计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 75-79.doi: 10.11896/j.issn.1002-137X.2019.06.010

• 大数据与数据科学* • 上一篇    下一篇

基于网络评论情感信任分析的推荐策略

卢竹兵1, 李玉州2   

  1. (西南大学经济管理学院 重庆400715)1
    (西南大学计算机与信息科学学院 重庆400715)2
  • 收稿日期:2018-11-10 发布日期:2019-06-24
  • 通讯作者: 卢竹兵(1981-),男,硕士,主要研究方向为Web智能与应用,E-mail:36921434@qq.com
  • 作者简介:李玉州(1981-),男,硕士,主要研究方向为知识工程与数据挖掘。基于网络评论情感信任分析的推荐策略
  • 基金资助:
    中央高校基本科研业务费项目基金(XDJK2017C087)资助。

Recommendation Strategy Based on Trust Model via Emotional Analysis of Online Comment

LU Zhu-bing1, LI Yu-zhou2   

  1. (College of Economics and Management,Southwest University,Chongqing 400715,China)1
    (College of Computer and Information Science,Southwest University,Chongqing 400715,China)2
  • Received:2018-11-10 Published:2019-06-24

摘要: 个性化推荐技术已经成为电子商务领域解决信息过载问题的一种有效手段。传统的协同过滤推荐系统由于算法自身的特点,普遍存在数据稀疏性和冷启动等问题,这些问题的存在使得个性化推荐过程中的准确率大大降低,影响了用户的个性化体验和对系统的信心。从社会学中的信任关系角度着手,通过对网络用户在线评论信息进行情感分析,提取出评论信息中用户的情感倾向,并对它进行有效量化,然后通过计算用户情感倾向的相似性建立用户间的信任关系。同时,在推荐过程中将所构建的信任关系与评分数据的相似度进行有效结合,弥补了相似度作为唯一权重因素而导致的推荐准确率降低的不足。首先,基于在线评论信息对用户的情感倾向性进行分析与量化;然后,基于情感相似度对用户信任关系进行建模;最后,基于用户情感信任关系对推荐策略进行设计。在所选数据集上的模拟对比实验表明,改进的引入情感分析信任模型的个性化推荐策略能够有效地降低平均绝对误差值MAE,推荐的准确率得到了提高;同时,覆盖率coverage和推荐系统对商品长尾的发掘能力也得到了有效的提升;另外,信任关系自主管理机制的引入,也大大改善了用户对系统的个性化体验,增强了用户对系统的信心。

关键词: 协同过滤, 数据稀疏, 信任关系, 情感分析, 相似度

Abstract: Personalized recommendation technology has become a very effective approach to cope with “information overload” in E-commerce.Aiming at the problems of data sparseness and cold-start in traditional collaborative filtering recommender system,which have led to the decline of the accuracy in recommendation,weakened user’s confidence towards the system,this paper proposed a new recommendation strategy using trust theory in sociology to offer users better personalized service. From this perspective,user’s online comments to the items that they have experienced are analyzed,the user’s emotional tendency is extracted,and it is effectively quantified.The trust relationship between users is grown by analyzing the similarity of user’s emotional tendency.At the same time,users’ rating data are combined to compensate for the lack of recommendation factor caused by similarity as the only preference weight.The work in this paper includes three parts:analysis and quantification of user emotional tendency based on online reviews,mo-deling of trust relationship based on similarity between emotion and design of recommendation strategy based on trust relationship.Experiments show that the proposed recommendation strategy can effectively reduce the average absolute error value called MAE,which means the recommendation accuracy is improved.At the same time,the coverage rate is also effective increased,which means that the system has more items to recommend.Additionally,the management mechanism of trust relationship can also greatly enhance user’s personalized experience of the system and user’s confidence to the system.

Key words: Collaborative filtering, Data sparsity, Trust relationship, Emotion analysis, Similarity

中图分类号: 

