Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (8): 9-17     https://doi.org/10.11925/infotech.2096-3467.2017.08.02
  首届"数据分析与知识发现"学术研讨会专辑(II) 本期目录 | 过刊浏览 | 高级检索 |
基于用户偏好与商品属性情感匹配的图书个性化推荐研究*
侯银秀, 李伟卿, 王伟军(), 张婷婷
华中师范大学信息管理学院 武汉 430079
华中师范大学青少年网络心理与行为教育部重点实验室 武汉 430079
Personalized Book Recommendation Based on User Preferences and Commodity Features
Hou Yinxiu, Li Weiqing, Wang Weijun(), Zhang Tingting
School of Information Management, Central China Normal University, Wuhan 430079, China
Key Laboratory of Adolescent Cyber Psychology and Behavior, Ministry of Education, Central China Normal University, Wuhan 430079, China
全文: PDF (609 KB)   HTML ( 2
输出: BibTeX | EndNote (RIS)      
摘要 

目的】识别并获取细粒度的用户偏好信息, 优化图书个性化推荐的效果。【方法】使用情感分析方法对用户图书评论进行属性层文本挖掘, 通过用户本身的图书评论获取用户对图书属性的偏好; 基于每本图书的所有评论的情感计算获得其属性评分; 将用户偏好矩阵、图书属性得分矩阵进行匹配, 从而实现用户对图书属性情感偏好的个性化推荐。【结果】利用亚马逊图书评论数据作为数据来源分别对传统的协同过滤方法与本文提出的推荐方法进行实验对比。结果表明, 本文提出的方法在准确性、召回率、覆盖率上分别提高了0.030、0.097、0.2812。【局限】未考虑时间因素对用户偏好的影响, 并且属性类型的全面程度受亚马逊图书评论数量和质量的限制。【结论】本文计算用户对图书属性的情感得分, 得到细粒度的用户偏好信息, 并通过与图书属性的得分进行匹配, 提升了图书个性化推荐的效果。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
侯银秀
李伟卿
王伟军
张婷婷
关键词 图书个性化推荐情感匹配商品属性用户偏好    
Abstract

[Objective] This paper identifies the fine-grained preferences of online bookstore users, aiming to optimize the personalized book recommendation service. [Methods] First, we conducted sentiment analysis of the book features through readers’ comments, which indicated their preferences. Then, we calculated the books’ sentiment scores based on the readers’ comments. Finally, the user preferences matrix and the sentiment scores matrix were matched to personalize the book recommendation. [Results] We retrieved the needed data from Amazon’s book comments, and then conducted an experiment to compare the results of our new method with those of the traditional collaborative filtering methods. We found that the proposed method improved the precision, recall and coverage by 0.030, 0.097, 0.2812. [Limitations] We did not consider the impacts of time on user’s preferences, and the feature types might not be comprehensive due to the limited number and quality of Amazon’s book comments. [Conclusions] The proposed method improves the performance of personalized book recommendation service.

Key wordsPersonalized Book Recommendation    Sentiment Matching    Commodity Feature    User Preference
收稿日期: 2017-05-22      出版日期: 2017-09-28
ZTFLH:  G35  
基金资助:*本文系国家自然科学基金项目“基于用户偏好感知的SaaS服务选择优化研究”(项目编号: 71271099)和国家自然科学基金项目“基于屏幕视觉热区的网络用户偏好提取及交互式个性化推荐研究”(项目编号: 71571084)的研究成果之一
引用本文:   
侯银秀, 李伟卿, 王伟军, 张婷婷. 基于用户偏好与商品属性情感匹配的图书个性化推荐研究*[J]. 数据分析与知识发现, 2017, 1(8): 9-17.
