计算机科学 ›› 2017, Vol. 44 ›› Issue (10): 254-258.doi: 10.11896/j.issn.1002-137X.2017.10.046
金相宏,李琳,钟珞
JIN Xiang-hong, LI Lin and ZHONG Luo
摘要: 随着电子商务的飞速发展,网络购物越来越被消费者认同,而随之产生的产品评论给消费者的购买决策带来了影响。产品评论是指用户在购物站点上对商品的评价信息,而 经过分析和研究发现这些评论中充斥着大量的垃圾评论,因此垃圾评论的识别成了电子商务在提高服务质量的过程中需解决的重要问题之一。根据垃圾评论的主要特点提出LDA-SP(LDA-Sentiment Polarity)垃圾评论识别方法。首先利用LDA主题模型过滤出内容型垃圾评论,然后结合情感分析识别出欺骗型垃圾评论。对网络商城的大量评论数据进行准确度分析实验的结果表明,LDA-SP方法的识别准确度高于传统的LDA主题模型和单一的情感极性分析方法,能够有效地检测垃圾评论,从而使产品评论信息更加客观准确,为电子商务用户提供了有效的参考信息。
[1] DoubleClick Search before the purchase Understanding BuyerSearch Activity as it Builds to Online purchase.http:// www.Doubleclick.com /insight/pdfs/searchpurchase_0502.pdf. [2] HEYDARI A,ALITAVAKOLI M,SALIM N,et al.Detection of review spam:A survey[J].Expert Systems with Applications,2015,2(7):3634-3642. [3] SUN S Y,TIAN X.Product review comment spam detection research[J].Computer Science,2011,38(10):198-201.(in Chinese) 孙升芸,田萱.产品垃圾评论检测研究综述[J].计算机科学,2011,38(10):198-201. [4] GILBERT E,KARAHALIOS K.Understanding Deja Reviewers [C]∥Proc.of ACM Conference on Computer Supported Coo-perative Work.New York,USA,2010:225-228. [5] JINDAL N,LIU B.Opinion spam and analysis[C]∥Internatio-nal Conference on Web Search and Data Mining.ACM,2008:219-230. [6] OTT M,CHOI Y J,CARDIE C,et al.Finding Deceptive Opi-nion Spam by Any Stretch of the Imagination[C]∥Proceedings of the 49th Annual Meeting of the Association for Computatio-nal Linguistics:Human Language Technologies.Stroudsburg,PA,USA:Association for Computational Linguistics,2011:309-319. [7] LIU B.Sentiment Analysis and Opinon Mining[M].Chicago:Morgan & Clayppol,2012:113-115. [8] MA Y,LI F.Detecting review spam:Challenges and opportunities[C]∥2012 8th International Conference on Collaborative Computing:Networking,Applications and Worksharing (CollaborateCom).IEEE,2012:651-654. [9] DIAO Y F,LIN H F.LDA-based Opionion Spam Discovering[J].Journal of Chinese Information Processing,2011,5(1):41-47.(in Chinese) 刁宇峰,林鸿飞.基于LDA模型的博客垃圾评论发现[J].中文信息学报,2011,5(1):41-47. [10] LAI C L,XU K Q,LAU R Y K,et al.Toward a language mo-deling approach for consumer review spam detection[C]∥2010 IEEE 7th International Conference on e-Business Engineering (ICEBE).IEEE,2010:1-8. [11] JIN J,JI P.Co-training Algorithm for Quality Analysis of Online Customer Reviews[J].Journal of Shanghai University(Natural Science Edition),2014,0(3):289-295.(in Chinese) 靳健,季平.用于在线产品评论质量分析的Co-trainning算法[J].上海大学学报(自然科学版),2014,0(3):289-295. [12] 中科院分词系统[DB/OL].http://ictclas.org. [13] XU L H,LIN H F,PAN Y,et al.The structure of the emotional vocabulary ontology[J].Journal of Emotion,2008,27(2):180-185.(in Chinese) 徐琳宏,林鸿飞,潘宇,等.情感词汇本体的构造[J].情感学报,2008,27(2):180-185. [14] BLEI D M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003(3):993-1022. [15] QIU Y F,WANG J K,SHAO L S.Research on Product Review Spammer Detection Based on Users’ Behavior[J].Computer Engineering,2012,8(11):254-257.(in Chinese) 邱云飞,王建坤,邵良杉.基于用户行为的产品垃圾评论者检测研究[J].计算机工程,2012,38(11):254-257. |
No related articles found! |
|