The use of alluring headlines (clickbait) to tempt the readers has become a growing practice nowadays. For sake existence in highly competitive media industry, most on-line including mainstream ones, have started following this practice. Although wide-spread clickbait makes reader's reliability on vulnerable, large scale analysis reveal fact is still absent. In paper, we analyze 1.67 million Facebook posts created by 153 organizations understand extent practice, its impact and user...

The spread of 'fake' health news is a big problem with even bigger consequences. In this study, we examine collection health-related articles published by reliable and unreliable media outlets. Our analysis shows that there are structural, topical, semantic patterns which different in contents from Using machine learning, leverage these build classification models to identify the source (reliable or unreliable) article. model can predict an article F-measure 96%. We argue findings study will...

Studies show that users do not reliably click more often on headlines classified as clickbait by automated classifiers. Is this because the linguistic criteria (e.g., use of lists or questions) emphasized classifiers are psychologically relevant in attracting interest, their classifications confounded other unknown factors associated with assumptions classifiers? We address these possibilities three studies—a quasi-experiment using machine-learning models (Study 1), a controlled experiment...

The use of alluring headlines (clickbait) to tempt the readers has become a growing practice nowadays. For sake existence in highly competitive media industry, most on-line including mainstream ones, have started following this practice. Although wide-spread clickbait makes reader's reliability on vulnerable, large scale analysis reveal fact is still absent. In paper, we analyze 1.67 million Facebook posts created by 153 organizations understand extent practice, its impact and user...

The use of tempting and often misleading headlines (clickbait) to allure readers has become a growing practice nowadays among the media outlets. widespread clickbait risks reader’s trust in media. In this paper, we present BaitBuster, browser extension social bot based framework, that detects clickbaits floating on web, provides brief explanation behind its decision, regularly makes users aware potential clickbaits.

Verifying a factual claim made by public figures, aka fact-checking, is common task of the journalists in newsrooms. One critical challenge that fact-checkers face is-they have to swift through large amount text find claims are check-worthy. While there exist some computational methods for automating fact-checking process, little research has been done on how system should combine such techniques with visualizations assist fact-checkers. ClaimViz visual analytic integrates natural language...

Most scholarly discussions around ridesharing applications center on the experiences of drivers and riders (passengers), thus role owners cars, if they are different from drivers, remain understudied. However, in many countries Global South, car often tensions between them shape experience with these apps those countries. In this paper, we address issue based our interview-based study Dhaka, Bangladesh, which incorporates semi-structured interviews 31 Uber 10 owners. From interviews,...

In this study, we closely look at the use of social media contents as source or reference in U.S. news media. Specifically, examine about 60 thousand articles published within 5 years period 2013-2017 by 153 outlets and analyze content compared to other sources. We designed a extraction algorithm investigated extent nature usage across different topics. Our results show that uses almost doubled five years. Unreliable rely on more than mainstream Both unreliable sites prefer Twitter Facebook...

Media outlets play crucial roles in disseminating health information. Previous studies have examined how journalism is practiced by reliable and unreliable media outlets. However, most of the existing works are conducted over a relatively small set samples. In this study, we investigate large collection (about 30 thousand) health-related news articles which were published 29 20 identify several differences practice. Our analysis shows that there significant structural, topical, semantic...

In the digital age, prevalence of misleading news headlines poses a significant challenge to information integrity, necessitating robust detection mechanisms. This study explores efficacy Large Language Models (LLMs) in identifying versus non-misleading headlines. Utilizing dataset 60 articles, sourced from both reputable and questionable outlets across health, science & tech, business domains, we employ three LLMs- ChatGPT-3.5, ChatGPT-4, Gemini-for classification. Our analysis reveals...

Many people find it difficult to comprehend basic charts on the web, let alone make effective decisions from them. To address this gap, several ML models aim automatically detect useful insights and narrate them in a simpler textual format. However, most of these solutions can only factual (a.k.a. descriptive insights) that are already present chart, which may help with chart comprehension, but not decision-making. In work, we study whether more advanced predictive investigative users...