{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/safecity-understanding-diverse-forms-of","title":"SafeCity: Understanding Diverse Forms of Sexual Harassment Personal Stories","arxiv_id":"1809.04739","date":"2018-09-13","proceeding":"EMNLP 2018 10","authors":["Sweta Karlekar","Mohit Bansal"],"abstract":"With the recent rise of #MeToo, an increasing number of personal stories\nabout sexual harassment and sexual abuse have been shared online. In order to\npush forward the fight against such harassment and abuse, we present the task\nof automatically categorizing and analyzing various forms of sexual harassment,\nbased on stories shared on the online forum SafeCity. For the labels of\ngroping, ogling, and commenting, our single-label CNN-RNN model achieves an\naccuracy of 86.5%, and our multi-label model achieves a Hamming score of 82.5%.\nFurthermore, we present analysis using LIME, first-derivative saliency\nheatmaps, activation clustering, and embedding visualization to interpret\nneural model predictions and demonstrate how this extracts features that can\nhelp automatically fill out incident reports, identify unsafe areas, avoid\nunsafe practices, and 'pin the creeps'.","url_abs":"http://arxiv.org/abs/1809.04739v2","url_pdf":"http://arxiv.org/pdf/1809.04739v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"safecity-understanding-diverse-forms-of","repo_url":"https://github.com/swkarlekar/safecity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"safecity-understanding-diverse-forms-of","repo_url":"https://github.com/Manojkumar8300/Sexual-Harassment-Personal-Story-Classsification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"safecity-understanding-diverse-forms-of","repo_url":"https://github.com/bhaveshnaidu999/sexual-harassment-classification-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"safecity-understanding-diverse-forms-of","repo_url":"https://github.com/zaid7860/Safecity_BERT-LogisticRegression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[{"method_slug":"lime","method_name":"LIME"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.04739","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}