Russian Deception Bank

We introduce Russian Deception Bank!

To the best of our knowledge, this is a first corpus of written texts for Slavic languages specially designed for text-based deception detection studies. It currently contains truthful and deceptive narratives written by the same individuals on the same topic (“How I spent yesterday” etc.), 113 deceptive texts and 113 truthful texts written by 113 university students. Besides texts, it contains rich metadata (gender, age, results of psychological testing and so on).

This research collection is reported in the paper 
Olga Litvinova, Tatiana Litvinova, Pavel Seredin, John Lyell. Deception Detection in Russian Texts. Proceedings of EACL SRW 2017  (Valencia, Spain, 3-7 June, 2017).

Any scientific publication derived from the use of this collection should explicitly refer to this CLEF 2017 paper.

 

The corpus was developed with support of a grant from the Russian Foundation for Basic Research (former Russian Humanitarian Science Foundation), N 15-34- 01221 “Lie Detection in a Written Text: A Corpus Study”.