  • TP391
[1]HERLOCKER J L,KONSTAN J A,TERVEEN L G.Evaluating collaborative filtering recommender systems[J].ACM Transactions on Information System,2004,22(1):5-53.
[2]CAO D,HE X N,MIAO L H,et al.Attentive Group Recommendation[C]∥Proceedings of SIGIR’18Ann Arbor.MI,USA,ACM,2018:645-654.
[3]CHEN J,ZHANG H,HE X,et al.Attentive collaborative filtering:Multimedia recommendation with item- and component le-vel attention[C]∥Proceedings of SIGIR’17.MI,USA,ACM,2017:335-344.
[4]HE X,LIAO L,ZHANG H,et al.Neuralcollaborative filtering[C]∥Proceedings of 26th International Conference of World Wide Web.USA,IEEE Press,2017:173-182.
[5]GE M,DELGADO-BATTENFEL D,JANNACH D.Beyond accuracy Evaluating recommender systems by coverage and serendipity[C]∥RecSys the 2010 ACM Conference on Recommender Systems.Barcelona,ACM,2010:257-260.
[6]XING C X,GAO F R,ZHAN S N,et al.A Collaborative Filtering Recommendation Algorithm Incorporated with User Inte-rest Change[J].Journal of Computer Research and Development,2007,44(2):296-301.(in Chinese)
邢春晓,高凤荣,战思南,等,适应用户兴趣变化的协同过滤推荐算法[J].计算机研究与发展,2007,44(2):296-301.
[7]DU Y P,HUANG L,HE M.Collaborative Filteration Recom-mendation Algorithm Based on Trust Computation[J].Pattern Recognition & Artificial Intelligence,2014,27(5):417-425.(in Chinese)
杜永萍,黄亮,何明.融合信任计算的协同过滤推荐方法[J]模式识别与人工智能,2014,27(5):417-425.
[8]LIN J H,YAN X H,HUANG B.Collaborative Filtering Recommendation Algorithm Based on Trust Users[J].Computer Systems&Applications,2017,26(6):124-130.(in Chinese)
林建辉,严宣辉,黄波.融合信任用户的协同过滤推荐算法[J].计算机系统应用,2017,26(6):124-130.
[9]LU Z B,TANG Y.A Trust Network-based Collaborative Filtering Recommendation Strategy[J].Journal of Southwest China Normal University(Natural Science Edition),2008,33(2):123-126.(in Chinese)
卢竹兵,唐雁.一种基于信任网络的协同过滤推荐策略[J].西南师范大学学报(自然科学版),2008,33(2):123-126.
[10]ZHANG Y,LIAN D F,YANG G W.Discrete personalized ran-king for fast collaborativefiltering from implicit feedback[C]∥Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence.USA,AAAI Press,2017:1669-1675.
[11]CHENG Z Y,DING Y,HE X N,et al.A3NCF:An Adaptive Aspect Attention Model for Rating Prediction[C]∥Proceedings of the 27th International Joint Conference on Artificial Intelligence(IJCAI’18).Sweden,2018:3748-3754.
[12]GAO Y F.Design and Implementation of Recommendation Algorithm Based on Review Analysis[D].Shanghai:East China Normal University,2016.(in Chinese)
高祎璠.基于评论分析的推荐算法的设计与实现[D].上海:华东师范大学,2016.
[13]ZHOU G Q,LIU X,YANG X H.User Collaborative Recommendation Model Based on Emotional Weight[J].Journal of Chinese Computer Systems,2016,37(5):938-942.(in Chinese)
周国强,刘旭,杨锡慧.基于情感权重的用户协同推荐模型[J].小型微型计算机系统,2016,37(5):938-942.
[14]YOU H.A Sociological Research on the Relationship between Emotion and Trust[D].Wuhan:Wuhan University,2009.(in Chinese)
游泓.情感与信任关系的社会学研究[D].武汉:武汉大学,2009.
[15]MC K,NIGHT D H,CHERVANY N L.The Meaning of Trust[C]∥Technical Report MISRC Working Paper Series 96 04 University of Minnesota.Management Information System Research Center,1996.
[16]GABBETTA D.Can we Trust?[C]∥Trust: Making and Breaking Cooperative Relations.BasilBlackwell,Oxford,1990:213-238.
[17]WANG Y,VASSILEVA J.Trust and reputation model in peer-to-peer networks.[C]∥Proceedings of the 3rd International Conference on Peer-to-Peer Computing.IEEE Press,2003:150-157.
