Opinion Mining and Sentiment Analysis
Foundations and Trends in Information Retrieval
Decision support for determining veracity via linguistic-based cues
Decision Support Systems
An investigation of data and text mining methods for real world deception detection
Expert Systems with Applications: An International Journal
Adaptive context modeling for deception detection in emails
MLDM'11 Proceedings of the 7th international conference on Machine learning and data mining in pattern recognition
"I don't know where he is not": does deception research yet offer a basis for deception detectives?
EACL 2012 Proceedings of the Workshop on Computational Approaches to Deception Detection
| Hi-index | 0.00 |
The present study investigates changes in both the sender's and the target's linguistic style across truthful and deceptive dyadic communication in a synchronous text-based setting. A computer-based analysis of 242 transcripts revealed that senders produced more words overall, decreased their use of self-oriented pronouns but increased other-oriented pronouns, and used more sense-based descriptions (e.g., seeing, touching) when lying than when telling the truth. In addition, motivated senders avoided causal terms during deception, while unmotivated senders relied more heavily on simple negations. Receivers used more words when being deceived, but they also asked more questions and used shorter sentences when being lied to than when being told the truth, especially when the sender was unmotivated. These findings are discussed in terms of their implications for linguistic style matching and interpersonal deception theory.