社会媒体中用户的隐式消费意图识别

不同于已有的显式消费意图识别的研究，提出了社会媒体中用户的隐式消费意图自动识别方法.该方法将隐式消费意图识别视作多标记分类问题，并综合使用了基于用户关注行为、意图关注行为、意图转发行为以及个人信息的多种特征.由于隐式消费意图识别难以评价，自动抽取了大量跨社会媒体的用户链指信息，利用该方法，共抽取出12万余对的用户链指.在此自动评价集上的实验结果表明，所采用的多标记分类方法对于识别用户的隐式消费意图是行之有效的，其中使用的各种特征对于提高隐式消费意图识别的效果皆有帮助.

Implicit User Consumption Intent Recognition in Social Media

Unlike previous works such as explicit consumption intent recognition research, this paper presents a method that uses user behavior analysis to automatically recognize the implicit consumption intent. Specifically, the proposed method recasts implicit consumption intent recognition as a multi-label classification problem, which combines multiple features based on follower''s behavior, intent behavior, retweets behavior, and user profiles. The paper proposes a method for the automatic extraction of a large user linkage across social media. With the proposed method, more 120000 user linkage pairs are extracted. Experimental results show that the multi-label classification-based method is effective for implicit intent recognition. Especially, the exploited features are all helpful for improving the recognition performance.