协同过滤推荐算法研究: 考虑在线评论情感倾向

王伟, 王洪伟, 孟园

系统工程理论与实践 ›› 2014, Vol. 34 ›› Issue (12) : 3238-3249.

PDF(1003 KB)
PDF(1003 KB)
系统工程理论与实践 ›› 2014, Vol. 34 ›› Issue (12) : 3238-3249. DOI: 10.12011/1000-6788(2014)12-3238
论文

协同过滤推荐算法研究: 考虑在线评论情感倾向

    王伟, 王洪伟, 孟园
作者信息 +

The collaborative filtering recommendation based on sentiment analysis of online reviews

    WANG Wei, WANG Hong-wei, MENG Yuan
Author information +
文章历史 +

摘要

协同过滤推荐算法通常是基于兴趣相似的用户行为来实现个性化推荐, 其核心义用户之间的兴趣相似度. 本文在传统的协同过滤推荐算法基础上, 考虑在线评论对用似度识别的影响. 在混合商品推荐中, 粗粒度识别评论情感极性; 而在同类商品推荐中, 细粒别每个商品特征的情感极性. 如果用户对产品的某个特征评价次数大于平均次数, 表明用户对征较关注; 如果对产品的某个特征评价低于平均评价, 表明用户对该特征较挑剔. 进而根据用户评论来建立用户偏好模型, 用户在评论中反映出来的相似度越高, 表明用户之间的偏好越. 实验表明, 同传统的协同过滤算法相比, 基于在线评论情感分析的用户协同过滤算法在率和召回率指标上有显著提升.

Abstract

Collaborative filtering recommendation algorithm bases on user behavior with similar interests to produce personalized recommendation. The core of the algorithm is to define the distance between the user's interest similarities. The paper considers the online review sentiment impact on user similarity recognition. In mixed products recommendation, coarse-grained sentimental polarity is identified; while in same category products recommendation, fine-grained sentimental analysis is employed for each feature. If the user's evaluation frequency is greater than the average on a special feature, it indicates that the user pays close attention to the feature; while if the user's rating is smaller than the average rating on a special feature, it means the user has a strict requirement on this feature. And then the user's preference model is created according to reviews, the higher the similarity between users in the reviews, the more consistent preferences between users. Experiment results show that the proposed collaborative filtering algorithm based on sentiment analysis of online reviews improves the traditional algorithm significantly on accuracy and recall.

关键词

推荐系统 / 推荐算法 / 协同过滤 / 在线评论 / 情感分析

Key words

recommendation system / recommendation algorithm / collaborative filtering / online review / sentiment analysis

引用本文

导出引用
王伟 , 王洪伟 , 孟园. 协同过滤推荐算法研究: 考虑在线评论情感倾向. 系统工程理论与实践, 2014, 34(12): 3238-3249 https://doi.org/10.12011/1000-6788(2014)12-3238
WANG Wei , WANG Hong-wei , MENG Yuan. The collaborative filtering recommendation based on sentiment analysis of online reviews. Systems Engineering - Theory & Practice, 2014, 34(12): 3238-3249 https://doi.org/10.12011/1000-6788(2014)12-3238
中图分类号: TP18   

