User Profiling for CSDN:Keyphrase Extraction,User Tagging and User Growth Value Prediction

作     者：Guoliang Xing Hao Gao Qi Cao Xinyu Yue Bingbing Xu Keting Cen Huawei Shen 

作者机构：Key Laboratory of Network Data Science and TechnologyInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of SciencesBeijing 100049China 

出 版 物：《Data Intelligence》 (数据智能（英文）)

年 卷 期：2019年第1卷第2期

页      面：137-159页

核心收录：

学科分类：0711[理学-系统科学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 

基　　金：The work is supported by the National Natural Science Foundation of China(NSFC)under grant numbers 61472400,91746301 and 61802371 H.Shen is also funded by K.C.Wong Education Foundation and the Youth Innovation Promotion Association of the Chinese Academy of Sciences 

主　　题：User profiling Keyphrase extraction User tagging Growth value prediction Word embedding 

摘      要：The Chinese Software Developer Network(CSDN)is one of the largest information technology communities and service platforms in *** paper describes the user profiling for CSDN,an evaluation track of SMP Cup *** contains three tasks:(1)user document keyphrase extraction,(2)user tagging and(3)user growth value *** the first task,we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive *** the second task,to deal with class imbalance and capture the interdependency between classes,we propose a two-stage framework:(1)for each class,we train a binary classifier to model each class against all of the other classes independently;(2)we feed the output of the trained classifiers into a softmax classifier,tagging each user with multiple *** the third task,we propose a comprehensive architecture to predict user growth *** contributions in this paper are summarized as follows:(1)we extract various types of features to identify the key factors in user value growth;(2)we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model,resulting in an impressive performance in our *** the competition,we achieved the first place out of 329 teams.