Studies on a multidimensional public opinion network model and its topic detection algorithm |
| |
| Institution: | 1. Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190, China;2. Center for Interdisciplinary Studies of Natural and Social Sciences, Chinese Academy of Sciences, Beijing 100190, China;3. University of Chinese Academy of Sciences, Beijing 100190, China;4. Beijing University of Posts and Telecommunications, Beijing 100876, China;1. Department of Computer Science, University of Vigo, ESEI, Campus As Lagoas, 32004 Ourense, Spain;2. The Biomedical Research Centre (CINBIO), Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain;3. SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain;4. Centre of Biological Engineering (CEB), University of Minho, Campus de Gualtar, 4710-057 Braga, Portugal;1. School of Computer Science, South China Normal University, Guangzhou, China;2. Department of SEEM, The Chinese University of Hong Kong, Hong Kong;3. Graduate School at Shenzhen, Tsinghua University, Shenzhen, China;4. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China;5. School of Electronics and Computer Engineering, Peking University Shenzhen Graduate School, China;1. Faculty of Information Technology, Hung Yen University of Technology and Education, Hung Yen, Vietnam;2. School of Information Science, Japan Advanced Institute of Science and Technology (JAIST), 1-1 Asahidai, Nomi, Ishikawa, 923-1292, Japan;3. Hanoi University of Science and Technology, Hanoi, Vietnam;4. AI Academy Vietnam, 489 Hoang Quoc Viet Rd, Hanoi, Vietnam;1. Department of Data Analytics, College of Business and Public Administration, Drake University, 385 Aliber Hall, 2847 University Ave, Des Moines, IA, USA;2. Department of Public Health, Des Moines University, Des Moines, IA, USA |
| |
| Abstract: | “We the Media” networks are real time and open, and such networks lack a gatekeeper system. As netizens’ comments on emergency events are disseminated, negative public opinion topics and confrontations concerning those events also spread widely on “We the Media” networks. Gradually, this phenomenon has attracted scholarly attention, and all social circles attach importance to the phenomenon as well. In existing topic detection studies, a topic is mainly defined as an "event" from the perspective of news-media information flow, but in the “We the Media” era, there are often many different views or topics surrounding a specific public opinion event. In this paper, a study on the detection of public opinion topics in “We the Media” networks is presented, starting with the characteristics of the elements found in public opinions on “We the Media” networks; such public opinions are multidimensional, multilayered and possess multiple attributes. By categorizing the elements’ attributes using social psychology and system science categories as references, we build a multidimensional network model oriented toward the topology of public opinions on “We the Media” networks. Based on the real process by which multiple topics concerning the same event are generated and disseminated, we designed a topic detection algorithm that works on these multidimensional public opinion networks. As a case study, the “Explosion in Tianjin Port on August 12, 2015″ accident was selected to conduct empirical analyses on the algorithm's effectiveness. The theoretical and empirical research findings of this paper are summarized along the following three aspects. 1. The multidimensional network model can be used to effectively characterize the communication characteristics of multiple topics on “We the Media” networks, and it provided the modeling ideas for the present paper and for other related studies on “We the Media” public opinion networks. 2. Using the multidimensional topic detection algorithm, 70% of the public opinion topics concerning the case study event were effectively detected, which shows that the algorithm is effective at detecting topics from the information flow on “We the Media” networks. 3. By defining the psychological scores of single and paired Chinese keywords in public opinion information, the topic detection algorithm can also be used to judge the sentiment tendencies of each topic, which can facilitate a timely understanding of public opinion and reveal negative topics under discussion on “We the Media” networks. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
