数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (4): 54-69.doi: 10.11871/jfdc.issn.2096-742X.2021.04.005

• 可视化与可视分析专题 • 上一篇    下一篇

基于局部模型融合的交互式电影推荐系统

王攸妍(),孙康高(),汤颖()   

  1. 浙江工业大学,计算机科学与技术学院,浙江 杭州 310000
  • 收稿日期:2021-06-10 出版日期:2021-08-20 发布日期:2021-08-30
  • 通讯作者: 汤颖
  • 作者简介:王攸妍,浙江工业大学计算机科学与技术学院,硕士研究生,主要研究方向为异构信息网络挖掘和数据可视化分析。
    本文中负责论文写作,系统开发与系统测试。
    WANG Youyan is a master's student at the School of Computer Science and Technology, Zhejiang University of Technology. Her main research interests cover heterogeneous information network mining and data visuali-zation analysis.
    In this paper, she is responsible for thesis writing, system implementation, and system testing.
    E-mail: ping_o96@qq.com|孙康高,浙江工业大学计算机科学与技术学院,硕士研究生,主要研究方向为推荐算法和数据可视化。
    本文中负责推荐算法的设计与开发。
    SUN Kanggao is a master's student at the School of Computer Science and Technology, Zhejiang University of Technology. His main research interests cover recommendation algorithms and data visualization.

    In this paper, he is responsible for the design and development of recommendation algorithm.
    E-mail: sunkanggao@163.com|汤颖,浙江工业大学计算机科学与技术学院,教授,主要研究方向为异构信息网络挖掘、数据可视化。
    本文中负责算法框架以及论文写作指导
    TANG Ying is currently the Professor of the Department of Computer Science and Technology, Zhejiang University of Technology. Her research interests cover heterogeneous information network mining and information visualization.
    In this paper, she is responsible for the design of algorithm framework and paper writing guidance.
    E-mail: ytang@zjut.edu.cn
  • 基金资助:
    国家自然科学基金面上项目(61972355);浙江省公益技术研究计划(LGG19F020012)

Interactive Movie Recommendation System Based on Local Model Fusion

WANG Youyan(),SUN Kanggao(),TANG Ying()   

  1. Department of Computer Science &Technology, Zhejiang University of Technology, Hangzhou, Zhejiang 310000, China
  • Received:2021-06-10 Online:2021-08-20 Published:2021-08-30
  • Contact: TANG Ying

摘要:

【目的】设计并实现一个交互式可视推荐系统,帮助用户理解推荐结果的产生原因,提高使用体验以及对推荐系统的信任。【方法】从用户历史观影标签集合中提取用户偏好特征,通过LDA模型基于此特征对用户进行聚类,并利用SLIM模型对不同用户子群分别训练局部模型,最后利用训练过程的上下文语义信息设计和实现最终的交互式电影推荐系统。【结果】设计了一个交互式的电影推荐系统RecVis,能够可视化推荐原因和用户画像,向用户提供推荐解释和交互反馈功能,以及实时获得根据其交互反馈的感兴趣的最新推荐结果。【结论】通过豆瓣电影数据集的测试,证明了该系统在推荐方面的有效性,并通过一系列案例分析验证了RecVis能够帮助用户理解推荐结果,增加对推荐系统的信任。

关键词: 模型融合, 稀疏线性模型, 主题模型, 用户画像, 交互式推荐

Abstract:

[Objective] To improve user experience and confidence in the recommendation system, and help users understand the cause of recommendation, we design and implement an interactive visual recommendation system. [Methods] Firstly, we extract the preference features of each user from the user's history viewing tag set, and allow all users to be clustered into different subgroups based on these preference features using the LDA topic model. After that, we apply the SLIM sparse linear model to train the local recommendation model separately for each user subgroup. Finally, we use the contextual semantic information of the training process to design and implement the interactive movie recommendation system. [Results] This system, RecVis, can visualize the semantic information of recommendation and user portraits, provide recommendation explanation and interactive feedback function, and obtain the latest recommendation according to the user's interactive feedback in real-time. [Conclusions] The test on the Douban movie dataset proves the effectiveness of the system in terms of recommendation. In addition, a series of case studies verify that RecVis can help users understand the recommendation results and increase trust in the recommendation system.

Key words: model fusion, SLIM, topic model, user portrait, interactive movie recommendation