An Influence Prediction Model for Microblog Entries on Public Health Emergencies

Luo, An; Yi, Xingyue; Han, Yuxin; Li, Gang

doi:10.2478/dim-2018-00013

Cited by 2 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core of this type of method is how to represent the feature of a document effectively. Commonly used feature representation methods comprise EL 41,5 BERT (Devlin et al, 2018), BiLSTM (Qi and Liu, 2021) and Word2vec (An and Wu, 2017). The probabilistic topic model-based methods assume that each document has a latent distribution over all topic terms, and each topic has a latent distribution over all documents (Huang et al, 2022).…”

Section: Topic Discovery Of Online Public Opinionmentioning

confidence: 99%

Constructing a spatiotemporal situational awareness framework to sense the dynamic evolution of online public opinion on social media

Li,

Zeng,

Sun

et al. 2023

View full text Add to dashboard Cite

Purpose The paper aims to construct a spatiotemporal situational awareness framework to sense the evolutionary situation of public opinion in social media, thus assisting relevant departments in formulating public opinion control measures for specific time and space contexts. Design/methodology/approach The spatiotemporal situational awareness framework comprises situational element extraction, situational understanding and situational projection. In situational element extraction, the data on the COVID-19 vaccine, including spatiotemporal tags and text contents, is extracted. In situational understanding, the bidirectional encoder representation from transformers – latent dirichlet allocation (BERT-LDA) and bidirectional encoder representation from transformers – bidirectional long short-term memory (BERT-BiLSTM) are used to discover the topics and emotional labels hidden in opinion texts. In situational projection, the situational evolution characteristics and patterns of online public opinion are uncovered from the perspective of time and space through multiple visualisation techniques. Findings From the temporal perspective, the evolution of online public opinion is closely related to the developmental dynamics of offline events. In comparison, public views and attitudes are more complex and diversified during the outbreak and diffusion periods. From the spatial perspective, the netizens in hotspot areas with higher discussion volume are more rational and prefer to track the whole process of event development, while the ones in coldspot areas with less discussion volume pay more attention to the expression of personal emotions. From the perspective of intertwined spatiotemporal, there are differences in the focus of attention and emotional state of netizens in different regions and time stages, caused by the specific situations they are in. Originality/value The situational awareness framework can shed light on the dynamic evolution of online public opinion from a multidimensional perspective, including temporal, spatial and spatiotemporal perspectives. It enables decision-makers to grasp the psychology and behavioural patterns of the public in different regions and time stages and provide targeted public opinion guidance measures and offline event governance strategies.

show abstract

Section: Topic Discovery Of Online Public Opinionmentioning

confidence: 99%

Constructing a spatiotemporal situational awareness framework to sense the dynamic evolution of online public opinion on social media

Li,

Zeng,

Sun

et al. 2023

View full text Add to dashboard Cite

show abstract

“…During the energy crisis in the 1960s, the term 'life cycle' was widely used in various fields, especially in politics, economy, environment, technology, society, and many other fields [55]. Online public opinions refer to a collection of information about a certain event which also arises and dies with the progress of the event [56]. One of the most influential division methods of crisis management is the Four-Stage Model of a Crisis Lifecycle: the prodromal stage, the acute stage, the chronic stage, and the resolution stage [57].…”

Section: Life Cycle Of Online Public Opinionsmentioning

confidence: 99%

Locked down in Wuhan: Exploring the evolution of public emotions during the COVID-19 pandemic (Preprint)

Shen¹,

Cao²,

Bi³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND In late December 2019, Wuhan Municipal Health Commission reported the first cases of SARS-CoV-2, the underlying virus that caused the devastating outbreak of the coronavirus (COVID-19). On 23 January 2020, the government of Wuhan announced a city-wide lockdown with the aim of controlling the spread of the virus. With outbreaks of COVID-19 around the world, lockdown restrictions are routinely imposed to limit the spread of the virus and reduce the strain on healthcare services. During periods of lockdown, social media has become the main channel for citizens to exchange information and communicate with friends and family. Public emotions and opinions are being generated and shared rapidly online with citizens using internet platforms to reduce anxiety and stress, and stay connected while isolated. OBJECTIVE This study aims to explore the regularity of emotional evolution by examining public emotions expressed in online discussions during the lockdown of Wuhan in January 2020. We divide the lockdown into different phases and analyze the distribution of emotions against different dimensions. Further, the temporal evolution of emotion and the topic-based emotional distribution during each phase of the Wuhan lockdown is determined. METHODS Data related to the Wuhan lockdown was collected from Sina Weibo, the most active microblogging site in China, by web crawler. In this study, the Ortony, Clore, and Collins (OCC) model, Word2Vec, and Bi-directional Long Short-Term Memory model were employed to determine emotional types, train vectorization of words, and identify each text emotion for the training set. Latent Dirichlet Allocation models were also employed to mine the various topic categories found in each phase, while topic emotional evolution was visualized. RESULTS Based on the OCC model, seven types of emotions were categorized to describe emotional distribution during the Wuhan lockdown: admiration, hope, joy, neutral, fear, reproach, and distress. Among these, admiration and reproach held the largest proportions of emotional expression. Further, expressions of emotion were significantly related to users’ gender, location, and whether or not their account was verified. The lockdown was divided into five phases, incubation phase, explosive phase, declining phase, stable phase, and unblocked phase, which showed citizens emotions transition from reproach and fear, through reproach and admiration, hope and admiration, to reproach and admiration, then to joy and admiration. Admiration and joy increased while fear declined. There were statistically significant correlations between different emotions within the subtle emotional categories. The topics showed that public attitudes towards the lockdown gradually improved. In addition, emotional evolution was influenced by topics, but not limited to them. CONCLUSIONS This study revealed insights into public emotions expressed on Sina Weibo during the lockdown of Wuhan in January 2020. Seven emotion categories were determined, providing governments with greater appreciation of citizen emotions to support them and develop appropriate policies to minimize stress and anxiety. The responses of the government of Wuhan were found to comfort citizens during lockdown which can be used as best practice or a case for other countries and regions affected by COVID-19 outbreaks. In addition, emergency agencies should pay continuous attention to citizens lives and psychological status post-pandemic.

show abstract

An Influence Prediction Model for Microblog Entries on Public Health Emergencies

Cited by 2 publications

References 36 publications

Constructing a spatiotemporal situational awareness framework to sense the dynamic evolution of online public opinion on social media

Constructing a spatiotemporal situational awareness framework to sense the dynamic evolution of online public opinion on social media

Locked down in Wuhan: Exploring the evolution of public emotions during the COVID-19 pandemic (Preprint)

Contact Info

Product

Resources

About