Hou Yinxiu,Li Weiqing,Wang Weijun,Zhang Tingting. Personalized Book Recommendation Based on User Preferences and Commodity Features. Data Analysis and Knowledge Discovery, 2017, 1(8): 9-17.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.08.02      或      http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I8/9
编号 类型 图书属性词
1 内容和主题思想(mind) mind, content, thesis, topic, thought, story, setting, plot, detail, spirit, soul, idea, belief, concept, ideal, sensation, heart, thinking, thinker, theory, event, deeds, reflections, feel, feeling, view, emotion, essence, mood, humanity, characters, memories, opinion
2 结构和形式(structure) structure, framework, layout, chapter, length, clue, thread, passages, circus
3 实用性(practice) practice, purpose, use, useful, information, device, advice, technique, effective, creative, meaningful, impact, progress, discoveries
4 趣味性(interest) hobby, interest, interested, interesting, moved, exciting, excite, excited, delight, delightful, surprised, delighted, pleasure, joy, joyous, joys, enjoy, enjoyable, taste, enthusiast, pleasure
5 难度和专业性(difficulty) depth, difficult, difficulty, classic, readability, specialty, profession, major
6 价格(cost) price, cost, value
7 质量(quality) quality, hardcover, paperback, package, paper, cover, print, printed
  图书属性词表
词语 等级 极性
Very Negative 0 -1
Negative 1 -1
Neutral 2 0
Positive 3 1
Very Positive 4 1
  情感词汇等级分类
  情感匹配图书个性化推荐流程
  用户偏好矩阵
用户 t1 (内容) t2 (结构) t3 (实用性) t4 (趣味性) t5 (专业性) t6 (价格) t7 (质量)
u1 1.56 0.00 0.83 2.63 1.18 0.00 1.00
u2 -1.00 0.53 0.76 0.00 1.42 1.56 -1.83
u3 1.00 1.89 -2.00 0.00 0.00 1.56 0.34
u4 0.00 2.00 -1.82 0.34 1.88 1.57 -2.00
u5 0.80 -2.00 1.55 0.59 0.35 2.00 -2.00
  用户偏好表示(部分用户偏好)
  图书属性得分矩阵
图书 t1 (内容) t2 (结构) t3 (实用性) t4 (趣味性) t5 (专业性) t6 (价格) t7 (质量)
p1 -0.56 0 -0.29 1 -1 0 1
p2 0.14 0 -0.57 0.44 0.33 1 0
p3 -0.34 0 -0.67 0 0 1 -0.4
p4 -0.21 -0.08 -0.68 -2 -1 0 -0.67
p5 0.2 0 -0.33 0 0.5 0 0
p6 0 0 -0.17 0 0 0 -0.67
p7 -0.49 0 0.95 0 -1 1 0
p8 -0.4 0 -1.33 1 -1 0 -1
p9 -0.13 0 -0.71 0.07 1 0 0
  图书属性情感分析(部分图书得分)
推荐算法 正确推荐数量 推荐数量 准确率 召回率 覆盖率
Item-base 244 1 630 0.1497 0.1124 0.3418
User-base 249 1 630 0.1528 0.1285 0.3051
本文方法 298 1 630 0.1828 0.1382 0.5863
  Item-base、User-base与基于用户偏好与商品属性的情感分析推荐算法结果对比
[1] 刘建国, 周涛, 汪秉宏. 个性化推荐系统的研究进展[J]. 自然科学进展, 2009, 19(1): 1-15.
doi: 10.3321/j.issn:1002-008X.2009.01.001
[1] (Liu Jianguo, Zhou Tao, Wang Binghong.Research Progress of Personalized Recommendation System[J]. Progress in Natural Science, 2009, 19(1): 1-15.)
doi: 10.3321/j.issn:1002-008X.2009.01.001
[2] Xu Y, Yin J.Collaborative Recommendation with User Generated Content[J]. Engineering Applications of Artificial Intelligence, 2015, 45: 281-294.
doi: 10.1016/j.engappai.2015.07.012
[3] Hu N, Koh N S, Reddy S K.Ratings Lead You to the Product, Reviews Help You Clinch It? The Mediating Role of Online Review Sentiments on Product Sales[J]. Decision Support Systems, 2014, 57(1): 42-53.
doi: 10.1016/j.dss.2013.07.009
[4] Sohail S S, Siddiqui J, Ali R.Book Recommendation System Using Opinion Mining Technique[C]////Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics. IEEE, 2013: 1609-1614.
