[目的/意义]通过对移动图书馆用户生成内容的情感分析，预测用户情感倾向对移动图书馆资源的评价效果，从而更好地实现移动图书馆资源推广和精准推荐服务。[方法/过程]基于情感分析提出移动图书馆用户生成内容评价效果分析过程，以获取的"掌阅图书馆"中15部年度畅销书籍的用户生成内容为研究样本，对数据进行预处理，在此基础上从领域词典构建、情感分类、评价效果3个过程入手进行分析。[结果/结论]数据分析结果表明，移动图书馆UGC用户情感倾向具有多元性和一致性，中性评价具有重要性，能够较为准确地预测移动图书馆资源的得分情况。将情感分析相关理论和方法引入移动图书馆UGC研究，能够为移动图书馆完善其服务措施、提高其服务质量提供参考意见。
[Purpose/significance] This study aims to make an analysis of the evaluation effect of the mobile library user-generated content (UGC), which is beneficial to improve the recommendation and promotion of mobile library resources.[Method/process] An evaluation model is constructed based on the sentimental analysis. After the preprocessing of the UGC of the 16 best-selling books from Zhangyue library, data analysis is divided into three stages, including dictionary construction, sentiment classification and evaluation.[Result/conclusion]The results show that the sentimental tendencies of UGC in mobile libraries are pluralistic and consistent, and the neutral evaluation is important, as well as the final evaluation results is reasonable.In this paper, the theory of sentiment analysis is introduced into the research of mobile library UGC, which can provide reference for mobile library to improve its social service measures and improve its social service quality.
[1] 赵宇翔, 朱庆华. Web2.0环境下影响用户生成内容的主要动因研究[J]. 中国图书馆学报,2009,35(5):107-116.
[2] ZHITOMIRSKY-GEFFET M, MAMAN Y. Wisdom of the crowds and online information reliability:a case study of Israeli real estate websites[J]. Online information review,2014,38(3):7-8.
[3] SIGUENZA-GUZMAN L, SAQUICELA V, AVILA-ORDONEZ E, et al. Literature review of data mining applications in academic libraries[J]. The journal of academic librarianship,2015,41(4):499-510.
[4] ZHOU Q, ZHANG C, ZHAO S X, et al. Measuring book impact based on the multi-granularity online review mining[J]. Scientometrics,2016,107(3):1435-1455.
[5] 祝振媛. 基于信息分类的网络书评内容挖掘与整合研究[J]. 图书情报工作,2016,60(1):114-124.
[6] 侯银秀, 李伟卿, 王伟军, 等. 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.
[7] ZHANG X, YU Y, LI H, et al. Sentimental interplay between structured and unstructured user-generated contents:an empirical study on online hotel reviews[J]. Online information review,2016,40(1):119-145.
[8] OECD. Participative web and user-created content:web 2.0, wikis and social networking edition complete. OCDE information sciences and technologies (October 2007)[OL].[2008-11-18]. http://www.oecd.org/document/40/0,3343,en_2649_34223_39428648_1_1_1_1,00.html.
[9] 赵宇翔, 范哲, 朱庆华. 用户生成内容(UGC)概念解析及研究进展[J]. 中国图书馆学报,2012,38(5):68-81.
[10] FLANAGIN A J, METZGER M J. Trusting expert-versus user-generated ratings online:the role of information volume, valence, and consumer characteristics[J]. Computers in human behavior,2013,29(4):1626-1634.
[11] 范哲, 朱庆华, 赵宇翔. Web2.0环境下UGC研究述评[J]. 图书情报工作,2009,53(22):60-63.
[12] CHOI B, LEE I. Trust in open versus closed social media:the relative influence of user-and marketer-generated content in social network services on customer trust[J]. Telematics and informatics,2017,34(5):550-559.
[13] SUN J, WANG G, CHENG X, et al. Mining affective text to improve social media item recommendation[J]. Information processing & management,2015,51(4):444-457.
[14] PIRYANI R, MADHAVI D, SINGH V K. Analytical mapping of opinion mining and sentiment analysis research during 2000-2015[J]. Information processing & management,2017,53(1):122-150.
[15] 朱琳琳, 徐健. 网络评论情感分析关键技术及应用研究[J]. 情报理论与实践,2017,40(1):121-126.
[16] PECOSKIE J, SPITERI L F, TARULLI L. OPACs, users, and readers' advisory:exploring the implications of user-generated content for readers' advisory in canadian public libraries[J]. Cataloging & classification quarterly,2014,52(4):431-453.
[17] DEZELARTIEDMAN C. Exploring user-contributed metadata's potential to enhance access to literary works:social tagging in academic library catalogs[J]. Library resources & technical services,2011,55(4):221-233.
[18] NAIK Y, TROTT B. Finding good reads on goodreads:readers take RA into theirown hands[J]. Reference & user services quarterly,2012,51(4):319-323.
[19] SPITERI L F. Social discovery tools:extending the principle of user convenience[J]. Journal of documentation,2012,68(2):206-217.
[20] MOON Y J, KIM W G, ARMSTRONG D J. Exploring neuroticism and extraversion in flow and user generated content consumption[J]. Information & management,2014,51(3):347-358.
[21] 杨华. 图书馆UGC资源建设机制初探[J]. 图书馆理论与实践,2017(1):48-52.
[22] RUMELHART D E, MCCLELLAND J L. Parallel distributed processing:explorations in the microstructure of cognition[J]. Language,1986,63(4):45-76.
