpected and useful recommendations, and help to successfully mitigate the filter bubble problem, and enhance users' satisfaction levels and provide them with diverse recommendations. Since SRDP is highly subjective and challenging to study, only a few studies have focused on it in recent years. In this study, the research results on SRDP were summarized, the various definitions of SRDP and its applications were discussed, the specific SRDP calculation process from qualitative to quantitative perspectives was presented, the challenges and the development directions were outlined to provide a framework for further research.

Key words: serendipity, recommended algorithm, recommended diversity, filter bubbles, evaluation indicators

中图分类号: