Abstract: By exploiting the context information, such as time, relationship and user feedback information in social network, a time-aware social recommendation method based on user feedback is proposed. The proposed method incorporates the temporal factors by introducing a time weight function, which models the decay of user interest. Moreover, the method considers the user positive feedback and negative feedback information, as well as the social relationship information for recommendation. Experimental results and analysis show that the proposed method outperforms the collaborative filtering method for top-k item recommendation in social networks.

Key words: collaborative filtering, time-aware recommendation, user feedback, recommender system, social network

摘要： 将社交网络的动态性和用户反馈信息融入到推荐方法中，提出一种基于用户反馈的时间感知推荐方法。该方法利用时间衰减因子对带有时间加权的动态社交网络进行兴趣衰减分析，使时间间隔较近用户的选择行为对资源对象的推荐作用获得较高的贡献度，体现用户兴趣的时间效应特性。扩展相似度计算方法，将用户反馈表示为正反馈信息和负反馈信息，考虑用户反馈信息对推荐方法的影响。通过在社交网络真实推荐数据集上的对比实验，结果表明该方法优于基于协同过滤的推荐方法。

关键词: 协同过滤, 时间感知推荐, 用户反馈, 推荐系统, 社交网络