[18]CHANG T M,HSIAO W F.LDA-based personalized document recommendation[C]∥Proceeding of the PACIS’13.Jeju Island,Korea:Journal of the Association for Information System,2013.
[19]LIU B,HU M Q,CHENG J S.Opinion observer:analyzingand comparing opinions on the Web[C]∥Proceedings of the 14th International Conference on World Wide Web.Japan,ACM Press,2005:342-351.
[20]PENG M,XI J J,DAI X Y,et al.Collaborative Filtering Recommendation Based on Sentiment Analysis and LDA Topic Model[J].Journal of Chinese Information Processing,2017,31(2):194-203.(in Chinese)
彭敏,席俊杰,代心媛,等.基于情感分析和LDA主题模型的协同过滤推荐算法[J].中文信息学报,2017,31(2):194-203.
[21]LIU H,YANG H,LI W,et al.CRO:A System for Online Review Structurization[C]∥Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.NewYork,ACM Press.2008:1085-1088.
[22]BLAZE M,KANNAN S,LEE I,et al.Dynamic Trust Management[J].Computer,2009,42(2):44-52.
[23]MCAULEY J,LESKOVEC J.Hidden factors and hidden topics:understandingrating dimensions with review text[C]∥Procee-dings of the 7th ACM Conference on Recommender System.ACM Press,2013:165-172.
[24]YANG W,SONG J J,TANG J Q.A Study on the Classification Approach for Chinese MicroBlog Subjective and Objective Sentences.Journal of Chongqing University of Technology(Natural Science),2013,27(1):51-56. (in Chinese)
杨武,宋静静,唐继强.中文微博情感分析中主客观句分类方法.重庆理工大学学报(自然科学版),2013,27(1):51-56.
[1] 王涵, 夏鸿斌. LDA模型和列表排序混合的协同过滤推荐算法[J]. 计算机科学, 2019, 46(9): 216-222.
[2] 孙中锋, 王静. 用于基于方面情感分析的RCNN-BGRU-HN网络模型[J]. 计算机科学, 2019, 46(9): 223-228.
[3] 邓存彬, 虞慧群, 范贵生. 融合动态协同过滤和深度学习的推荐算法[J]. 计算机科学, 2019, 46(8): 28-34.
[4] 张艳红, 张春光, 周湘贞, 王怡鸥. 项目多属性模糊联合的多样性视频推荐算法[J]. 计算机科学, 2019, 46(8): 78-83.
[5] 康林瑶, 唐兵, 夏艳敏, 张黎. 基于GPU加速和非负矩阵分解的并行协同过滤推荐算法[J]. 计算机科学, 2019, 46(8): 106-110.
[6] 刘强,况晓辉,陈华,李响,李广轲. 一种基于程序切片相似度匹配的脆弱性发现方法[J]. 计算机科学, 2019, 46(7): 126-132.
[7] 张璐, 沈忱林, 李寿山. 基于情绪特定词向量的情绪分类算法[J]. 计算机科学, 2019, 46(6A): 93-97.
[8] 王旭, 庞巍, 王喆. 异构信息网络中基于元结构的协同过滤算法[J]. 计算机科学, 2019, 46(6A): 397-401.
[9] 刘晴晴, 罗永龙, 汪逸飞, 郑孝遥, 陈文. 基于SVD填充的混合推荐算法[J]. 计算机科学, 2019, 46(6A): 468-472.
[10] 徐聪, 潘小东. 基于正态云相似度的语言型多属性群决策方法[J]. 计算机科学, 2019, 46(6): 218-223.
[11] 唐家琪, 吴璟莉, 廖元秀, 王金艳. 基于双加权投票的蛋白质功能预测[J]. 计算机科学, 2019, 46(4): 222-227.
[12] 苏畅, 武鹏飞, 谢显中, 李宁. 基于用户兴趣和地理因素的兴趣点推荐方法[J]. 计算机科学, 2019, 46(4): 228-234.
[13] 吴祎凡, 崔艳鹏, 胡建伟. 基于层次聚类的警报处理方法[J]. 计算机科学, 2019, 46(4): 203-209.
[14] 李长镜,赵书良,池云仙. 一种基于谱嵌入和局部密度的离群点检测算法[J]. 计算机科学, 2019, 46(3): 260-266.
[15] 王永, 王永东, 邓江洲, 张璞. 融合Jensen-Shannon散度的推荐算法[J]. 计算机科学, 2019, 46(2): 210-214.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[2] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[3] 钟菲,杨斌. 基于主成分分析网络的车牌检测方法[J]. 计算机科学, 2018, 45(3): 268 -273 .
[4] 吴姝,周安民,左政. PDiOS:iOS应用程序中私有API的调用检测[J]. 计算机科学, 2018, 45(4): 163 -168 .
[5] 郭俊霞,郭仁飞,许南山,赵瑞莲. 基于Session的Web应用软件EFSM模型构建方法研究[J]. 计算机科学, 2018, 45(4): 203 -207, 214 .
[6] 童泽平,李涛,李立杰,任亮. 基于随机需求与产能限制的供应链协同优化研究[J]. 计算机科学, 2018, 45(4): 260 -265 .
[7] 徐周波,张鵾,宁黎华,古天龙. 图编辑距离概述[J]. 计算机科学, 2018, 45(4): 11 -18 .
[8] 司念文,王衡军,李伟,单义栋,谢鹏程. 基于注意力长短时记忆网络的中文词性标注模型[J]. 计算机科学, 2018, 45(4): 66 -70, 82 .
[9] 胡庆成, 张勇, 邢春晓. 基于有重叠社区划分的社会网络影响最大化方法研究[J]. 计算机科学, 2018, 45(6): 32 -35 .
[10] 崔一辉, 宋伟, 彭智勇, 杨先娣. 基于差分隐私的多源数据关联规则挖掘方法[J]. 计算机科学, 2018, 45(6): 36 -40,56 .