Microblog Personal Topic Detection Method Based on Word2vec

摘要：

　　We propose a novel model architectures for detecting the personarl topic in Microblog.Using googles brand-new Word2vec model, we find an esay and high accurate way to project one Microblog into a vector.In this way, we can use some cluster algorithm to divide personal Microblog into several different topics, which clearly figure out the persons favorite topic.Comparing with normal topic detection, this method is highly personal dependence.Different person will achieve their unique topic.We also use some technique form text mining to improve our performance.Finally, we show that these topics provide state-of-the-art performance on our test set for measuring users interest.

关键词： word2vec Microblog clustering topic detection text mining social networking

作者: DU Zhendong HU Xuelei

作者单位: School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China

会议类型: 国际会议

会议名称: 第一届信息获取与知识服务国际会议暨第六届搜索行为与用户认知研讨会

会议地点: 武汉

会议语种:英文

页码: 116-120

在线出版日期: 2014-10-10（万方平台首次上网日期，不代表论文的发表时间）