Abstract
With the recent rise of #MeToo, an increasing number of personal stories about sexual harassment and sexual abuse have been shared online. In order to push forward the fight against such harassment and abuse, we present the task of automatically categorizing and analyzing various forms of sexual harassment, based on stories shared on the online forum SafeCity. For the labels of groping, ogling, and commenting, our single-label CNN-RNN model achieves an accuracy of 86.5%, and our multi-label model achieves a Hamming score of 82.5%. Furthermore, we present analysis using LIME, first-derivative saliency heatmaps, activation clustering, and embedding visualization to interpret neural model predictions and demonstrate how this helps extract features that can help automatically fill out incident reports, identify unsafe areas, avoid unsafe practices, and ‘pin the creeps’.- Anthology ID:
- D18-1303
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2805–2811
- Language:
- URL:
- https://aclanthology.org/D18-1303
- DOI:
- 10.18653/v1/D18-1303
- Cite (ACL):
- Sweta Karlekar and Mohit Bansal. 2018. SafeCity: Understanding Diverse Forms of Sexual Harassment Personal Stories. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2805–2811, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- SafeCity: Understanding Diverse Forms of Sexual Harassment Personal Stories (Karlekar & Bansal, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/D18-1303.pdf
- Code
- swkarlekar/safecity + additional community code