参考文献

[1] Rosenberg D. Early modern information overload[J]. Journal of the History of Ideas, 2003, 64(1): 1-9.
[2] Bruce R, Wiebe J. Recognizing subjectivity: A case study of manual tagging[J]. Natural Language Engineering, 1999, 5(2): 187-205.
[3] Wiebe J, Bruce R, Bell M, et al. A corpus study of evaluative and speculative language[C]// Proceedings of the Second SIGdial Workshop on Discourse and Dialogue-Volume 16. Association for Computational Linguistics, 2001: 1-10.
[4] Hu M, Liu B. Mining and summarizing customer reviews[C]// Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2004: 168-177.
[5] Turney P D. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[C]// Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2002: 417-424.
[6] Turney P D, Littman M L. Measuring praise and criticism: Inference of semantic orientation from association[J]. ACM Transactions on Information Systems (TOIS), 2003, 21(4): 315-346.
[7] Jindal N, Liu B. Identifying comparative sentences in text documents[C]// Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2006: 244-251.
[8] Liu J, Yao J, Wu G. Sentiment classification using information extraction technique[M]// Advances in Intelligent Data Analysis VI. Springer Berlin Heidelberg, 2005: 216-227.
[9] Popescu A M, Etzioni O. Extracting product features and opinions from reviews[M]// Natural Language Processing and Text Mining. Springer London, 2007: 9-28.
[10] Darena F, Burda K. Grouping of customer opinions written in natural language using unsupervised machine learning[C]// Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2012 14th International Symposium on. IEEE, 2012: 265-270.
[11] Chen C C, Chen Z Y, Wu C Y. An unsupervised approach for person name bipolarization using principal component analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2012, 24(11): 1963-1976.
[12] Paltoglou G, Thelwall M. Twitter, MySpace, Digg: Unsupervised sentiment analysis in social media[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2012, 3(4): 66.
[13] 黄诗琳, 郑小林, 陈德人. 针对产品命名实体识别的半监督学习方法[J]. 北京邮电大学学报, 2013, 36(002): 20-23.Huang Shilin, Zheng Xiaolin, Chen Deren. A semi-supervised learning method for product named entity recognition[J]. Journal of Beijing University of Posts and Telecommunications, 2013, 36(002): 20-23.
[14] Moraes R, Valiati J F, Gaviao Neto W P. Document-level sentiment classification an empirical comparison between SVM and ANN[J]. Expert Systems with Applications, 2013, 40(2): 621-633.
[15] Sayeedunnissa S F, Hussain A R, Hameed M A. Supervised opinion mining of social network data using a bag-of-words approach on the cloud[C]// Proceedings of Seventh International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA 2012). Springer India, 2013: 299-309.
[16] Kanayama H, Nasukawa T. Unsupervised lexicon induction for clause-level detection of evaluations[J]. Natural Language Engineering, 2012, 18: 83-107.
[17] Xianghua F, Guo L, Yanyan G, et al. Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon[J]. Knowledge-Based Systems, 2013, 37: 186-195.
[18] Kawamae N. Predicting future reviews: Sentiment analysis models for collaborative filtering[C]// Proceedings of the Fourth ACM International Conference on Web Search and Data Mining. ACM, 2011: 605-614.
[19] Leung C W K, Chan S C F, Chung F L, et al. A probabilistic rating inference framework for mining user preferences from reviews[J]. World Wide Web, 2011, 14(2): 187-215.
[20] Danesh S, Liu W, French T, et al. An investigation of recursive auto-associative memory in sentiment detection[M]// Advanced Data Mining and Applications. Springer Berlin Heidelberg, 2011: 162-174.
[21] 秦宇强, 张雪英. 连续汉语普通话中基于 SVM 的说话人情感互相关性算法[J]. 系统工程理论与实践, 2011, 31(增刊2): 154-159.Qin Yuqiang, Zhang Xueying. SVM-based speaker emotional cross-correlation algorithm in continuous Chinese mandarin[J]. Systems Engineering - Theory & Practice, 2011, 31(S2): 154-159.
[22] Yin P, Wang H W, Guo K Q. Feature-opinion pair identification of product reviews in Chinese: A domain ontology modeling method[J]. New Review of Hypermedia and Multimedia, 2013, 19(1): 3-24.
[23] Alam M H, Lee S K. Semantic aspect discovery for online reviews[C]// Proceedings of the 2012 IEEE 12th International Conference on Data Mining. IEEE Computer Society, 2012: 816-821.
[24] Yu Z Z, Zheng N, Xu M. An automatic product features extracting method in Chinese customer reviews[C]// 7th International Conference on System of Systems Engineering (SoSE), 2012: 455-459.
[25] Kasper W, Vela M. Sentiment analysis for hotel reviews[C]//Computational Linguistics-Applications Conference. 2011: 45-52.
[26] Somprasertsri G, Lalitrojwong P. A maximum entropy model for product feature extraction in online customer reviews[C]// 2008 IEEE Conference on Cybernetics and Intelligent Systems, IEEE, 2008: 575-580.
[27] Hu M, Liu B. Mining opinion features in customer reviews[C]// AAAI, 2004, 4(4): 755-760.
[28] Liu Q, Li S. Word similarity computing based on how-net[J]. Computational Linguistics and Chinese Language Processing, 2002, 7(2): 59-76.
[29] Billsus D, Pazzani M J. Learning collaborative information filters[C]//ICML. 1998, 98: 46-54.