[5] Diao Q, Qiu M, Wu C Y, et al.Jointly Modeling Aspects, Ratings and Sentiments for Movie Recommendation (JMARS)[C]////Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2014: 193-202.
[6] Liu Q, Liu K, Wang Y, et al.User-Oriented Real-Time Preference Obtaining Screen Visual Hotspots Recognition Based on the Research of Eye Movement Experiments[C]//// Proceedings of the 1st International Conference on Information Acquisition and Knowledge Services.2014, 39: 181-185.
[7] 刘凯. 基于屏幕视觉热区的用户偏好提取及个性化推荐[M]. 北京: 科学出版社, 2016.
[7] (Liu Kai.User Preference Extraction and Personalized Recommendation Based on Screen Visual Hotspot[M]. Beijing: Science Press, 2016.)
[8] 李树青, 徐侠, 许敏佳. 基于读者借阅二分网络的图书可推荐质量测度方法及个性化图书推荐服务[J]. 中国图书馆学报, 2013, 39(3): 83-95.
doi: 10.3969/j.issn.1001-8867.2013.03.021
[8] (Li Shuqing, Xu Xia, Xu Minjia.The Measures of Books’ Recommending Quality and Personalized Book Recommendation Service Based on Bipartite Network of Readers and Books’ Lending Relationship[J]. Journal of Library Science in China, 2013, 39(3): 83-95.)
doi: 10.3969/j.issn.1001-8867.2013.03.021
[9] 林耀进, 胡学钢, 李慧宗. 基于用户群体影响的协同过滤推荐算法[J]. 情报学报, 2013, 32(3): 299-305.
doi: 10.3772/j.issn.1000-0135.2013.03.009
[9] (Lin Yaojin, Hu Xuegang, Li Huizong.Collaborative Filtering Recommendation Algorithm Based on User Group Influence[J]. Journal of the China Society for Scientific and Technical Information, 2013, 32(3): 299-305.)
doi: 10.3772/j.issn.1000-0135.2013.03.009
[10] Liao C L, Lee S J.A Clustering Based Approach to Improving the Efficiency of Collaborative Filtering Recommendation[J]. Electronic Commerce Research & Applications, 2016, 18: 1-9.
doi: 10.1016/j.elerap.2016.05.001
[11] Najafabadi M K, Mahrin M N, Chuprat S, et al.Improving the Accuracy of Collaborative Filtering Recommendations Using Clustering and Association Rules Mining on Implicit Data[J]. Computers in Human Behavior, 2017, 67: 113-128.
doi: 10.1016/j.chb.2016.11.010
[12] 王伟军, 宋梅青. 一种面向用户偏好定向挖掘的协同过滤个性化推荐算法[J]. 现代图书情报技术, 2014(6): 25-32.
[12] (Wang Weijun, Song Meiqing.A Collaborative Filtering Personalized Recommendation Algorithm Through Directionally Mining User’ Preferences[J]. New Technology of Library and Information Service, 2014(6): 25-32.)
[13] Qiu L, Gao S, Cheng W, et al.Aspect-based Latent Factor Model by Integrating Ratings and Reviews for Recommender System[J]. Knowledge-Based Systems, 2016, 110: 233-243.
doi: 10.1016/j.knosys.2016.07.033
[14] Li Y M, Wu C T, Lai C Y.A Social Recommender Mechanism for E-commerce: Combining Similarity, Trust, and Relationship[J]. Decision Support Systems, 2013, 55(3): 740-752.
doi: 10.1016/j.dss.2013.02.009
[15] 刘凯, 王伟军, 黄英辉, 等. 个性化推荐系统理论探索: 从系统向用户为中心的演进[J]. 情报理论与实践, 2016, 39(3): 52-56.
doi: 10.16353/j.cnki.1000-7490.2016.03.011
[15] (Liu Kai, Wang Weijun, Huang Yinghui, et al.Exploration on Personalized Recommendation System Theory: Evolution from System-centric to User-centric[J]. Information Studies: Theory & Application, 2016, 39(3): 52-56.)
doi: 10.16353/j.cnki.1000-7490.2016.03.011
[16] 丁雪. 认知视角下网络用户偏好复合模型的构建与验证[D]. 武汉: 华中师范大学, 2016.
