一种基于支持向量机和主题模型的评论分析方法
|
摘要
在移动应用软件中,用户评论是一种重要的用户反馈途径.用户可能提到一些移动应用使用中的问题,比如系统兼容性问题、应用崩溃等.随着移动应用软件的广泛流行,用户提供大量无结构化的反馈评论.为了从用户抱怨评论中提取有效信息,提出一种基于支持向量机和主题模型的评论分析方法 RASL(reviewanalysis methodbased on SVM and LDA)以帮助开发人员更好、更快地了解用户反馈.首先对移动应用的中、差评提取特征,然后使用支持向量机对评论进行多标签分类.随后使用LDA主题模型(latentdirichletallocation)对各问题类型下的评论进行主题提取与代表句提取.从两个移动应用中爬取5 141条用户原始评论,并对这些评论分别用RASL方法和ASUM方法进行处理,得到两个新的文本.与经典方法ASUM相比,RASL方法的困惑度更低、可理解性更佳,包含更完整的原始评论信息,冗余信息也更少.
In mobile apps(applications), the app reviews by users have become an important feedback resource. Users may raise some issues when they use apps, such as system compatibility issues, application crashes, and so on. With the development of mobile apps,users provide a large number of unstructured feedback comments. In order to extract effective information from user complaint comments,a review analysis method is proposed based on support vector machine(SVM) and latent dirichlet allocation(LDA)(RASL) which can help developers to understand user feedback better and faster. Firstly, features are extracted from the user neutral reviews and negative reviews, and then the support vector machine(SVM) is used to label comments on multiple tags. Next, the LDA topic model is used to get topic extraction and representative sentence extraction which are performed on the comments under each question type. 5141 original reviews are crawled from two mobile apps. Then the proposed method(RASL) and ASUM are used to process these comments to get new texts. In comparison with the classical approach ASUM, RASL has less perplexity, better understandability, more complete original review information, and less redundant information.
In mobile apps(applications), the app reviews by users have become an important feedback resource. Users may raise some issues when they use apps, such as system compatibility issues, application crashes, and so on. With the development of mobile apps,users provide a large number of unstructured feedback comments. In order to extract effective information from user complaint comments,a review analysis method is proposed based on support vector machine(SVM) and latent dirichlet allocation(LDA)(RASL) which can help developers to understand user feedback better and faster. Firstly, features are extracted from the user neutral reviews and negative reviews, and then the support vector machine(SVM) is used to label comments on multiple tags. Next, the LDA topic model is used to get topic extraction and representative sentence extraction which are performed on the comments under each question type. 5141 original reviews are crawled from two mobile apps. Then the proposed method(RASL) and ASUM are used to process these comments to get new texts. In comparison with the classical approach ASUM, RASL has less perplexity, better understandability, more complete original review information, and less redundant information.
引文
[1]Zhang L.The sentiment analysis&user requirement mining based on mobile user comment[Ph.D.Thesis].Beijing:BeiHang University,2015(in Chinese with English abstract).[1]张林.基于移动在线评论的用户情感分析及需求挖掘研究[博士学位论文].北京:北京航空航天大学,2015.
[2]Pagano D,Maalej W.User feedback in the appstore:An empirical study.In:Proc.of the 2013 21st IEEE Int’l Conf.on Requirements Engineering(RE).IEEE,2013.125-134.
[3]Pagano D,Brügge B.User involvement in software evolution practice:a case study.In:Proc.of the 2013 Int’l Conf.on Software Engineering.IEEE Press,2013.953-962.
[4]Panichella S,Di Sorbo A,Guzman E,et al.How can I improve my app?Classifying user reviews for software maintenance and evolution.In:Proc.of the 2015 IEEE Int’l Conf.on Software Maintenance and Evolution(ICSME).IEEE,2015.281-290.
[5]Maalej W,Nabil H.Bug report,feature request,or simply praise?On automatically classifying app reviews.In:Proc.of the 2015IEEE 23rd Int’l Conf.on Requirements Engineering(RE).IEEE,2015.116-125.
[6]Mcilroy S,Ali N,Khalid H,Hassan AE.Analyzing and automatically labelling the types of user issues that are raised in mobile app reviews.Empirical Software Engineering,2016,21(3):1067-1106.
[7]Galvis Carre?o LV,Winbladh K.Analysis of user comments:An approach for software requirements evolution.In:Proc.of the2013 Int’l Conf.on Software Engineering.IEEE Press,2013.582-591.
[8]Jiang W,Zhang L,Dai Y,Jiang J,Wang G.Analyzing helpfulness of online reviews for user requirements elicitation.Chinese Journal of Computers,2013,36(1):119-131(in Chinese with English abstract).[8]姜巍,张莉,戴翼,蒋竞,王刚.面向用户需求获取的在线评论有用性分析.计算机学报,2013,36(1):119-131.
[9]Blei DM,Ng AY,Jordan MI.Latent dirichlet allocation.Journal of Machine Learning Research,2003,3:993-1022.
[10]Zhang L,Huang XY,Jiang J,Hu YK.Cslabel:An approach for labelling mobile app reviews.Journal of Computer Science and Technology,2017,32(6):1076-1089.
[11]Seaman CB,Shull F,Regardie M,et al.Defect categorization:Making use of a decade of widely varying historical data.In:Proc.of the 2nd ACM-IEEE Int’l Symp.on Empirical Software Engineering and Measurement.ACM Press,2008.149-157.
