Identity Deception Detection
Verónica Pérez-Rosas, Quincy Davenport, Anna Mengdan Dai, Mohamed Abouelenien, Rada Mihalcea
Abstract
This paper addresses the task of detecting identity deception in language. Using a novel identity deception dataset, consisting of real and portrayed identities from 600 individuals, we show that we can build accurate identity detectors targeting both age and gender, with accuracies of up to 88. We also perform an analysis of the linguistic patterns used in identity deception, which lead to interesting insights into identity portrayers.- Anthology ID:
- I17-1089
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 885–894
- Language:
- URL:
- https://aclanthology.org/I17-1089
- DOI:
- Cite (ACL):
- Verónica Pérez-Rosas, Quincy Davenport, Anna Mengdan Dai, Mohamed Abouelenien, and Rada Mihalcea. 2017. Identity Deception Detection. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 885–894, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Identity Deception Detection (Pérez-Rosas et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/I17-1089.pdf