Automatic deception detection: Methods for finding fake news

By Niall Conroy, Victoria L. Rubin, Yimin Chen. ASIS&T Annual Meeting, 2015

995 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/939feec48ae1abb222cf9881932680b7ec3c68a7

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

1. Xinyi Zhou
2. Neema Kotonya
3. Jiliang Tang
4. Francesca Toni
5. Erik Cambria
6. Rada Mihalcea
7. Kai Shu
8. Huan Liu

In Information Systems

1. Xinyi Zhou
2. Kai Shu
3. Huan Liu
4. Jiliang Tang
5. Francesca Toni
6. Neema Kotonya
7. Suhang Wang
8. Sabrine Amri

In Sociology and Political Science

1. Xinyi Zhou
2. Kai Shu
3. Neema Kotonya
4. Francesca Toni
5. Huan Liu
6. Suhang Wang
7. Dongwon Lee
8. Sabrine Amri

Citations in the corpus

• Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter (2017, background): “On the other extreme is satire, e.g., @TheOnion, where the writer’s primary purpose is not to mislead the reader, but rather entertain or criticize (Conroy et al., 2015).”
• Fake news detection using naive Bayes classifier (2017, background): “In [3] the authors provide a general overview of the available techniques for the matter.”
• Fake News Detection on Social Media: A Data Mining Perspective (2017, result): “This definition has been widely adopted in recent studies [57; 17; 62; 41].”
• “Fake News” Is Not Simply False Information: A Concept Explication and Taxonomy of Online Content (2019, background): “For example, Allcott and Gentzkow (2017) and Conroy et al. (2015) argue that “fake news” should be defined as news articles that could mislead readers and are intentionally and verifiably false.”
• Explaining Credibility in News Articles using Cross-Referencing (2019, background): “Consequently, the credibility judgment is only aided by the system and not replacing the reader’s judgment [5].”
• Fake news, disinformation and misinformation in social media: a review (2023, background): “…et al. 2022; Allen et al. 2020; Allcott and Gentzkow 2017; Shu et al. 2017; Sharma et al. 2019; Zhou and Zafarani 2020; Zhang and Ghorbani 2020; Conroy et al. 2015; Celliers and Hattingh 2020; Nakov 2020; Shu et al. 2020c; Jin et al. 2016; Rubin et al. 2016; Balmas 2014; Brewer et al. 2013;…”
• Automatic Detection of Fake News (2017, background): “, ”Barack Obama assumed office on a Tuesday”) to assess the truthfulness of their claims (Conroy et al., 2015).”
• Fake News Detection Using Machine Learning Ensemble Methods (2020, background): “At conceptual level, fake news has been classified into different types; the knowledge is then expanded to generalize machine learning (ML) models for multiple domains [10, 15, 16].”
• A survey on fake news and rumour detection techniques (2019, neutral): “Several recent studies, such as [24], have adopted this definition.”
• Explainable Automated Fact-Checking: A Survey (2020, background): “(2019) X Gad-Elrab et al. (2019) X X X X Ahmadi et al.”
• NewsEmbed: Modeling News through Pre-trained Document Representations (2021, methodology): “People use traditional approaches such as Naive Bayes and Support Vector Machines [15, 54], and neural network approaches such as LSTM [51] and CNN [18].”
• A Survey of Fake News (2020, background): “These features describe content style from (at least) four language levels: lexicon , syntax , discourse , and semantic [Conroy et al. 2015].”
• Detecting Fake News in Social Media Networks (2018, background): “For content publishers, however, more clicks translate into more revenues as the commercial aspect of using online advertisements is highly contingent on web tra ffi c [12].”
• Science audiences, misinformation, and fake news (2019, background): “org have also emerged to boost people’s abilities to debunk misinformation (35), and efforts are ongoing to offer reliable, automated “deception detection” for both text and images (36, 37).”
• Supervised Learning for Fake News Detection (2019, methodology): “1) Language Features (Syntax): Sentence-level features, including bag-of-words approaches, “n-grams” and part-of-speech (POS tagging) were explored in previous efforts as features for fake news detection.(2,6) Here, we implemented 31 features from this set including number of words and syllables per”