{"id":19152537,"url":"https://github.com/gesiscss/sexism_custom_classifier","last_synced_at":"2025-05-07T05:47:16.613Z","repository":{"id":56577701,"uuid":"287249439","full_name":"gesiscss/sexism_custom_classifier","owner":"gesiscss","description":"Custom classifiers to detect sexist language.","archived":false,"fork":false,"pushed_at":"2021-02-11T11:36:22.000Z","size":33807,"stargazers_count":7,"open_issues_count":0,"forks_count":3,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-04-19T19:05:18.460Z","etag":null,"topics":["bert","natural-language-processing","nlp","sckit-learn","sexism-detection"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gesiscss.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-08-13T10:29:34.000Z","updated_at":"2024-11-15T22:26:44.000Z","dependencies_parsed_at":"2022-08-15T21:20:26.377Z","dependency_job_id":null,"html_url":"https://github.com/gesiscss/sexism_custom_classifier","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gesiscss%2Fsexism_custom_classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gesiscss%2Fsexism_custom_classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gesiscss%2Fsexism_custom_classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gesiscss%2Fsexism_custom_classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gesiscss","download_url":"https://codeload.github.com/gesiscss/sexism_custom_classifier/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252823685,"owners_count":21809707,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert","natural-language-processing","nlp","sckit-learn","sexism-detection"],"created_at":"2024-11-09T08:18:17.198Z","updated_at":"2025-05-07T05:47:16.591Z","avatar_url":"https://github.com/gesiscss.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Binder](https://notebooks.gesis.org/binder/badge.svg)](https://notebooks.gesis.org/binder/v2/gh/gesiscss/sexism_custom_classifier/master?filepath=notebooks)\n\n# Sexism Custom Classifier\n\n## Introduction\n\nSexism custom classifier is implemented to detect sexism automatically in the field of natural language processing. In this work, the dataset from [Samory et al. (2020)](https://arxiv.org/abs/2004.12764) was used to train three models on top of four different feature sets (both individual and combinations). The aim of the experiments is to answer two research questions:  \n\n* What is the informativeness of different feature sets on the sexism detection task?\n* What are the improvements on the sexism classifiers’ performance when different feature sets are introduced?\n\n## Support Features\n\n* Sentiment : The sentiment intensity provided by [VADER](http://eegilbert.org/papers/icwsm14.vader.hutto.pdf) sentiment analysis method.\n* Word N-grams : Term Frequency/Inverse Frequency (TF-IDF) weights of word n-grams proviided by [scikit-learn](https://jmlr.csail.mit.edu/papers/v12/pedregosa11a.html).\n* Type Dependency : The type dependency relationships provided by [Stanford Parser](https://nlp.stanford.edu/~wcmac/papers/td-lrec06.pdf). The parser can be dowloaded from [here](https://nlp.stanford.edu/software/lex-parser.shtml#Download).  \n* Document Embeddings : The document embeddings provided by [BERT](https://arxiv.org/abs/1810.04805) language representation model.\n\n## Support Models\n\n* Logistic Regression\n* Convolutional Neural Network\n* Support Vector Machine\n\n## Experiments\n\nThis example code trains Logistic Regression on top of sentiment and uni-gram features. To replicate the results, run the scripts in the 'experiments/scripts.txt'\n\n```shell\nexport PARAMS_FILE='experiments/params.json'\nexport HYPERPARAMS_FILE='experiments/hyperparams.json'\n\npython run.py \\\n  --params_file=$PARAMS_FILE \\\n  --hyperparams_file=$HYPERPARAMS_FILE \\\n```\n\nThis example code obtains the pre-trained BERT embeddings.\n\n```shell\nexport DATA_FILE=/path/data.csv\n\npython run_bert_feature_extraction.py \\\n\t--data_file=$DATA_FILE \\\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgesiscss%2Fsexism_custom_classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgesiscss%2Fsexism_custom_classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgesiscss%2Fsexism_custom_classifier/lists"}