Comparing features of fabricated and legitimate political news in digital environments (2016‐2017)

Abstract

With the problem of ‘fake news’ in the digital media, there are efforts at creation of awareness, automation of ‘fake news’ detection and news literacy. This research is descriptive as it pulls evidence from the content of online fabricated news for the features that distinguish fabrications from the legitimate political news around the time of the U.S. Presidential Elections (276 articles in total, from November 2016 ‐ June 2017). Certain stylistic and psycho‐linguistic features of fabrications may be apparent to the news readers: fewer words and paragraphs but longer paragraphs, more slangs, swear words and affective words in the stories. Such features could be used for educational information literacy campaigns for spotting so‐called ‘fake news’. Other informative features may require specialized analytical tools (or further training) to notice the presence of more words, punctuation marks, demonstratives and emotiveness in fabrications but fewer verifiable facts (or named entities) in their headlines.

Disinformation and misinformation triangle

“…2. For a database of 137 political falsified news (matched to their likely 137 legitimate counterpart from which each news originated), see “POLIT-FALSE-n-LEGIT NEWS DB 2016-2017.” Available at: http://victoriarubin.fims.uwo.ca/news-verification/access-polit-false-n-legit-news-db-2016-2017/ (accessed December 15, 2018). The statistical differences in linguistic and stylistic features are described in Asubiaro and Rubin (2018).…”

What Does Fake Look Like? A Review of the Literature on Intentional Deception in the News and on Social Media

“…Editors of trustworthy sources are possibly quite rigorous about removing language that seems too personal, while such processes do not play a role in the production of fabricated news items (see also the findings about source use). In a similar vein, Asubiaro and Rubin (2018) find that the use of (all types of) pronouns is typically higher in deceptive news. Applied to social media, the aforementioned study by Van Der Zee et al (2018) finds similar patterns (for third-person pronouns) for tweets by former President Trump that were established to be deceptive by The Washington Post.…”

“…To develop methods of automated detection, scholars rely on benchmark labeled datasets (e.g., PolitiFact) that contain truthful and deceptive news content that has been fact-checked for its veracity. Based on such datasets, machine learning models are developed to automatically detect disinformation based on linguistic features, with varying degrees of success (e.g., Asubiaro and Rubin 2018;Wang 2017). Horne and Adali (2017), for example, use three separate datasets to study the linguistic features of real news, fake news, and satire.…”

“…In general, the headlines of intentionally deceptive news items tend to be eyecatching, with a propensity for exaggeration, sensationalism, and scaremongering (Chen, Conroy, and Rubin 2015;Potthast et al 2016;Sahoo and Gupta 2021;Shu et al 2017;Tucker et al 2018). In addition, these headlines tend to be longer (Asubiaro and Rubin 2018 ;Liu et al 2019), using more capitalized words, proper nouns and verb phrases. By doing so, titles of fabricated news items try to get many points across, while titles of truthful texts most often opt for brief and general summary statements (Horne and Adali 2017, 764).…”

“…However, it is reasonable to assume that the content of deceptive information is structurally different compared to fully correct information. For example, work in the field of linguistics suggests that deceptive language contains more tentative, angry, and emotional words than truthful language does (Asubiaro and Rubin 2018).…”