基于情感分析的新浪微博争议度分析

摘要/Abstract

摘要：

随着新浪微博的广泛使用，新浪微博传播的内容涵盖了各种领域的信息，涉及范围越来越广；同时，当用户浏览消息时，不仅能够表达自己的看法，同时能够看到别人的观点。因此,当用户无法判断问题的客观性时，通常会利用其他公众的反馈信息进行评估。为了充分利用公众反馈信息，提出了一种描述公众反馈信息的社会属性——争议度。给出了争议度的概念并构建了争议度计算模型，该模型将公众对微博的反应（即表态、评论、转发等行为）作为争议度的影响因素，通过情感分析等技术计算微博消息的争议度。实验结果对照人工标注结果，模型准确率达到93%，有效率达84%，证明了该模型的可行性。

关键词: 新浪微博, 情感分析, 争议度, 公众反应

Abstract:

With the popular use of microblogs,the contents of Sina Microblog cover information of various fields,and the rang becomes increasingly wider.As a result,when users of the microblog browse news,they may feel confused concerning what they can believe.So they probably turn to others’ feedback.We propose a concept of disputed-level,a new social property of microblogs,which describes the feedback from public.We define the content of disputed-level and build a disputed-level calculation model.In the model,the influencing factors of disputed-level include comments and forwording.We use the sentiment analysis to calculate the disputed-level.The accuracy rate of the model in the experiment can reach 93%,the efficiency 84%,which prove the feasibility of the model.

Key words: Sina Microblog, sentiment analysis, disputed-level, public feedback

刘莉平，刘梦，李绍鹏. 基于情感分析的新浪微博争议度分析[J]. 计算机工程与科学.

LIU Li-ping，LIU Meng，LI Shao-peng.

Sina Microblog disputed-level analysis

based on sentiment analysis

[J]. Computer Engineering & Science.

参考文献

［1］Efstratios K，Christos B,Theologos D,et al.Ontology-based sentiment analysis of Twitter posts［J］,Expert Systems with Applications,2013,40(10):4065-4074.

［2］Haewoon K,Changhyun L,Hosung P,et al.What is Twitter,a social network or a news media?［C］∥Proc of the 19th ACM International Conference on World Wide Web,2010:591-600.

［3］Liu Guo,Wang Tie-jun.Comment on the function and value of micro-blog expansion［J］.Journal of Hunan University(Social Sciences),2013,27(6):158-160.(in Chinese)

［4］Wang Lai-hua. The “Snowball” of the public opinions and sentiments:An Internet stress on the people’s Interests demands［J］.Theory and Modernization,2013,(3):94-97.(in Chinese)

［5］Tan Cheng-fang. The Chinese microblog emotional tendency analysis based on sentiment dictionary［J］.Applied Mechanics and Materials,2013,333-335:795-798.

［6］Du Wei-fu.Research on sentimental lexicon construction for text sentiment analysis［D］.Harbin:Harbin Institute of Technology,2000.(in Chinese)

［7］Kaji N,Kitsuregawa M.Building lexicon for sentiment analysis from massive collection of html documents［C］∥Proc of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (Emnlp-Conll),2007:1075-1083.

［8］Whitelaw C,Garg N,Argamon S.Using appraisal groups for sentiment analysis［C］∥Proc of the 14th ACM International Conference on Information and Knowledge Management(CIKM’05),2005:625-631.

［9］Liu S M, Chen J H. A multi-label classification based approach for sentiment classification［J］.Expert Systems with Applications,2015,42(3):1083-1093.

［10］Chu Jian-feng.Research and implementation of product attribute and inclination recognition technology form comments of E-commerce and Weibo［D］.Shanghai:Donghua University,2014.(in Chinese)

［11］Xu Zhi-heng, Yang Qing.Analyzing user retweet behavior on Twitter［C］∥Proc of 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining,2012:18,DOI 10.1109/ASONAM.

［12］David R B,Liu Yue,Robert P D,et al.Aggregate characterization of user behavior in Twitter and analysis of the retweet graph［J］.ACM Transactions on Internet Technology,2015,15(1):1-24.

［13］Kyumin L,Jalal M,Chen Ji-lin,et al.Who will retweet this?Detecting strangers from Twitter to retweet information［J］.ACM Transactions on Intelligent Systems and Technology,2015,6(3):1-25.

［14］Xie Song-xian,Tang Jin-tao,Wang Ting.Resonance elicits diffusion:Modeling subjectivity for retweeting behavior analysis［J］.Cogn Comput,2015,7(2):198-210.

［15］Macskassy S A,Michelson M.Why do people retweet?Antihomophily wins the day!［C］∥Proc of the International Conference on Weblogs Social Uledia.2011:1.

［16］Jenders M,Kasneci G,Naumann F.Analyzing and predicting viral tweets［C］∥Proc of the 22nd International Conferenceon World Wide Web Companion,WWW ’13 Companion.International World Wide Web Conferences Steering Committee,2013:657-664.

［17］Pfitzner R,Garas A,Schweitzer F.Emotional divergence influences information spreading in twitter［C］∥Proc of Internctional AAAI Conference on Weblogs & Social Media,2012:1.

［18］Wang Bin.Like:Sociological interpretation of youth network interactive new ways［J］.China Youth Study,2014(7):20-24.(in Chinese)

［19］Zhao Yan-yan,Qin Bing,Liu Ting.Sentiment analysis［J］.Journal of Software,2010,21(8):1834-1848.(in Chinese)

［20］Rafeeque P, Selvaraju S, Mahalakshmi G S. Twitter sentiment analysis for large-scale data:An unsupervised approach［J］.Cogn Comput,2015,7(2):254-262.

［21］Farhan H K,Saba B,Usman Q .TOM:Twitter opinion mining framework using hybrid classification scheme［J］.Decision Support Systems,2014,57(3):245-257.

附中文参考文献：

［3］刘果,王铁军.论微博的评论功能及价值拓展［J］.湖南大学学报(社会科学版),2013,27(6):158-160.

［4］王来华.“舆情雪球”现象:新媒体对民意诉求的强化［J］.理论与现代化,2013(3):94-97.

［6］杜伟夫.文本倾向性分析中的情感词典构建技术研究［D］.哈尔滨：哈尔滨工业大学，2010.

［10］褚剑峰.电商和微博评论中商品属性与倾向性识别技术的研究与实现［D］.上海：东华大学，2014.

［18］王斌.点赞:青年网络互动新方式的社会学解读［J］.中国青年研究,2014（7）：20-24.

［19］赵妍妍,秦兵,刘挺.文本情感分析［J］.软件学报,2010,21（8）:1834-1848.

[1]	董芃杉, 张晶, 金日泽. 基于双通道门控复合网络的中文产品评论情感分析[J]. 计算机工程与科学, 2023, 45(05): 911-919.
[2]	杨春霞, 姚思诚, 宋金剑, . 一种融合字词信息的中文情感分析模型[J]. 计算机工程与科学, 2023, 45(03): 512-519.
[3]	杨春霞, 姚思诚, 宋金剑, . 基于词共现的方面级情感分析模型[J]. 计算机工程与科学, 2022, 44(11): 2071-2079.
[4]	杨春霞, 宋金剑, 姚思诚, . 基于深度BiLSTM和图卷积网络的方面级情感分析[J]. 计算机工程与科学, 2022, 44(10): 1893-1900.
[5]	张宝华 , 李奀林 , 张华平 , 商建云. 基于层次体系的情感单元表示方法[J]. 计算机工程与科学, 2022, 44(01): 149-158.
[6]	王春东, 张卉, 莫秀良, 杨文军. 微博情感分析综述[J]. 计算机工程与科学, 2022, 44(01): 165-175.
[7]	黄泽民, 吴晓鸰, 吴迎岗, 凌捷. 结合BERT和BiSRU-AT的中文文本情感分类[J]. 计算机工程与科学, 2021, 43(09): 1668-1674.
[8]	张琦, 张祖凡, 甘臣权. 融合社会关系的社交网络情感分析综述[J]. 计算机工程与科学, 2021, 43(01): 180-190.
[9]	李俭兵1,2,3,刘栗材1,3. 基于改进型神经网络的影评文本情感分析算法[J]. 计算机工程与科学, 2019, 41(12): 2261-2269.
[10]	裴颂文1,2，王露露1. 基于注意力机制的文本情感倾向性研究[J]. 计算机工程与科学, 2019, 41(02): 343-353.
[11]	洪庆,王思尧,赵钦佩,李江峰,饶卫雄. 基于弹幕情感分析和聚类算法的视频用户群体分类[J]. 计算机工程与科学, 2018, 40(06): 1125-1139.
[12]	杜昌顺，黄磊. 分段卷积神经网络在文本情感分析中的应用[J]. 计算机工程与科学, 2017, 39(01): 173-179.
[13]	谢松县1，赵舒怡 2. 一种基于混合特征的中文情感词典扩展方法[J]. 计算机工程与科学, 2016, 38(07): 1502-1509.
[14]	刘义红1，2,朱琛2,祝恒书3. 一种基于词序的社会情感演变分析模型[J]. J4, 2015, 37(11): 2175-2181.
[15]	杨〓亮,林鸿飞,郭〓巍. 面向文本的情感迁移分析策略[J]. J4, 2011, 33(9): 123-129.