No abstract

No abstract

PurposeThe COVID-19 pandemic has spurred a concurrent outbreak of false information online. Debunking false information about a health crisis is critical as misinformation can trigger protests or panic, which necessitates a better understanding of it. This exploratory study examined the effects of debunking messages on a COVID-19-related public chat on WhatsApp in Singapore.Design/methodology/approachTo understand the effects of debunking messages about COVID-19 on WhatsApp conversations, the following was studied. The relationship between source credibility (i.e. characteristics of a communicator that affect the receiver's acceptance of the message) of different debunking message types and their effects on the length of the conversation, sentiments towards various aspects of a crisis, and the information distortions in a message thread were studied. Deep learning techniques, knowledge graphs (KG), and content analyses were used to perform aspect-based sentiment analysis (ABSA) of the messages and measure information distortion.FindingsDebunking messages with higher source credibility (e.g. providing evidence from authoritative sources like health authorities) help close a discussion thread earlier. Shifts in sentiments towards some aspects of the crisis highlight the value of ABSA in monitoring the effectiveness of debunking messages. Finally, debunking messages with lower source credibility (e.g. stating that the information is false without any substantiation) are likely to increase information distortion in conversation threads.Originality/valueThe study supports the importance of source credibility in debunking and an ABSA approach in analysing the effect of debunking messages during a health crisis, which have practical value for public agencies during a health crisis. Studying differences in the source credibility of debunking messages on WhatsApp is a novel shift from the existing approaches. Additionally, a novel approach to measuring information distortion using KGs was used to shed insights on how debunking can reduce information distortions.

PurposeThis study aims to investigate three common approaches – quantitative blog features analysis, content analysis, and community identification – to detect influence in the blogosphere (i.e. among blog posts).Design/methodology/approachQuantitative analysis of blog features, together with manual sentiment and agreement analysis and community identification, were performed on blog postings and their content. Correlation studies of the selected influential variables were conducted to determine the effectiveness of each variable.FindingsAgreement expressed by the linking blogger with the linked blogger, similar sentiments expressed by both bloggers on common topics, and community identity are statistically significant features for detecting influence in the linked blogs.Research limitations/implicationsA small data set of 196 blog posting pairs was used for the study as the blog features and content are analysed manually. Nonetheless statistical analysis on the data set identified significant features that could be used in future studies to automate the influence detection process.Practical implicationsKnowing the effects of blog features and content analysis in detecting influence among blog posts allows a better influence detection method to determine the main chain of information propagation within the blogosphere and the identities of influential bloggers.Originality/valueThe approach of using blog features, content analysis, and community identity provides a comprehensive evaluation of influence in the blogosphere. Unlike previous content analysis approaches that measure document similarity (i.e. common terms) between linked blog posts, our study applies sentiment and agreement analysis to consider the context of the whole blog post content.

No abstract