Syntactic Stylometry for Deception Detection

By Song Feng, Ritwik Banerjee, Yejin Choi. Annual Meeting of the Association for Computational Linguistics, 2012

559 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e5cee4d89c17d307d5c2bdde60dbaa4773720733

How researchers see this paper

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

Citations in the corpus

What Yelp Fake Review Filter Might Be Doing? (2013, methodology): “Our study shows that although linguistic methods in (Ott et al., 2011; Feng et al., 2012b) reported very high (90”
Graph based anomaly detection and description: a survey (2014, methodology): “[Feng et al., 2012b] study the distributional patterns in rating behaviors, while [Xie et al., 2012] focus on temporal reviewing behaviors to detect fake review(er)s.”
Automatic Detection of Fake News (2017, background): “CFG-based features have been previously shown to be useful for linguistic deception detection (Feng et al., 2012).”
The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task (2017, background): “It is influenced by personal factors such as age and gender (Schler et al., 2006), by personality traits such as agreeableness and openness (Ireland and Mehl, 2014), as well as by mental states such as sentiment (Davidov et al., 2010), sarcasm (Tsur et al., 2010), and deception (Feng et al., 2012).”
What Online Reviewer Behaviors Really Matter? Effects of Verbal and Nonverbal Behaviors on Detection of Fake Online Reviews (2016, methodology): “Supervised machine learning has been the dominant approach to detecting fake reviews [10, 12, 14, 32, 46, 49] where fake review detection is viewed as a binary classification problem—a target review will be labeled as either an authentic review or a fake review.”
Linguistic Cues to Deception and Perceived Deception in Interview Dialogues (2018, background): “Syntactic features such as part of speech tags have also been found to be useful for structured data (Ott et al., 2011; Feng et al., 2012).”
Sentiment Analysis: An Overview from Linguistics (2016, unknown): “Some of the research, however, relies on the same principles that are deployed in authorship attribution: genre identification through part of speech distribution, similarity of linguistic patterns, and style characteristics of the text (Feng et al 2012, Ott et al 2011).”
Combating Fake News (2019, methodology): “Feng et al. 2012 noted that of the four variants of production rules, the ones with the terminal nodes included were more powerful since they contained word based information in addition to syntax information.”
Fake It Till You Make It: Reputation, Competition, and Yelp Review Fraud (2016, unknown): “There is now extensive evidence that consumer reviews have a causal impact on demand in industries ranging from books to restaurants to hotels, among others (Chevalier and Mayzlin (2006), Luca (2011), Ghose et al. (2012)). However, there is considerably less agreement about whether reviews contain t”
Collective Opinion Spam Detection: Bridging Review Networks and Metadata (2015, background): “At a high level, those can be categorized as linguistic approaches [6, 21, 22] that analyze the language patterns of spam vs.”
Beyond News Contents: The Role of Social Context for Fake News Detection (2017, background): “ent based models include i) knowledgebased: using external sources to fact-checking claims in news content [17, 37], and 2) style-based: capturing the manipulators in writing style, such as deception [7, 27] and non-objectivity [24]. For example, Potthast et al. [24] extracted various style features”
“Liar, Liar Pants on Fire”: A New Benchmark Dataset for Fake News Detection (2017, background): “Recent studies have also proposed stylometric (Feng et al., 2012), semi-supervised learning (Hai et al.”
Opinion Fraud Detection in Online Reviews by Network Effects (2013, background): “A large body of work on fraud detection relies on review text information (Jindal and Liu 2008; Ott et al. 2011; Feng, Banerjee, and Choi 2012) or behavioral evidence (Lim et al. 2010; Xie et al. 2012; Feng et al. 2012), and ignore the connectivity structure of review data.”
Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter (2017, methodology): “Syntax and grammar features have been predictive of deception in the product review domain (Feng et al., 2012; Pérez-Rosas and Mihalcea, 2015).”