Characterizing the Spread of Exaggerated Health News Content over Social Media

Patro, Jasabanta; Baruah, Sabyasachee; Gupta, Vivek Kumar; Choudhury, Monojit; Goyal, Pawan; Mukherjee, Animesh

doi:10.1145/3342220.3344927

Cited by 8 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The association between death, funerals, and emotions or affective processes (Gortner and Pennebaker, 2003 ; Glasgow et al, 2014 ) led to the selection of affective processes for further evaluation. Previous studies also identified words expressing emotions or affect significantly that influence linguistic dimensions (Wardecker et al, 2017 ; Khalil et al, 2018 ; Patro et al, 2018 ). The present research aimed to explore the association between linguistic dimensions such as function, words, and affect.…”

Section: Methodsmentioning

confidence: 95%

Coronavirus Disease 2019: Exploring Media Portrayals of Public Sentiment on Funerals Using Linguistic Dimensions

2021

View full text Add to dashboard Cite

Funerals are a reflective practice to bid farewell to the departed soul. Different religions, cultural traditions, rituals, and social beliefs guide how funeral practices take place. Family and friends gather together to support each other in times of grief. However, during the coronavirus pandemic, the way funerals are taking place is affected by the country's rules and region to avoid the spread of infection. The present study explores the media portrayal of public sentiments over funerals. In particular, the present study tried to identify linguistic dimensions associated with lexical components of social processes, affective processes, fear, and disgust. An exhaustive search of newspaper coverage of funeral and related articles was made for a specific corona period. After an initial screening for the details and language used, a total of 46 newspaper articles on funerals were finalized for the analysis. Linguistic Inquiry and Word Count (LIWC) software was used to determine the association between linguistic dimensions of function words and words related to social and affective processes, as presented in the newspaper articles. Sentiment Analysis and Cognition Engine (SEANCE) was applied for the analysis of sentiment, social cognition, and social order. Bayesian correlation analysis and regression revealed positive and significant associations between function words and affective processes, between pronouns and social processes, and between negative adjectives and psychological processes of fear and disgust. Also, significant negative associations were found between polarity nouns and psychological processes of fear and disgust and between polarity verbs and psychological processes of fear and disgust. Bayes factor 10 provides strong evidence in favor of the study hypotheses. The media is influenced by the prevailing sentiments in society and reflects their perception of the current social order and beliefs. The findings provide a glimpse into the prevailing sentiment of society through the lens of media coverage. These understandings are expected to enhance our observations of how people express their feelings over the loss of their loved ones and help mental health professionals develop their therapeutic protocols to treat the coronavirus disease 2019 (COVID-19)-affected population.

show abstract

Section: Methodsmentioning

confidence: 95%

Coronavirus Disease 2019: Exploring Media Portrayals of Public Sentiment on Funerals Using Linguistic Dimensions

2021

View full text Add to dashboard Cite

show abstract

“…Exaggeration: Exaggeration can take different forms, such as the alteration of correlational statements into causal statements, change in explicitness and directness of included advice, or twisting of important experimental facts (Patro et al, 2018). Clickbait headlines are often modified to appear more negative than the actual article, exaggerate main points, or over-emphasize conflicts to attract more readers (Ecker et al, 2014).…”

Section: Data Representationmentioning

confidence: 99%

Untitled

2024

AJMMC

View full text Add to dashboard Cite

Reviewers' BoardClick HereviPresident's Message All ATINER's publications including its e-journals are open access without any costs (submission, processing, publishing, open access paid by authors, open access paid by readers etc.) and is independent of presentations at any of the many small events (conferences, symposiums, forums, colloquiums, courses, roundtable discussions) organized by ATINER throughout the year and entail significant costs of participating. The intellectual property rights of the submitting papers remain with the author. Before you submit, please make sure your paper meets the basic academic standards, which includes proper English. Some articles will be selected from the numerous papers that have been presented at the various annual international academic conferences organized by the different divisions and units of the Athens Institute for Education and Research. The plethora of papers presented every year will enable the editorial board of each journal to select the best, and in so doing produce a top-quality academic journal. In addition to papers presented, ATINER will encourage the independent submission of papers to be evaluated for publication. The current issue is the second of the tenth volume of the Athens Journal of Mass Media and Communications (AJMMC), published by the Mass Media & Communication Unit of ATINER.

show abstract

“…In the last two decades, there is a substantial increase in the number of publications in the domain of media manipulation and fake news [10], [11]. A number of tasks have been introduced since then such as fact checking [12]- [14], rumor detection [15], stance detection [16], assessing credibility [17], and exaggeration [18], [19]. Moreover, several datasets have been introduced for these tasks (see in particular the datasets on claim verification [16], [20]- [22], entire article verification [23] and verification of social media posts [24]- [26]).…”

Section: Related Workmentioning

confidence: 99%

Context-Aware Deep Markov Random Fields for Fake News Detection

Huu¹,

Berneman

Patro

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Fake news is a serious problem, which has received considerable attention from both industry and academic communities. Over the past years, many fake news detection approaches have been introduced, and most of the existing methods rely on either news content or the social context of the news dissemination process on social media platforms. In this work, we propose a generic model that is able to take into account both the news content and the social context for the identification of fake news. Specifically, we explore different aspects of the news content by using both shallow and deep representations. The shallow representations are produced with word2vec and doc2vec models while the deep representations are generated via transformer-based models. These representations are able to jointly or separately address four individual tasks, namely bias detection, clickbait detection, sentiment analysis, and toxicity detection. In addition, we make use of graph convolutional neural networks and mean-field layers in order to exploit the underlying structural information of the news articles. That way, we are able to take into account the inherent correlation between the articles by leveraging their social context information. Experiments on widely-used benchmark datasets indicate the effectiveness of the proposed method.

show abstract

Characterizing the Spread of Exaggerated Health News Content over Social Media

Abstract: categories like 'bio', 'health', 'body' and 'negative emotion' are more pronounced in the tweets posted by the users in the latter class. As a final step we use these observations as features and automatically classify the two groups achieving an F1-score of 0.83.

Cited by 8 publications

References 9 publications

Coronavirus Disease 2019: Exploring Media Portrayals of Public Sentiment on Funerals Using Linguistic Dimensions

Coronavirus Disease 2019: Exploring Media Portrayals of Public Sentiment on Funerals Using Linguistic Dimensions

Untitled

Context-Aware Deep Markov Random Fields for Fake News Detection

Contact Info

Product

Resources

About