评论是一种反映事物价值的重要主观信息。该文从用户角度出发,提出一种基于全局用户意图的商品评论自动估价方法。该研究首先定义了一种简易的评论价值划分标准(“实用”和“垃圾”评论),借以实现前瞻性的方法尝试。在此基础上,该文采用SVM分类器作为划分评论价值类别(二元分类问题)的基本平台,并基于这一平台重点考察三种影响评论价值的特征 1)属性热度;2)内容可信度;3)用户情感和观点。该文在文本结构特征的基础上,加入上述三类反映用户意图的特征进行评论价值判定,并在大规模商品评论语料集中进行测试。实验表明通过引入用户意图特征,评论自动估价的性能有较大幅度提高。
Abstract
Reviews reflect the value of things. From the customer’s point of view, we propose a novel method for automatically evaluating the quality of product reviews based on the global-user-intent. In this paper, we firstly divide the reviews into two opposing groups, i.e. useful reviews and spammed reviews. By means of this definition, we attempt to realize a proactive approach. We experiment with SVM classifier to classify the quality of reviews. This is a typical binary classification and taking extra three kinds of features into considerationthe popular information of product, reviewers’ opinion and review credibility. In this paper, we combine text structure feature with above three kinds of features which reflect the global user intent, and then test on a large-scale corpus of product reviews. The experimental results show a significant improvement on the global accuracy by involving diverse user intent features.
Key wordsquality of reviews; attribute extraction; opinion mining; review credibility
关键词
评论价值 /
属性抽取 /
观点挖掘 /
评论可信度
{{custom_keyword}} /
Key words
quality of reviews /
attribute extraction /
opinion mining /
review credibility
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Kim S M, Pantel P, Chklovski T, et al. Automatically assessing review helpfulness[C]//Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. 2006: 423-430.
[2] Ghose A, Ipeirotis P G. Estimating the helpfulness and economic impact of product reviews: mining text and reviewer characteristics[J]. IEEE Transactions on Knowledge and Data Engineering, 2010.
[3] O’Mahony M P, Smyth B. Using readability tests to predict helpful product reviews[C]//Proceedings of Adaptivity, Personalization and Fusion of Heterogeneous Information. 2010: 164-167.
[4] Liu J, Cao Y, Lin C Y, et al. Low-quality product review detection in opinion summarization[C]//Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL). 2007: 334-342.
[5] Jindal N, Liu B. Opinion spam and analysis[C]//Proceedings of the International Conference on Web Search and Web Data Mining. 2008: 219-230.
[6] Danescu-Niculescu-Mizil C, Kossinets G, Kleinberg J, et al. How opinions are received by online communities: a case study on amazon.com helpfulness votes[C]//Proceedings of the 18th International Conference on World Wide Web. 2009: 141-150.
[7] Lu Y, Tsaparas P, Ntoulas A, et al. Exploiting social context for review quality prediction[C]//Proceedings of the 19th International Conference on World Wide Web. 2010: 691-700.
[8] Paltoglou G, Thelwall M. A study of information retrieval weighting schemes for sentiment analysis[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. 2010: 1386-1395.
[9] DuBay W H. The principles of readability[J]. Impact Information, 2004: 1-76.
[10] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3): 27.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金资助项目(60970056;60970057;61003152);教育部博士学科点专项基金项目(2009321110006;20103201110021);江苏省苏州市自然科学基金资助项目(SYG201030)
{{custom_fund}}
PDF(2337 KB)
