An Improving Deception Detection Method in Computer-Mediated Communication

Abstract

<p>Online deception is disrupting our daily life, organizational process, and even national security. Existing deception detection approaches followed a traditional paradigm by using a set of cues as antecedents, and used a variety of data sets and common classification models to detect deception, which were demonstrated to be an accurate technique, but the previous results also showed the necessity to expand the deception feature set in order to improve the accuracy. In our study, we propose a novel feature selection method of the combination of CHI statistics and hypothesis testing, and achieve the accuracy level of 86% and F-measure of 0.84 by using the novel feature sets and SVM classification models, which exceeds the previous experiment results.</p

Automatic deception detection: Methods for finding fake news

“…In this method, any resolution of ambiguous word sense remains nonexistent (Larcker & Zakolyukina ). Many deception detection researchers have found this method useful in tandem with different, complementary analysis (Zhang, Fan, Zeng & Liu, ; Lary, Nikitov & Stone, 2010; Ott, Cardi, & Hancock, 2013), several of which are discussed in the remainder of this proposal.…”

“…Sets of word and category frequencies are useful for subsequent automated numerical analysis. One common use is for the training of “classifiers” as in Support Vector Machines (SVM) (Zhang et al, ) and Naïve Bayesian models (Oraby et al, ). Simply put, when a mathematical model is sufficiently trained from pre‐coded examples in one of two categories, it can predict instances of future deception on the basis of numeric clustering and distances.…”

Challenges in the use of social media data for the next generation analyst

“…40 In this regard, studies have begun to recognize to the need to expand the feature sets of linguistic cues defining "deceptive" or "truthful" texts, and move beyond lexical frequencies alone to consideration of stylistic, 41 syntactic and discursivestructural features. 42,43 Awareness of the contextuality of deception leads to reconsiderations of the way deception detection might be theorized. Li and Santos provide one example as they move the scope of detection beyond an individual text to social networks.…”

TALIP Perspectives, Guest Editorial Commentary

“…Acknowledging deception detection is in its initial stages for Chinese texts. Zhang et al [2012] follow the traditional paradigm and improve on their feature selection method with 86% accuracy results. An analysis of the impressive jump in Zhang et al's [2012] success rates is in order, preferably by native speakers.…”