[30] Lin C, Tsai C. Applying social bookmarking to collective information searching (CIS): An analysis of behavioral pattern and peer interaction for co-exploring quality online resources[J]. Computers in Human Behavior, 2011, 27(3): 1249-1257.
[31] Dalcanale F, Fontane D, Csapo J. A general framework for a collaborative water quality knowledge and information network[J]. Environmental Management, 2011, 47(3): 443-455.
[32] Liu H, He J, Wang T, et al. Combining user preferences and user opinions for accurate recommendation[J]. Electronic Commerce Research and Applications, 2013, 12(1): 14-23.
[33] Xu J, Zheng X, Ding W. Personalized recommendation based on reviews and ratings alleviating the sparsity problem of collaborative filtering[C]// 2012 IEEE Ninth International Conference on E-Business Engineering (ICEBE), IEEE, 2012: 9-16.
[34] 邓晓懿, 金淳, 韩庆平, 等. 基于情境聚类和用户评级的协同过滤推荐模型[J]. 系统工程理论实践, 2013, 33(11): 2945-2953.Deng Xiaoyi, Jin Chun, Han Qingping, et al. Improved collaborative filtering model based on context clustering and user ranking[J]. Systems Engineering - Theory & Practice, 2013, 33(11): 2945-2953.
[35] 郁雪, 李敏强. 基于 PCA-SOM 的混合协同过滤模型[J]. 系统工程理论与实践, 2010, 30(10): 1850-1854.Yu Xue, Li Minqiang. Effective hybrid collaborative filtering model based on PCA-SOM[J]. Systems Engineering - Theory & Practice, 2010, 30(10): 1850-1854.
[36] Hu N, Tian G, Liu L, et al. Do links matter? An investigation of the impact of consumer feedback, recommendation networks, and price bundling on sales[J]. IEEE Transactions on Engineering Management, 2012, 59(2): 189-200.
[37] Tyagi S, Bharadwaj K K. Enhanced new user recommendations based on quantitative association rule mining[J]. Procedia Computer Science, 2012, 10: 102-109.
[38] 李聪, 梁昌勇. 基于n序访问解析逻辑的协同过滤冷启动消除方法[J]. 系统工程理论与实践, 2012, 32(7): 1537-1545.Li Cong, Liang Changyong. Cold-start eliminating method of collaborative filtering based on n-sequence access analytic logic[J]. Systems Engineering - Theory & Practice, 2012, 32(7): 1537-1545.
[39] 钟佳丰. 基于在线评论的产品模糊推荐系统研究[D]. 大连: 大连理工大学, 2012. Zong Jiafeng. Research on product fuzzy recommendation system based on online review[D]. Dalian: Dalian University of Technology, 2012.
[40] 胡新明. 基于商品属性的电子商务推荐系统研究[D]. 武汉: 华中科技大学, 2012. Hu Xinming. Research on recommender system based on product attributes[D]. Wuhan: Huazhong University of Science and Technology, 2012.
[41] Gan M, Jiang R. Constructing a user similarity network to remove adverse influence of popular objects for personalized recommendation[J]. Expert Systems with Applications, 2013, 40(10): 4044-4053.
[42] Pham H X, Jung J J. Preference-based user rating correction process for interactive recommendation systems[J]. Multimedia Tools and Applications, 2013, 65(1): 119-132.
[43] 金淳, 张一平. 基于 Agent 的顾客行为及个性化推荐仿真模型[J]. 系统工程理论与实践, 2013, 33(2): 463-472.Jin Chun, Zhang Yiping. Agent-based simulation model of customer behavior and personalized recommendation[J]. Systems Engineering - Theory & Practice, 2013, 33(2): 463-472.
[44] Song H, Fan Y, Liu X, et al. Extracting product features from online reviews for sentimental analysis[C]// 2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT), IEEE, 2011: 745-750.
[45] Xunsearch. SCWS 中文分词[EB/OL]. [2014-01-19]. http://www.xunsearch.com/scws/
[46] 北京大学.中文汉语标注集[EB/OL]. [2014-01-19]. http://icl.pku.edu.cn/icl_groups/corpus/addition.htm.
[47] Nakagawa H, Mori T. A simple but powerful automatic term extraction method[C]// COLING-02 on COMPUTERM 2002: Second International Workshop on Computational Terminology-Volume 14. Association for Computational Linguistics, 2002: 1-7.
[48] Somprasertsri G, Lalitrojwong P. Mining feature-opinion in online customer reviews for opinion summarization[J]. Journal of Universal Computer Science, 2010, 16(6): 938-955.
[49] Merton R K. The Matthew effect in science[J]. Science, 1968, 159(3810): 56-63.
[50] Cho J, Roy S. Impact of search engines on page popularity[C]//Proceedings of the 13th International Conference on World Wide Web. ACM, 2004: 20-29.
[51] Fleder D M, Hosanagar K. Recommender systems and their impact on sales diversity[C]//Proceedings of the 8th ACM Conference on Electronic Commerce. ACM, 2007: 192-199.
[52] Goel S, Broder A, Gabrilovich E, et al. Anatomy of the long tail: Ordinary people with extraordinary tastes[C]// Proceedings of the Third ACM International Conference on Web Search and Data Mining. ACM, 2010: 201-210.
[53] Anderson C. The long tail[M]. Random House Business, 2006.
[54] Linden G. Early amazon: Similarities[EB/OL]. [2014-01-19]. http://glinden.blogspot.com/2006/03/early-amazon-similarities.html.
[55] 项亮.推荐系统实践[M].北京: 人民邮电出版社, 2012: 23-29, 45-49. Xiang Liang. Recommendation system in action[M].Beijing: The People's Posts and Telecommunications Press (Posts & Telecom Press), 2012: 23-29, 45-49.
[56] 刘青文. 基于协同过滤的推荐算法研究[D]. 合肥: 中国科学技术大学, 2013. Liu Qingwen. Research on recommender systems based on collaborative filtering[D]. Hefei: University of Science and Technology of China, 2013.

基金

国家自然科学基金(70971099,71371144);上海市哲学社会科学规划课题一般项目(2013BGL004);中央高校基本科研业务费专项资金(1200219198)
PDF(1003 KB)

Accesses

Citation

Detail

段落导航
相关文章

/