Research ArticleMeasuring and profiling the topical influence and sentiment contagion of public event stakeholders
Introduction
When a society is in a period of transformation, social contradictions and problems become increasingly serious, resulting in frequent public events. According to the National Overall Emergency Plan for Public Emergencies (2006), public events can be divided into four types, i.e., natural disasters, accident disasters, public health events, and social security incidents. In the UK Government Advice on Definition of an Emergency (2007), public events consist of an event which “threatens serious damage” to human welfare, the environment, or security. If a public event cannot be disposed properly, it may have serious consequences and evolve into a crisis. Among those types of public events, the social security-related events often attract a lot of discussions. More and more netizens express their opinions and emotions in relation to major events through social media, such as microblogging (Son, Lee, Jin, & Lee, 2019). Their behaviors, such as forwarding and commenting on posts, contribute to the emergence of intricate networks of topic and sentiment propagation. A consensus has been reached that social media has become an important platform for the dissemination of public opinions on major events. A public event often involves multiple stakeholders. Due to the differences in occupation, influence and their relationship with the public event, different stakeholders play different roles in topic and sentiment propagation. With the help of multi-directional communication channels in social network, views and emotions of individuals, especially those of high influence, may quickly infect other users and occupy the whole network instantly.
As early as 1961, a phenomenon of group polarization (Stoner, 1961) was discovered that group decision-making tends to be more risky than individual decision-making in most cases, and deviates from the best decision-making scheme. It is also found that online groups are more prone to group polarization than those in real life (Sia, Tan, & Wei, 2002). When a public event occurs, plenty of information and opinions rapidly spread on various social media platforms that the situation may become uncontrollable due to malicious rumors, extreme opinions, and negative emotions (Kwon, Bang, Egnoto, & Rao, 2016). The rumors may ignite the emotions of netizens, and the panic of the public can be amplified. These may lead to a mass event and eventually cause a serious blow to the harmony and stability of society. On the other hand, when public opinion is pushed to an extreme, it will bring great challenges to the emergency response. Therefore, it is of great significance for the emergency response departments to understand the evolution and propagation patterns of topics and emotions in social media, the composition and influence of stakeholders in online information dissemination as well as their interaction so that the administrators can provide timely and effective response to major events.
This study aims to explore the answers to the following questions:
- 1)
When a social security-related public event triggers a tsunami of opinion on social media, how can we measure the topical influence and sentiment contagion of stakeholders?
- 2)
Which types of stakeholders contribute the most to the topical influence and sentiment contagion of public opinions at different phases of an event life cycle?
- 3)
How do the propagation of stakeholders' topics of concerns are associated with their emotions?
In order to answer these questions, this study generates the topic and sentiment propagation maps, which are built upon forwarding relationships among stakeholders at the microblogging platform. The findings can help the public event management departments understand the dissemination mechanism of online public opinion so that they, in turn, can develop scientific and effective strategies for public crisis response.
This article is organized as follows: Section 2 reviews the related literature on social media in public crises, the lifecycle and stakeholder theories. Section 3 develops several hypotheses regarding the research questions. Section 4 describes the methods of data collection, constructing topic and sentiment propagation maps and measuring the users’ topical influence and sentiment contagion. Section 5 presents the results and findings followed by the discussion of contributions, limitations, and future research (Section 6). Finally, Section 7 summarizes the conclusion.
Section snippets
Studies on social media in public crises
The emergence of social media has created an unprecedented environment in which people can rapidly share their opinions. Governmental agencies who were formerly unidirectional information disseminators are now also recipients of large amounts of information originating from the public (Simon, Goldberg, & Adini, 2015). From the organizational perspective, social media has become an interactive communication channel which can deliver information and receive feedback in a fast way (Alalwan, Rana,
Hypotheses development
A public event usually undergoes several stages, such as the prodromal stage, the acute stage, the chronic stage, and the resolution stage (Steven, 1986). At different stages, stakeholders tend to discuss about the issues that are related to the current status of the event. Thus, the microblog topics at different stages are different (An et al., 2018). With the development of the public event, the related problems may be solved or worsen. Hence the microblog sentiments vary across different
Methodology
In this study, we crawled the microblog entries on a specific public event and classified microblog users into different types of stakeholders. The propagation maps of topics and sentiment were constructed based on the forwarding relationships among microblog entries, and they were labeled with the topic and sentiment features of microblogging. The flowchart includes five modules as shown in Fig. 1.
Data
We chose the child abuse event in the Beijing RYB Kindergarten on November 22, 2017 as the case study. The incident was triggered by the parents’ accusations of child abuse at the kindergarten. Their allegations that children were pierced by needles and given unidentified pills raised massive media attention and a storm of public opinion. Fig. 3 shows the micro index trends of the event-related keywords “three colors,” “red, yellow and blue,” and “child abuse”. Micro index is provided by the
Discussion
Existing literature, such as Cody et al. (2015) and Karami et al. (2018), mainly analyze the content characteristics of social media over time when a public event occurs. The information disseminators are often ignored in previous studies. This study has made the following three research findings, i.e., a) identifying the different roles played by different stakeholder types in information propagation chains, b) measuring the differences in the topical influence and sentiment contagion among
Conclusion
In this study, we measure and profile the topical influence and sentiment contagion of public event stakeholders and propose four indicators, i.e., topic out-degree, topic variation degree, sentiment out-degree, and sentiment deviation degree. By quantifying and comparing the topical and emotional influence of different stakeholders, we provide a deep insight into the public opinion propagation pattern in social media context. Combining the three dimensions of information dissemination, i.e.
