%0 Conference Paper %1 Velutharambath2023 %A Velutharambath, Aswathy %A Klinger, Roman %B Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis %C Toronto, Canada %D 2023 %I Association for Computational Linguistics %K corpus deception imported myown nlp %P 39--51 %T UNIDECOR: A Unified Deception Corpus for Cross-Corpus Deception Detection %U https://aclanthology.org/2023.wassa-1.5 %X Verbal deception has been studied in psychology, forensics, and computational linguistics for a variety of reasons, like understanding behaviour patterns, identifying false testimonies, and detecting deception in online communication. Varying motivations across research fields lead to differences in the domain choices to study and in the conceptualization of deception, making it hard to compare models and build robust deception detection systems for a given language. With this paper, we improve this situation by surveying available English deception datasets which include domains like social media reviews, court testimonials, opinion statements on specific topics, and deceptive dialogues from online strategy games. We consolidate these datasets into a single unified corpus. Based on this resource, we conduct a correlation analysis of linguistic cues of deception across datasets to understand the differences and perform cross-corpus modeling experiments which show that a cross-domain generalization is challenging to achieve. The unified deception corpus (UNIDECOR) can be obtained from https://www.ims.uni-stuttgart.de/data/unidecor.

@inproceedings{Velutharambath2023, abstract = {Verbal deception has been studied in psychology, forensics, and computational linguistics for a variety of reasons, like understanding behaviour patterns, identifying false testimonies, and detecting deception in online communication. Varying motivations across research fields lead to differences in the domain choices to study and in the conceptualization of deception, making it hard to compare models and build robust deception detection systems for a given language. With this paper, we improve this situation by surveying available English deception datasets which include domains like social media reviews, court testimonials, opinion statements on specific topics, and deceptive dialogues from online strategy games. We consolidate these datasets into a single unified corpus. Based on this resource, we conduct a correlation analysis of linguistic cues of deception across datasets to understand the differences and perform cross-corpus modeling experiments which show that a cross-domain generalization is challenging to achieve. The unified deception corpus (UNIDECOR) can be obtained from https://www.ims.uni-stuttgart.de/data/unidecor.}, added-at = {2023-09-06T19:04:49.000+0200}, address = {Toronto, Canada}, author = {Velutharambath, Aswathy and Klinger, Roman}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e50dd630729b78b258b1c89099e2b8b2/dr.romanklinger}, booktitle = {Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis}, interhash = {da0e06f5be7e5199a3715f93964fda02}, internaltype = {workshop}, intrahash = {e50dd630729b78b258b1c89099e2b8b2}, keywords = {corpus deception imported myown nlp}, month = jul, pages = {39--51}, pdf = {https://www.romanklinger.de/publications/VelutharambathKlinger_UNIDECOR_WASSA2023.pdf}, publisher = {Association for Computational Linguistics}, timestamp = {2023-09-06T19:06:29.000+0200}, title = {{UNIDECOR}: A Unified Deception Corpus for Cross-Corpus Deception Detection}, url = {https://aclanthology.org/2023.wassa-1.5}, year = 2023 }