Abstract
Much of our online communication is text-mediated and, lately, more common with automated agents. Unlike interacting with humans, these agents currently do not tailor their language to the type of person they are communicating to. In this pilot study, we measure the extent to which human perception of basic user trait information – gender and age – is controllable through text. Using automatic models of gender and age prediction, we estimate which tweets posted by a user are more likely to mis-characterize his traits. We perform multiple controlled crowdsourcing experiments in which we show that we can reduce the human prediction accuracy of gender to almost random – an over 20% drop in accuracy. Our experiments show that it is practically feasible for multiple applications such as text generation, text summarization or machine translation to be tailored to specific traits and perceived as such.- Anthology ID:
- D17-1248
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2335–2341
- Language:
- URL:
- https://aclanthology.org/D17-1248
- DOI:
- 10.18653/v1/D17-1248
- Cite (ACL):
- Daniel Preoţiuc-Pietro, Sharath Chandra Guntuku, and Lyle Ungar. 2017. Controlling Human Perception of Basic User Traits. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2335–2341, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Controlling Human Perception of Basic User Traits (Preoţiuc-Pietro et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/D17-1248.pdf