The Lie Detector: Explorations in the Automatic Recognition of Deceptive Language

By Rada Mihalcea, Carlo Strapparava. Annual Meeting of the Association for Computational Linguistics, 2009

384 citations recorded by the source corpus.

In this paper, we present initial experiments in the recognition of deceptive language. We introduce three data sets of true and lying texts collected for this purpose, and we show that automatic classification is a viable technique to distinguish between truth and falsehood as expressed in language. We also introduce a method for class-based feature analysis, which sheds some light on the features that are characteristic for deceptive text.

Subfields: Artificial Intelligence, Social Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/50d6a8834013b29927c708c556baee06ce94337b

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 Social Psychology

In Signal Processing

Citations in the corpus

“Liar, Liar Pants on Fire”: A New Benchmark Dataset for Fake News Detection (2017, background): “The broadly-related problem of deception detection (Mihalcea and Strapparava, 2009) is not new to the natural language processing community.”
Deception Detection using Real-life Trial Data (2015, methodology): “Research work has relied on the Linguistic Inquiry and Word Count (LIWC) lexicon [34] to build deception models using machine learning approaches [28, 4] and showed that the use of psycholinguistic information was helpful for the automatic identiﬁcation of deceit.”
Combating Fake News (2019, methodology): “2 trained an SVM classifier, and found PCFG features used with n-gram features to be more beneficial than POS tags with n-grams in classifying fake texts from hotel reviews and lie detection datasets [67, 77]. Feng et al. 2012 noted that of the four variants of production rules, the ones with the te”
Linguistic Cues to Deception and Perceived Deception in Interview Dialogues (2018, background): “Several studies use a fake opinion paradigm for collecting data, instructing subjects to write or record deceptive and truth-ful opinions about controversial topics such as the death penalty or abortion, or about a person that they like/dislike (Newman et al., 2003; Mihalcea and Strapparava, 2009).”
Divide and Conquer: Crowdsourcing the Creation of Cross-Lingual Textual Entailment Corpora (2011, background): “posed so far rely on post hoc verification to filter out undesired low-quality data (Mrozinski et al., 2008; Mihalcea and Strapparava, 2009; Wang and Callison-Burch, 2010).”
Automated Crowdturfing Attacks and Defenses in Online Review Systems (2017, methodology): “The research community has started to explore the possibility of automating the detection process by building an AI-assisted fact-checking pipeline [41, 72, 76].”
Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking (2017, background): “Linguistic aspects deception detection has been well-studied in a variety of NLP applications (Ott et al., 2011; Mihalcea and Strapparava, 2009; Jindal and Liu, 2008; Girlea et al., 2016; Zhou et al., 2004).”
Identifying fake Amazon reviews as learning from crowds (2014, background): “But like all work on deceptive language (computational or otherwise) (Newman et al., 2003; Strapparava and Mihalcea, 2009), such works suffer from a serious problem: the lack of a gold standard containing ‘real life’ examples of deceptive uses of language.”
Automatic deception detection in Italian court cases (2013, methodology): “As a result, many if not most studies in the area, and in particular the just mentioned papers proposing computational techniques for deception detection, rely on data collected in laboratory conditions (Newman et al. 2003; Strapparava and Mihalcea 2009).”
CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text (2014, result): “Our results are comparable with the state-of-the-art results of Mihalcea and Strapparava (2009) for English opinion texts.”
What Online Reviewer Behaviors Really Matter? Effects of Verbal and Nonverbal Behaviors on Detection of Fake Online Reviews (2016, positive): “0),(5) which provides easy-to-use interfaces to over fifty corpora and lexical resources such as WordNet, a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, and wrappers for industrial-strength natural language processing librar”
Estimating the prevalence of deception in online review communities (2012, background): “Previous work has shown that Support Vector Machines (SVM) trained on n-gram features perform well in deception detection tasks [8, 13, 15].”
Preserving integrity in online social networks (2020, background): “In the case of identifying deceptive language, Mihalcea and Strapparava [77] analyzed the counts of certain words in text.”
What Yelp Fake Review Filter Might Be Doing? (2013, background): “Also related is the task of psycholinguistic deception detection which investigates lying words (Hancock et al., 2008; Newman et al. 2003), untrue views (Mihalcea and Strapparava (2009), computer-mediated deception in roleplaying games (Zhou et al., 2008), etc.”