The Location of Maximum Emotion in Deceptive and Truthful Texts

Abstract

Meta-analytic evidence suggests that verbal patterns of emotion betray deceit, but it is presently unclear whether the location of maximum emotion in lies and truths matters to reveal deception. We contribute to the deception literature by offering analyses at the sentence level to locate where emotion is most pronounced in deceptive versus truthful texts. Using two public data sets—news articles (Study 1) and hotel reviews (Study 2)—we found that maximum emotion occurs toward the beginning of deceptive texts while maximum emotion appears later for truthful texts. In addition to demonstrating the effect across diverse settings, we used two different measurements for emotion and separated the results by valence, replicating the maximum emotion effect each time. The predictive nature of maximum affect ranged from 54% to 56% across data sets, a rate consistent with most deception studies using 50-50 lie–truth base rates. Implications for future research and deception theory are discussed.

Deception detection based on the linguistic style of honest and dishonest stories

“…Traits of personality, likewise kind of witness, are variables that have been considered as relevant factors in deception detection, but they have not been studied frequently (Gamer and Ambach, 2014; Elaad and Reizer, 2015; Carvajal-Builes and Barreto, 2020). By another hand, some studies have shown that emotional expression could vary depend on the part of the text; it means, at the beginning of the stories, probably there would appear more emotional words than at the end (Sepehri et al , 2021).…”

The Power of Indirect Appeals in Peer‐to‐Peer Fundraising: Why “S/He” Can Raise More Money for Me Than “I” Can For Myself

“…The consistency (or perhaps the contrast) between written narratives and their accompanying images may offer fruitful insights. Lastly, research on deception finds that strong‐emotion content tends to be situated early in fake (vs. late in genuine) news articles and online reviews (Sepehri, Markowitz, & Duclos, 2020). On this basis, future research may explore whether the location of strong emotions in charitable appeals (early vs. late) sways donor generosity.…”

Linguistic Markers of Inherently False AI Communication and Intentionally False Human Communication: Evidence from Hotel Reviews

“…LIWC is a tool that counts words as a percentage of the total word count per text against its internal dictionary of social (e.g., words related to friends or family), psychological (e.g., words related to emotion), and part of speech dimensions (e.g., pronouns, prepositions). LIWC is a gold-standard text analysis program that has been applied to the datasets acquired for the current work (Ott et al, 2011;Sepehri et al, 2020) and a wealth of other studies in the social sciences (Boyd & Schwartz, 2021;Tausczik & Pennebaker, 2010). Coh-Metrix is another popular text analysis program and was used to calculate structural properties of texts in this paper (e.g., readability) for hotel reviews that originated as text files (McNamara et al, 2014).…”