I would appreciate pointers to any papers that demonstrate progress in detecting deception (falsification/lying) in Japanese, Mandarin/Cantonese, and or Korean specifically, or any other Asian languages. Is your sense that the literature is not as readily available in English, or that there might not be as much work out there in NLP/ML on those issues yet? If you know of any work from interpersonal psychology, communications studies, or philosophy on the topic of lie-truth discernment and it either applies universally across languages or/and specifically for Asian speakers (nuances, cultural spins, etc.), please do respond. Thank you.
I have been involved in a meta-analysis of linguistic cues to deception assessed by computer programs. We were able to include 44 studies but none was performed on any Asian language--English was by far the most frequent language, followed by Spanish (two studies), Dutch (one study), and Arabic (one study). The only relevant report I know of is Zhou, L., & Sung, Y.-W. (2008). Cues to deception in online Chinese groups. Proceedings of the 41st Hawaii International Conference on System Sciences. doi:10.1109/HICSS.2008.109
We are working on a comparison of American English speakers and Mandarin Chinese speakers -- but both speaking English. Some work on Chinese speaking Chinese tho:
Cody et al. (1989). M. Cody, W. Lee, and E. Y. Chao, Telling lies: Correlates of deception among Chinese. In J. P. Forgas and J. M. Innes, eds., Recent Advances in Social Psychology: An International Perspective, 359-368, 1989.
O'Hair, D., Cody, M. J., Wang, S., & Chao, E. Y. (1990). Vocal stress and deception detection among Chinese. Communication Quarterly, 38(2, Spring), 158ff.
The Dutch study is:
Schelleman-Offermans, K., & Merckelbach, H. (2010). Fantasy proneness as a confounder of verbal lie detection tools. Journal of Investigative Psychology and Offender Profiling, 7, 247-260. doi:10.1002/jip.121
Thanks so much for your responses. Zhou and Sung 2008 does seem to be the only one that is in English. I wonder if that's the language barrier.
@Jaume Masip: Could I please have the citation/link for your meta-analysis study of the 44 cues? Again, appreciate your input!
Dear Rubin,
One of our recent work is to investigate Chinese (speaking Cantonese) neural responses (recorded by using both fMRI and ERP) to both telling lies and truth. I am not sure whether it is consistent with your requirement, but maybe it is helpful.
Sun D, Lee TM, Chan CC. (2013). Unfolding the Spatial and Temporal Neural Processing of Lying about Face Familiarity. Cereb Cortex. [Epub ahead of print]
http://cercor.oxfordjournals.org/cgi/pmidlookup?view=long&pmid=24186897
Hi, one of our recent work may be helpful for you.
Wu, S., Zou, H., Cai, W., Wang, X., & Jin, S. (2014). Motivational cues: The role of perceived senders' self-control ability in raters' deception judgements. International Journal of Psychology, 49(2), 123-130. doi: 10.1002/ijop.12039
We use a methodology called "adaptive psychological profiling" to perform lie detection - artificial intelligence classifiers learn for themselves from non-verbal behaviour by analysing truthful and deceptive interviews. We discuss the effect of ethnicity on NVB based lie detection in
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.211.1303&rep=rep1&type=pdf
We have applied adaptive psychological profiling to measure comprehension instead of deception and used it in a study with Kiswahili speaking Tanzanian women. We did discover interesting cultural NVB differences:
Buckingham, Fiona J., et al. "Measuring human comprehension from nonverbal behaviour using Artificial Neural Networks." Neural Networks (IJCNN), The 2012 International Joint Conference on. IEEE, 2012.
- Badges
- Science topic