A Parsimonious Language Model of Social Media Credibility Across Disparate Events

Mitra, Tanushree; Wright, G. Payling; Gilbert, Éric

doi:10.1145/2998181.2998351

Cited by 65 publications

(48 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This absence of interaction could be caused by participants' prior perceptions of the credibility of the media. Mitra, Wright, and Gilbert (2017) examined language factors as predictors of media credibility, finding that features of the language used in social media, such as subjectivity, modalities, negations, exclusions, conjunctions, quotes, hedges, boosters, evidentiality, anxiety, positive emotions, and negative emotions could affect the level of credibility perceived by participants. As a consequence, more than categorizing the language type into formal or informal, deeper linguistic analysis is also needed to create conditions where participants' perceptions of media credibility matches the syntax used.…”

Section: Discussionmentioning

confidence: 99%

Should I Trust Social Media? How Media Credibility and Language Affect False Memory

Maulina

Hakim

Arasy

et al. 2020

jpsi

View full text Add to dashboard Cite

This study examined the influence of credibility and .language in Internet-based media on false memory. A randomized factorial 2 (media credibility) × 2 (language) experimental design was conducted with 106 college students. The two groups of media credibility consisted of social media (LINE) and non-social media (detik.com), while media language consisted of formal and informal language. A confidence test was used to measure false memory. A two-factor ANOVA showed that media credibility significantly affects false memory. Participants in the detik.com group were more confident in the information received and had greater false memory than the LINE group. However, no significant effect of language was found, and no significant interaction effect between media credibility and language on false memory was found. This study suggests that individuals should be cautious when reading information on non-social media platforms, as individuals tend to place more confidence on the source, leading to greater false memory.

show abstract

Section: Discussionmentioning

confidence: 99%

Should I Trust Social Media? How Media Credibility and Language Affect False Memory

Maulina

Hakim

Arasy

et al. 2020

jpsi

View full text Add to dashboard Cite

show abstract

“…Where much of the prior research has aimed to label individual social media posts or the claims made on social media by veracity [25-29], we instead labeled Web pages shared on social media using a credibility appraisal checklist extended from previously validated instruments to be appropriate to vaccine-related communications [21,22]. In other related work, Mitra et al [51] examined the linguistic features in social media posts that influenced perceptions of credibility. Although we did not examine the linguistic features of the tweets that included links to low-credibility information, it would be interesting to connect these ideas to better understand whether they influence user behavior—making users more likely to engage with a tweet by URL access, replying, and sharing.…”

Section: Discussionmentioning

confidence: 99%

Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study

Shah¹,

Surian²,

Dyda³

et al. 2019

J Med Internet Res

View full text Add to dashboard Cite

BackgroundTools used to appraise the credibility of health information are time-consuming to apply and require context-specific expertise, limiting their use for quickly identifying and mitigating the spread of misinformation as it emerges.ObjectiveThe aim of this study was to estimate the proportion of vaccine-related Twitter posts linked to Web pages of low credibility and measure the potential reach of those posts.MethodsSampling from 143,003 unique vaccine-related Web pages shared on Twitter between January 2017 and March 2018, we used a 7-point checklist adapted from validated tools and guidelines to manually appraise the credibility of 474 Web pages. These were used to train several classifiers (random forests, support vector machines, and recurrent neural networks) using the text from a Web page to predict whether the information satisfies each of the 7 criteria. Estimating the credibility of all other Web pages, we used the follower network to estimate potential exposures relative to a credibility score defined by the 7-point checklist.ResultsThe best-performing classifiers were able to distinguish between low, medium, and high credibility with an accuracy of 78% and labeled low-credibility Web pages with a precision of over 96%. Across the set of unique Web pages, 11.86% (16,961 of 143,003) were estimated as low credibility and they generated 9.34% (1.64 billion of 17.6 billion) of potential exposures. The 100 most popular links to low credibility Web pages were each potentially seen by an estimated 2 million to 80 million Twitter users globally.ConclusionsThe results indicate that although a small minority of low-credibility Web pages reach a large audience, low-credibility Web pages tend to reach fewer users than other Web pages overall and are more commonly shared within certain subpopulations. An automatic credibility appraisal tool may be useful for finding communities of users at higher risk of exposure to low-credibility vaccine communications.

show abstract

“…Ironically, it seems that using too few words discourages rather than encourages sharing of health messages. Shorter messages may not provide enough detail for readers to determine content credibility, as previous work has shown that simply being from a reputable source does not offset credibility-harming effects in the message itself [27].…”

Section: Discussionmentioning

confidence: 99%

HIV messaging on Twitter

Lohmann

White

Zuo

et al. 2018

Aids

View full text Add to dashboard Cite

Objectives: Social media messages have been increasingly used in health campaigns about prevention, testing, and treatment of HIV. We identified factors leading to the retransmission of messages from expert social media accounts to create data-driven recommendations for online HIV messaging. Design and Methods: We sampled 20,201 HIV-related tweets (posted between 2010 and 2017) from 37 HIV experts. Potential predictors of retransmission were identified based on prior literature and machine learning methods and were subsequently analyzed using multilevel negative binomial models. Results: Fear-related language, longer messages, and including images (e.g., photos, gif, or videos) were the strongest predictors of retweet counts. These findings were similar for messages authored by HIV experts as well as messages retransmitted by experts but created by non-experts (e.g., celebrities or politicians). Conclusions: Fear appeals affect how much HIV messages spread on Twitter, as do structural characteristics like the length of the tweet and inclusion of images. A set of five data-driven recommendations for increasing message spread is derived and discussed in the context of current CDC social media guidelines.

show abstract

A Parsimonious Language Model of Social Media Credibility Across Disparate Events

Cited by 65 publications

References 48 publications

Should I Trust Social Media? How Media Credibility and Language Affect False Memory

Should I Trust Social Media? How Media Credibility and Language Affect False Memory

Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study

HIV messaging on Twitter

Contact Info

Product

Resources

About