Automatic deception detection is an important task that has gained momentum in computational linguistics due to its potential applications. In this paper, we propose a simple yet tough to beat multi-modal neural model for deception detection. By combining features from different modalities such as video, audio, and text along with Micro-Expression features, we show that detecting deception in real life videos can be more accurate. Experimental results on a dataset of real-life deception videos show that our model outperforms existing techniques for deception detection with an accuracy of 96.14% and ROC-AUC of 0.9799.
@article{arxiv.1803.00344,
title = {A Deep Learning Approach for Multimodal Deception Detection},
author = {Gangeshwar Krishnamurthy and Navonil Majumder and Soujanya Poria and Erik Cambria},
journal= {arXiv preprint arXiv:1803.00344},
year = {2018}
}
Comments
Accepted at the 19th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), 2018