[12]Seaman CB.Qualitative methods in empirical studies of software engineering.IEEE Trans.on Software Engineering,1999,25(4):557-572.
[13]Shrout PE,Fleiss JL.Intraclass correlations:Uses in assessing rater reliability.Psychological Bulletin,1979,86(2):420-428.
[14]Salton G.The SMART Retrieval System?Experiments in Automatic Document Processing.Prentice-Hall,1971.
[15]Salton G,Buckley C.Term-weighting approaches in automatic text retrieval.Information Processing&Management,1988,24(5):513-523.
[16]Hall M,Frank E,Holmes G,et al.The WEKA data mining software:an update.ACM SIGKDD Explorations Newsletter,2009,11(1):10-18.
[17]Tsoumakas G,Katakis I,Vlahavas I.Mining Multi-label Data.Data Mining and Knowledge Discovery Handbook.Boston:Springer-Verlag,2009.667-685.
[18]Witten IH,Frank E,Hall MA,et al.Data Mining:Practical Machine Learning Tools and Techniques.Morgan Kaufmann Publishers,2016.
[19]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization-Advances in Kernel Methods.Cambridge:MIT Press,1998.185-208.
[20]Elkan C.The foundations of cost-sensitive learning.In:Proc.of the 7th Int’l Joint Conf.on Artificial Intelligence.2001.973-978.
[21]Mann HB,Whitney DR.On a test of whether one of two random variables is stochastically larger than the other.The Annals of Mathematical Statistics,1947,18(1):50-60.
[2]Pagano D,Maalej W.User feedback in the appstore:An empirical study.In:Proc.of the 2013 21st IEEE Int’l Conf.on Requirements Engineering(RE).IEEE,2013.125-134.
[3]Pagano D,Brügge B.User involvement in software evolution practice:a case study.In:Proc.of the 2013 Int’l Conf.on Software Engineering.IEEE Press,2013.953-962.
[4]Panichella S,Di Sorbo A,Guzman E,et al.How can I improve my app?Classifying user reviews for software maintenance and evolution.In:Proc.of the 2015 IEEE Int’l Conf.on Software Maintenance and Evolution(ICSME).IEEE,2015.281-290.
[5]Maalej W,Nabil H.Bug report,feature request,or simply praise?On automatically classifying app reviews.In:Proc.of the 2015IEEE 23rd Int’l Conf.on Requirements Engineering(RE).IEEE,2015.116-125.
[6]Mcilroy S,Ali N,Khalid H,Hassan AE.Analyzing and automatically labelling the types of user issues that are raised in mobile app reviews.Empirical Software Engineering,2016,21(3):1067-1106.
[7]Galvis Carre?o LV,Winbladh K.Analysis of user comments:An approach for software requirements evolution.In:Proc.of the2013 Int’l Conf.on Software Engineering.IEEE Press,2013.582-591.
[8]Jiang W,Zhang L,Dai Y,Jiang J,Wang G.Analyzing helpfulness of online reviews for user requirements elicitation.Chinese Journal of Computers,2013,36(1):119-131(in Chinese with English abstract).[8]姜巍,张莉,戴翼,蒋竞,王刚.面向用户需求获取的在线评论有用性分析.计算机学报,2013,36(1):119-131.
[9]Blei DM,Ng AY,Jordan MI.Latent dirichlet allocation.Journal of Machine Learning Research,2003,3:993-1022.
[10]Zhang L,Huang XY,Jiang J,Hu YK.Cslabel:An approach for labelling mobile app reviews.Journal of Computer Science and Technology,2017,32(6):1076-1089.
[11]Seaman CB,Shull F,Regardie M,et al.Defect categorization:Making use of a decade of widely varying historical data.In:Proc.of the 2nd ACM-IEEE Int’l Symp.on Empirical Software Engineering and Measurement.ACM Press,2008.149-157.
[12]Seaman CB.Qualitative methods in empirical studies of software engineering.IEEE Trans.on Software Engineering,1999,25(4):557-572.
[13]Shrout PE,Fleiss JL.Intraclass correlations:Uses in assessing rater reliability.Psychological Bulletin,1979,86(2):420-428.
[14]Salton G.The SMART Retrieval System?Experiments in Automatic Document Processing.Prentice-Hall,1971.
[15]Salton G,Buckley C.Term-weighting approaches in automatic text retrieval.Information Processing&Management,1988,24(5):513-523.
[16]Hall M,Frank E,Holmes G,et al.The WEKA data mining software:an update.ACM SIGKDD Explorations Newsletter,2009,11(1):10-18.
[17]Tsoumakas G,Katakis I,Vlahavas I.Mining Multi-label Data.Data Mining and Knowledge Discovery Handbook.Boston:Springer-Verlag,2009.667-685.
[18]Witten IH,Frank E,Hall MA,et al.Data Mining:Practical Machine Learning Tools and Techniques.Morgan Kaufmann Publishers,2016.
[19]Platt J.Fast Training of Support Vector Machines Using Sequential Minimal Optimization-Advances in Kernel Methods.Cambridge:MIT Press,1998.185-208.
[20]Elkan C.The foundations of cost-sensitive learning.In:Proc.of the 7th Int’l Joint Conf.on Artificial Intelligence.2001.973-978.
[21]Mann HB,Whitney DR.On a test of whether one of two random variables is stochastically larger than the other.The Annals of Mathematical Statistics,1947,18(1):50-60.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |