Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter

By Svitlana Volkova, Kyle Shaffer, Jin Yea Jang, Nathan Oken Hodas. Annual Meeting of the Association for Computational Linguistics, 2017

322 citations recorded by the source corpus.

Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that “made-up news” has caused a “great deal of confusion” about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability. In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.

Subfields: Artificial Intelligence, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/081d25e020c8de36fc16d0e1b526b4dfd156fc83

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

Social Chemistry 101: Learning to Reason about Social and Moral Norms (2020, background): “Commonly used for coarse-grained analyses of morality in text (Fulgoni et al., 2016; Volkova et al., 2017; Weber et al., 2018), Graham et al. (2009) introduce the Moral Foundations lexicon, a dictionary of morality-evoking words (later extended by Rezapour et al., 2019).”
DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification (2020, background): “…claim veri-ﬁcation could be divided into two categories: the ﬁrst is that the methods relying on deep neural networks learn credibility indicators from claim content and auxiliary relevant articles or comments (i.e., responses) (Volkova et al., 2017; Rashkin et al., 2017; Dungs et al., 2018).”
A survey on fake news and rumour detection techniques (2019, methodology): “These linguistic cues, in addition to other features, have been successfully implemented in numerous approaches concerning fake news and rumour detection [15, 38, 39, 63, 76, 78, 95, 108].”
DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning (2018, methodology): “Approaches like (Castillo et al., 2011; Qazvinian et al., 2011; Yang et al., 2012; Xu and Zhao, 2012; Gupta et al., 2013; Zhao et al., 2015; Volkova et al., 2017) propose supervised methods for detecting deceptive content in social media platforms like Twitter, Sina Weibo, etc. Similarly,…”
The Limitations of Stylometry for Detecting Machine-Generated Fake News (2019, background): “…and the increasing interest in fake news, recent studies applied stylometry on entire news articles (Pisarevskaya 2017), short news reports (Pérez-Rosas et al. 2018), fact and political statements (Nakashole and Mitchell 2014; Rashkin et al. 2017) and posts in social media (Volkova et al. 2017).”
Multimodal Fusion with Co-Attention Networks for Fake News Detection (2021, background): “Textual features are extracted from text content, including statistical features, such as the number of paragraphs in the text (Volkova et al., 2017), the percentage of negative words (Potthast et al., 2017; Bond et al., 2017), the number of punctuation and emojis (Castillo et al., 2011), and…”
Fake News: A Survey of Research, Detection Methods, and Opportunities (2018, background): “…news studies is still in its early stages with only a limited number of such studies [Bond et al. 2017; Pisarevskaya 2015; Potthast et al. 2017; Volkova et al. 2017], deception analysis and detection has long been an active area of research and has focused on the general style of deceptive…”
Supervised Learning for Fake News Detection (2019, methodology): “io/en/dev/), we compute subjectivity and sentiment scores of a text as explored in previous efforts.(4)”
Combating Fake News (2019, background): “A specific variant called Long Short-TermMemory (LSTM) [42], which alleviates some of the training difficulties in RNN, is often used due to the its ability to effectively capture long-range dependencies in the text and has been applied to fake news detection, similarly to the use of convolutional n”