CRediT authorship contribution statement
Lu An: Conceptualization, Methodology, Writing - review & editing, Funding acquisition. Wenjing Zhou: Data curation, Writing - original draft, Investigation, Validation. Menghua Ou: Visualization, Investigation, Software, Writing - original draft, Data curation. Gang Li: Conceptualization, Methodology, Writing - review & editing, Funding acquisition. Chuanming Yu: Writing - review & editing, Funding acquisition. Xiaofen Wang: Software, Validation.
Declaration of Competing Interest
The authors reported no declarations of interest.
Acknowledgments
This research was supported by the Major Project of the Ministry of Education of China (Grant No. 17JZD034), the National Natural Science Foundation of China (Grant No. 71921002, 71790612 and 71974202, 71603189), and the world class discipline of the Ministry of Education “Library, Information, and Data Science.” We are very grateful to the anonymous reviewers for their insightful comments.
References (66)
- et al.
Social media in marketing: A review and analysis of the existing literature
Telematics and Informatics
(2017) - et al.
Search engine marketing is not all gold: Insights from Twitter and SEOClerks
International Journal of Information Management
(2018) - et al.
Evolution of complex disasters
Public Health
(1995) - et al.
Polarization and acculturation in US Election 2016 outcomes – Can twitter analytics predict changes in voting preferences
Technological Forecasting and Social Change
(2019) - et al.
Characterizing information propagation patterns in emergencies: A case study with Yiliang Earthquake
International Journal of Information Management
(2018) - et al.
Temporal and spatial evolution of online public sentiment on emergencies
Information Processing & Management
(2020) - et al.
Impact of degree mixing pattern on consensus formation in social networks
Physica A Statistical Mechanics and Its Applications
(2014) - et al.
How publics respond to crisis communication strategies: The interplay of information form and source
Public Relations Review
(2011) - et al.
SuperedgeRank algorithm and its application in identifying opinion leader of online public opinion super network
Expert Systems With Applications
(2014) - et al.
Twitter as a tool for the management and analysis of emergency situations: A systematic literature review
International Journal of Information Management
(2018)
Stakeholder theory for the E-government context: Framing a value-oriented normative core
Government Information Quarterly
Making retweeting social: The influence of content and context information on sharing news in twitter
Computers in Human Behavior
Contextual semantics for sentiment analysis of Twitter
Information Processing & Management
Socializing in emergencies - A review of the use of social media in emergency situations
International Journal of Information Management
Content features of tweets for eff ;ective communication during disasters: A media synchronicity theory perspective
International Journal of Information Management
Social media analytics – Challenges in topic discovery, data collection, and data preparation
International Journal of Information Management
Does government information release really matter in regulating contagion-evolution of negative emotion during public emergencies? From the perspective of cognitive big data analytics
International Journal of Information Management
Topical evolution patterns and temporal trends of microblogs on public health emergencies-A case study of Ebola on Twitter and Weibo
Online Information Review
Topic-aware social influence propagation models
Knowledge and Information Systems
Gephi: An open source software for exploring and manipulating networks
Proceedings of the Third International AAAI Conference on Weblogs and Social Media
Opinion propagation in online social networks: A survey
Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics
Measuring user influence in twitter: The million follower fallacy
Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media
LTP: A Chinese language technology platform
Journal of Chinese Information Processing
Climate change sentiment on twitter: An unsolicited public opinion poll
PloS One
Lexical TF-IDF: An n-gram feature space for cross-domain classification of sentiment reviews
Proceedings of the International Conference on Pattern Recognition and Machine Intelligence
Social media marketing and advertising
The Marketing Review
Strategic management: The stakeholder approach
Graph drawing by force-directed placement
Software: Practice & Experience
Crisis management
Use of microblogging for collective sense-making during violent crises: A study of three campus shootings
Journal of the Association for Information Science and Technology
Valence-based homophily on Twitter: Network analysis of emotions and political talk in the 2012 presidential election
New Media & Society
Online media as a means to affect public trust in emergency responders
Proceedings of the 12th International Conference on Information Systems for Crisis Response and Management
ForceAtlas2, a continuous Graph layout algorithm for handy network visualization designed for the Gephi software
PloS One
Cited by (39)
Diffusion of real versus misinformation during a crisis event: A big data-driven approach
2023, International Journal of Information ManagementCitation Excerpt :As a result, misinformation stories frequently circulate in cyberspace. However, the extant literature has been primarily focused on health-related misinformation (Wang, McKee, Torbica, & Stuckler, 2019) and general news stories or rumors (Agrawal, Rao, & Oh, 2013; An et al., 2021; Bunker, 2020; Cheng, Liu, Shen, & Yuan, 2013; Friggeri, Adamic, Eckles, & Cheng, 2014; Ma et al., 2016; Oh et al., 2010; Parra, Gupta, & Mikalef, 2021; Shin et al., 2018). Rumors are social by nature and can be either false or accurate.
Order from chaos: Deconstructing the interactions of multiple online stakeholders in NIMBY conflicts
2023, Environmental Science and PolicyExploring the impact of sentiment on multi-dimensional information dissemination using COVID-19 data in China
2023, Computers in Human BehaviorSentiment analysis on images using convolutional neural networks based Inception-V3 transfer learning approach
2023, International Journal of Information Management Data Insights