User Occupation Prediction on Microblogs

摘要：

　　User occupation plays an important role in many applications such as personalized recommendation and targeted advertising.However,user occupations on microblogging platforms are usually unavailable to public due to personal privacy.This opens an interesting problem,i.e.,how to predict user occupations on microblogging platforms.In this paper,we propose a framework for extracting user occupations on microblogs.In particular,we implement a number of classification models and devise various sets of features for predicting user occupations,and devise an occupation-oriented lexicon to generate the training data.The experimental results show that the proposed lexicon-based method can achieve higher accuracy compared with traditional models.

关键词： Occupation prediction Feature extraction Word embedding

作者: Xia Lv Peiquan Jin Lihua Yue

作者单位: School of Computer Science and Technology,University of Science and Technology of China,Hefei 230027 School of Computer Science and Technology,University of Science and Technology of China,Hefei 230027

会议类型: 国际会议

会议名称: International Asia-Pacific Web Conference(第18届国际亚太互联网大会)

会议地点: 苏州

会议语种:英文

页码: 497-501

在线出版日期: 2016-09-23（万方平台首次上网日期，不代表论文的发表时间）