Sentiment Diffusion of Public Opinions about Hot Events: Based on Complex Network

Xiaoqing Hao; Haizhong An; Lijia Zhang; Huajiao Li; Guannan Wei

doi:10.1371/journal.pone.0140027

Sentiment Diffusion of Public Opinions about Hot Events: Based on Complex Network

PLoS One. 2015 Oct 13;10(10):e0140027. doi: 10.1371/journal.pone.0140027. eCollection 2015.

Authors

Xiaoqing Hao¹, Haizhong An², Lijia Zhang¹, Huajiao Li², Guannan Wei¹

Affiliations

¹ School of Humanities and Economic Management, China University of Geosciences, Beijing 100083, China.
² School of Humanities and Economic Management, China University of Geosciences, Beijing 100083, China; Key Laboratory of Carrying Capacity Assessment for Resource and Environment, Ministry of Land and Resources, Beijing 100083, China; Lab of Resources and Environmental Management, China University of Geosciences, Beijing 100083, China.

Abstract

To study the sentiment diffusion of online public opinions about hot events, we collected people's posts through web data mining techniques. We calculated the sentiment value of each post based on a sentiment dictionary. Next, we divided those posts into five different orientations of sentiments: strongly positive (P), weakly positive (p), neutral (o), weakly negative (n), and strongly negative (N). These sentiments are combined into modes through coarse graining. We constructed sentiment mode complex network of online public opinions (SMCOP) with modes as nodes and the conversion relation in chronological order between different types of modes as edges. We calculated the strength, k-plex clique, clustering coefficient and betweenness centrality of the SMCOP. The results show that the strength distribution obeys power law. Most posts' sentiments are weakly positive and neutral, whereas few are strongly negative. There are weakly positive subgroups and neutral subgroups with ppppp and ooooo as the core mode, respectively. Few modes have larger betweenness centrality values and most modes convert to each other with these higher betweenness centrality modes as mediums. Therefore, the relevant person or institutes can take measures to lead people's sentiments regarding online hot events according to the sentiment diffusion mechanism.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Emotions*
Humans
Internet*
Public Opinion*

Grants and funding

This research is supported by grants from the Natural Science Foundation of China (Grant No. 71173199), the Humanities and Social Sciences planning funds project under the Ministry of Education of the PRC (Grant No.10YJA630001). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.