摘要
近年来社交媒体越来越流行,可以从中获得大量丰富多彩的信息的同时,也带来了严重的"信息过载"问题.推荐系统作为缓解信息过载最有效的方法之一,在社交媒体中的作用日趋重要.区别于传统的推荐方法,社交媒体中包含大量的用户产生内容,因此在社交媒体中,通过结合传统的个性化的推荐方法,集成各类新的数据、元数据和清晰的用户关系,产生了各种新的推荐技术.总结了社交推荐系统中的几个关键研究领域,包括基于社会化标注的推荐、组推荐和基于信任的推荐,之后介绍了在信息推荐中考虑时间因素时的情况,最后对社交媒体中信息推荐有待深入研究的难点和发展趋势进行了展望.
Social media has become tremendously popular in recent years, and much rich information can be derived from it. However, the massive amount results in a serious "information overload" problem. As one of the most effective methods to ease the "information overload" problem, recommender systems play an important role in social media. Social media contains a large amount of user-generated content. Through the aggregation of all types of new data, metadata, and clear relationships between users and by combining the traditional method of personal- ized recommendations, a variety of new technologies emerge in recommender systems. This paper summarizes sever- al key research areas in social recommender systems, including recommendations based on social tagging and group recommendations, as well as the recommendations based on trust. It then introduces several temporal aspects that affect social recommender systems, and finally proposes that the research difficulty be tackled while laying out the expectations for future development trends in the information recommendation system in social media.
出处
《智能系统学报》
北大核心
2012年第1期1-8,共8页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金资助项目(61035004)
关键词
信息推荐
信息过载
推荐系统
社交媒体
information recommendation
information overload
recommendation systems
social media