中国邮电高校学报(英文) ›› 2019, Vol. 26 ›› Issue (6): 54-62.doi: 10.19682/j.cnki.1005-8885.2019.1026

• Artificial Intelligence • 上一篇    下一篇

Improvement of LDA model with time factor for collaborative filtering

Yao Wenbin, Hu Fangyi   

  1. 1. Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China
    2. National Engineering Laboratory for Mobile Network, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • 收稿日期:2018-04-16 修回日期:2019-12-04 出版日期:2019-12-31 发布日期:2020-03-10
  • 通讯作者: Hu Fangyi, E-mail: 18810210126@163.com E-mail:18810210126@163.com
  • 作者简介:Hu Fangyi, E-mail: 18810210126@163.com

Improvement of LDA model with time factor for collaborative filtering

Yao Wenbin, Hu Fangyi   

  1. 1. Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China
    2. National Engineering Laboratory for Mobile Network, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2018-04-16 Revised:2019-12-04 Online:2019-12-31 Published:2020-03-10
  • Contact: Hu Fangyi, E-mail: 18810210126@163.com E-mail:18810210126@163.com
  • About author:Hu Fangyi, E-mail: 18810210126@163.com

摘要: Collaborative filtering (CF) is one of the most widely used Algorithm in recommender systems, which help users obtain the information they may like. We proposed a latent Dirichlet allocation (LDA) model combining time and rating (TR-LDA) for CF. We use mathematical methods to fit the Ebbinghaus forgetting curve in our method and introduce time weights based on time window to find out the impact of time on user's interests. The user's choice of items is not only influenced by his/ her interests, but also influenced by other's rating. According to the users' feedback, we find their rating distribution on items under the interests. Finally, experimental results on real data sets MovieLens 100 k and MovieLens 1 M show that the proposed Algorithm can predict the user implicit interests effectively and improve the recommendation performance.

关键词: CF, LDA, forgetting curve, time window, feedback

Abstract: Collaborative filtering (CF) is one of the most widely used Algorithm in recommender systems, which help users obtain the information they may like. We proposed a latent Dirichlet allocation (LDA) model combining time and rating (TR-LDA) for CF. We use mathematical methods to fit the Ebbinghaus forgetting curve in our method and introduce time weights based on time window to find out the impact of time on user's interests. The user's choice of items is not only influenced by his/ her interests, but also influenced by other's rating. According to the users' feedback, we find their rating distribution on items under the interests. Finally, experimental results on real data sets MovieLens 100 k and MovieLens 1 M show that the proposed Algorithm can predict the user implicit interests effectively and improve the recommendation performance.

Key words:

CF, LDA, forgetting curve, time window, feedback

中图分类号: