|
|
|
| Quantitatively Analyzing Social Network Information Interaction: Integrating the Emotional Elements from Machine Learning's Perspective |
| Ma Jie1,2, Hao Zhiyuan1 |
1.School of Management, Jilin University, Changchun 130022
2.Research Center for Big Data Management, Jilin University, Changchun 130022 |
|
|
|
|
Abstract In the digital information era, social networks provide a platform for users to discuss hot topics. To correctly guide the public opinion trends in social networks and reduce the negative impact on information dissemination, this study uses real comment data of social networks as the research object, from the perspective of interaction and information behavior. Additionally, the study confirmed the comment tendency category using density peak clustering algorithm. A quantitative model of social network information interaction degree was proposed, which introduced the basic strategy of variance weighted information entropy and referred to the existing methods of calculating emotional polarity. By calculating the information interaction degree mapped by the results of cognition classification, this study clarified the research subject's controversy degree and the public opinion evolution trends. Furthermore, the case study shows that the information interaction degree based on the emotion analysis perspective quantifies the information value of hot topics. The findings of the study can be of great theoretical significance for promoting the healthy and civilized development of the Internet and strengthening the network supervision ability of the relevant departments.
|
|
Received: 13 August 2020
|
|
|
|
1 Bayrakdar S, Yucedag I, Simsek M, et al. Semantic analysis on social networks: a survey[J]. International Journal of Communication Systems, 2020, 33(11): e4424.
2 Costello K L, Veinot T C. A spectrum of approaches to health information interaction: from avoidance to verification[J]. Journal of the Association for Information Science and Technology, 2020, 71(8): 871-886.
3 Buijs M, Spruit M. Asynchronous social search as a single point of access to information[J]. Library Hi Tech, 2017, 35(4): 649-664.
4 Bronstein J, Tzivian L. Perceived self-efficacy of library and information science professionals regarding their information retrieval skills[J]. Library & Information Science Research, 2013, 35(2): 151-158.
5 邓小咏, 李晓红. 网络环境下的用户信息行为探析[J]. 情报科学, 2008, 26(12): 1810-1813.
6 马捷, 孙梦瑶, 尹爽, 等. 微博信息生态链构成要素与形成机理[J]. 图书情报工作, 2012, 56(18): 73-77, 81.
7 杨璐伊, 汪祖柱. 政务微博的危机信息交互效果研究[J]. 大学图书情报学刊, 2018, 36(2): 118-125.
8 孙璐, 李力, 孔英. 信息交互能力的测度及其对竞争优势的影响研究: 基于用户体验的价值共创视角[J]. 管理工程学报, 2018, 32(2): 67-83.
9 王晰巍, 韦雅楠, 邢云菲, 等. 新媒体环境下企业与用户信息交互行为模型及特征研究[J]. 图书情报工作, 2018, 62(18): 6-15.
10 巴志超, 李纲, 毛进, 等. 微信群内部信息交流的网络结构、行为及其演化分析——基于会话分析视角[J]. 情报学报, 2018, 37(10): 1009-1021.
11 易明, 赵锦香, 张展豪, 等. 人类动力学视角下在线社区信息交流行为研究[J]. 情报科学, 2020, 38(8): 3-10.
12 尚丽维, 张向先, 卢恒, 等. 在线社区信息交互关系网络关键节点研究综述[J]. 情报科学, 2020, 38(8): 170-177.
13 胡蓉, 唐振贵, 赵宇翔, 等. 移动经验取样法: 促进真实情境下的用户信息行为研究[J]. 情报学报, 2018, 37(10): 1046-1059.
14 宋筱璇, 刘畅. 学习型搜索中用户信息源选择和使用策略研究[J]. 情报学报, 2019, 38(6): 655-666.
15 Irfan Ali Shah, 王芳. 巴基斯坦政府门户网站公众初始接受的影响因素研究——基于使用意向和执行意向双重视角[J]. 情报学报, 2019, 38(5): 543-556.
16 Pang B, Lee L, Vaithyanathan S. Thumbs up?: sentiment classification using machine learning techniques[C]// Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2002: 79-86.