[16] (Ding Xue.A Composite User Preference Model: An Experimental Model from a Cognitive Perspective[D]. Wuhan: Central China Normal University, 2016.)
[17] Mcauley J, Leskovec J.Hidden Factors and Hidden Topics: Understanding Rating Dimensions with Review Text[C]//// Proceedings of the 7th ACM Conference on Recommender Systems. 2013: 165-172.
[18] 李实, 叶强, 李一军, 等. 中文网络客户评论的产品特征挖掘方法研究[J]. 管理科学学报, 2009, 12(2): 142-152.
doi: 10.3321/j.issn:1007-9807.2009.02.015
[18] (Li Shi, Ye Qiang, Li Yijun, et al.Mining Features of Products from Chinese Customer Online Reviews[J]. Journal of Management Sciences in China, 2009, 12(2): 142-151.)
doi: 10.3321/j.issn:1007-9807.2009.02.015
[19] He T, Hao R, Qi H, et al.Mining Feature-Opinion from Reviews Based on Dependency Parsing[J]. International Journal of Software Engineering & Knowledge Engineering, 2016, 26(10): 1581-1591.
doi: 10.1142/S0218194016710029
[20] Lopez-Arevalo I, Sosa-Sosa V J, Rojas-Lopez F, et al. Improving Selection of Synsets from WordNet for Domain-specific Word Sense Disambiguation[J]. Computer Speech & Language, 2017, 41(10): 128-145.
doi: 10.1016/j.csl.2016.06.003
[21] Hung C, Chen S J.Word Sense Disambiguation Based Sentiment Lexicons for Sentiment Classification[J]. Knowledge-Based Systems, 2016, 110(5): 224-232.
doi: 10.1016/j.knosys.2016.07.030
[22] 汤颖, 钟南江, 范菁. 一种结合用户评分信息的改进好友推荐算法[J]. 计算机科学, 2016, 43(9): 111-115.
[22] (Tang Ying, Zhong Nanjiang, Fan Jing.An Improved Friend Recommendation Algorithm Combined with User Rating Information[J]. Computer Science, 2016, 43(9): 111-115.)
[23] 项亮. 推荐系统实践[M]. 北京: 人民邮电出版社, 2012.
[23] (Xiang Liang.Recommendation System Practice [M]. Beijing: Posts & Telecom Press, 2012.)
[1] 涂海丽,唐晓波. 基于标签的商品推荐模型研究*[J]. 数据分析与知识发现, 2017, 1(9): 28-39.
[2] 王伟军, 宋梅青. 一种面向用户偏好定向挖掘的协同过滤个性化推荐算法[J]. 现代图书情报技术, 2014, 30(6): 25-32.
[3] 朱恒民, 贾丹华, 黄震奇, 王春晖. 互联网用户偏好本体实例的学习方法研究[J]. 现代图书情报技术, 2013, 29(7/8): 43-48.
[4] 汪英姿. 基于本体的个性化图书推荐方法研究[J]. 现代图书情报技术, 2012, (12): 72-78.
[5] 张云中, 杨萌, 徐宝祥. 基于FCA的Folksonomy用户偏好挖掘研究[J]. 现代图书情报技术, 2011, 27(6): 72-78.
[6] 赵妍, 苏玉召, 管涛. 一种提高过滤用户偏好精度的数据采集方法[J]. 现代图书情报技术, 2011, (11): 31-37.
[7] 王翠英. 基于Folksonomies的用户偏好挖掘研究[J]. 现代图书情报技术, 2009, 25(6): 37-43.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn