基于用户画像和视频兴趣标签的个性化推荐  

Video Personalized Recommendation Based on User Profile and Video Interest Tags

作　　者：吴剑云[1] 胥明珠 WU Jian-yun;XU Ming-zhu(School of Business,Qingdao University,Qingdao 266071,China;School of Management,Shanghai University,Shanghai 200444,China)

机构地区：[1]青岛大学商学院,山东青岛266071 [2]上海大学管理学院,上海200444

出　　处：《情报科学》2021年第1期128-134,共7页Information Science

基　　金：教育部人文社科规划基金项目“资源编排视角下制造企业数字创业生态系统运行机制研究”(19YJA630115);山东省自然科学基金项目“面向社会化商务的个性化推荐研究:基于社会计算的视角”(ZR2018MG005)。

摘　　要：【目的/意义】用户画像深刻地描述了视频用户的个体和群体行为特征,为视频的个性化推荐服务提供参考。【方法/过程】通过文本挖掘对爬取的视频、用户及其观影数据分析,构建单个用户画像,并通过K-Means和LDA模型对用户聚类并提取主题,挖掘群体用户特征。基于用户画像和时间指数衰减的视频兴趣标签,并结合视频喜爱度和协同过滤,进行视频推荐。【结果/结论】考虑时间指数衰减的个性化推荐,提高了系统对用户兴趣的感知。结合视频喜爱度和协同过滤,推荐视频评分达0.87,有助于提高用户对网站的忠诚度和活跃度。【创新/局限】基于用户生成内容的文本挖掘结果,进行单个和群体用户画像,并创新性采用时间指数衰减构建用户视频兴趣标签,以捕获用户兴趣的变化。由于网络爬虫的限制,实验数据量有一定的局限性,且特征提取兴趣范围有限。【Purpose/significance】User Profile can describe the individual and group behavior characteristics of video users in a more profound manner,and provide reference for personalized recommendation service of video.【Method/process】Through text mining to the crawling video,users and their viewing data analysis,this paper builds a single user profile.Furthermore,based on K-Means and LDA model,this paper clusters users and extracts topics,and then mines the characteristics of group users.Video interest tags based on user profile and time exponential decay combined with video preference and collaborative filtering,are used for video recommendation.【Result/conclusion】Considering the personalized recommendation of time exponential decay,the system’s awareness of user interest is improved.Combined with video preference and collaborative filtering,the recommended video rating is 0.87,which helps increase user loyalty and activity to the site.【Innovation/limitation】Based on the results of text mining of user-generated content,individual and group user profile are carried out.And then this paper innovatively uses time exponential decay to construct user video interest tags to capture dynamic user interest.Due to the limitation of Network Crawler,the amount of experimental data has some limitations,and the range of interest in feature extraction is limited.

关 键 词：文本挖掘 用户画像 视频标签 指数衰减 个性化推荐 

分 类 号：G254.9[文化科学—图书馆学]