17 Berka P. Sentiment analysis using rule-based and case-based reasoning[J]. Journal of Intelligent Information Systems, 2020, 55(1): 51-66.
18 Sharma A, Ghose U. Sentimental analysis of twitter data with respect to general elections in India[J]. Procedia Computer Science, 2020, 173: 325-334.
19 杨鹏, 杨青, 李志斌, 等. 基于注意力机制的交互式神经网络模型在细粒度情感分类中的应用[J]. 计算机应用与软件, 2020, 37(7): 130-135.
20 林敏鸿, 蒙祖强. 基于注意力神经网络的多模态情感分析[J]. 计算机科学, 2020, 47(S2): 508-514, 548.
21 徐健, 吴思洋. 网络用户评论的情感分歧度量化算法研究[J]. 情报学报, 2020, 39(4): 427-435.
22 Fung T K F, Choi D H, Scheufele D A, et al. Public opinion about biofuels: the interplay between party identification and risk/benefit perception[J]. Energy Policy, 2014, 73: 344-355.
23 Stewart K N, Basic J, Erdelez S. ODI and information literacy: personal information management in a world of information overload[J]. Proceedings of the American Society for Information Science and Technology, 2012, 49(1): 1-4.
24 Rasmussen A, Romeijn J, Toshkov D. Dynamics of regulatory policymaking in Sweden: the role of media advocacy and public opinion[J]. Scandinavian Political Studies, 2018, 41(1): 49-74.
25 高俊峰, 宋绍成. 网络舆情分析及治理的研究进展[J]. 情报理论与实践, 2017, 40(6): 134-138.
26 陈福集, 胡改丽. 网络舆情热点话题传播模式研究[J]. 情报杂志, 2014, 33(1): 97-101, 156.
27 王晰巍, 张柳, 文晴, 等. 基于贝叶斯模型的移动环境下网络舆情用户情感演化研究——以新浪微博“里约奥运会中国女排夺冠”话题为例[J]. 情报学报, 2018, 37(12): 1241-1248.
28 陈思菁, 李纲, 毛进, 等. 突发事件信息传播网络中的关键节点动态识别研究[J]. 情报学报, 2019, 38(2): 178-190.
29 张连峰, 王丹, 张海涛. 全景生态视角的微博舆情传播本质: 机理与规律[J]. 情报科学, 2020, 38(8): 16-22, 34.
30 高俊峰. 网络舆情场内领袖型信息受众的观点动员能力测度[J]. 情报科学, 2019, 37(1): 37-42.
31 刘雅婷. 基于城市计算网络的信息交互建模[J]. 中国高新技术企业, 2014(16): 14-15.
32 苗壮, 王亚平. 基于私有云计算的信息交互模型研究[J]. 电子设计工程, 2013, 21(18): 97-100.
33 赵洪钢, 李娴, 时晨, 等. 基于社会感知计算的无线传感器网络信息交互模型[J]. 无线通信技术, 2016, 25(3): 7-12.
34 Kondylidis N, Tzelepi M, Tefas A. Exploiting tf-idf in deep convolutional neural networks for content based image retrieval[J]. Multimedia Tools and Applications, 2018, 77(23): 30729-30748.
35 Rodriguez A, Laio A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.
36 孔瑞远, 沈艳丽, 肖桃顺, 等. 基于信息熵的战场信息价值度量模型研究[J]. 中国电子科学研究院学报, 2019, 14(2): 139-145.
37 Wang L M, Hao Z Y, Han X M, et al. Gravity theory-based affinity propagation clustering algorithm and its applications[J]. Technical Gazette, 2018, 25(4): 1125-1135.
38 Wang L M, Hao Z Y, Sun W J. A novel self-adaptive affinity propagation clustering algorithm based on density peak theory and weighted similarity[J]. IEEE Access, 2019, 7: 175106-175115.
39 郭明, 王书满. 基于区域和方向方差加权信息熵的图像融合[J]. 系统工程与电子技术, 2013, 35(4): 720-724. |
|
|
|
