[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-154716-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-154716-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","automated-identification-of-sexual-orientation-and-gender-identity-discriminatory-texts-from-issue-comments-research","Automated Identification of Sexual Orientation and Gender Identity Discriminatory Texts from Issue Comments - Research","","Automated detection of Sexual Orientation and Gender Identity Discriminatory (SGID) language is needed because large-scale FLOSS communities cannot rely on manual inspection of developer issue comments. The study introduces SGID4SE, a supervised learning tool that combines six preprocessing steps with ten state-of-the-art algorithms and six strategies to improve minority-class performance. Empirical evaluation with BERT reports 85.9% precision, 80.0% recall, and 82.9% F1 for SGID, alongside 95.7% accuracy and a Matthews Correlation Coefficient of 80.4%, supported by an optimized configuration study.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/automated-identification-of-sexual-orientation-and-gender-identity-discriminatory-texts-from-issue-comments-research/154716/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/automated-identification-of-sexual-orientation-and-gender-identity-discriminatory-texts-from-issue-comments-research/154716.png","ImageObject",300,407,{"name":42,"@type":43},"Gelato","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-08","2026-08-28",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is automated identification of SGID discriminatory texts necessary in FLOSS communities?","Question",{"text":63,"@type":64},"The study argues that the volume of communications makes manual inspection infeasible, and discriminatory messages create barriers for women and LGBTQ+ contributors.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is SGID4SE and how does it work?",{"text":68,"@type":64},"SGID4SE is a supervised learning tool that applies six preprocessing steps, uses ten state-of-the-art algorithms, and includes six strategies to strengthen minority-class performance.",{"name":70,"@type":61,"acceptedAnswer":71},"Which model performed best in the SGID classification results?",{"text":72,"@type":64},"The BERT-based model achieved the best SGID performance with 85.9% precision, 80.0% recall, and 82.9% F1-score under ten-fold cross-validation.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},154716,1787897477,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144},19241457091524,"https://us-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","arXiv :2311 .08485v2 [ cs . SE] 28 Jul 2025  \nAutomated Identification of Sexual Orientation and Gender Identity Discriminatory Texts from Issue Comments  \nSAYMA SULTANA, Wayne State University, USA JAYDEB SARKER, University of Nebraska Omaha, USA FARZANA ISRAT, Wayne State University, USA RAJSHAKHAR PAUL, Idaho State University, USA AMIANGSHU BOSU, Wayne State University, USA  \nIn an industry dominated by straight men, many developers representing other gender identities and sexual orientations often encounter hateful or discriminatory messages. Such communications pose barriers to participation for women and LGBTQ+ persons. Due to sheer volume, manual inspection of all communications for discriminatory communication is infeasible for a large-scale Free Open-Source Software (FLOSS) community. To address this challenge, this study proposes an automated mechanism to identify Sexual Orientation and Gender Identity Discriminatory (SGID) texts in software developers’ communications. On this goal, we trained and evaluated SGID4SE (Sexual orientation and Gender Identity Discriminatory text identification for (4) Software Engineering texts), a supervised learning-based tool. SGID4SE incorporates six preprocessing steps and ten state-of-the-art algorithms. SGID4SE employs six distinct strategies to enhance the performance of the minority class. We empirically evaluated each strategy and identified an optimum configuration for each algorithm. In our ten-fold cross-validation-based evaluations, a BERT-based model achieves the best performance with 85.9% precision, 80.0% recall, and 82.9% F1-score for the SGID class. This model achieves 95.7% accuracy and a Matthews Correlation Coefficient of 80.4% . Our dataset and tool establish a foundation for further research in this direction.  \nCCS Concepts: • Software and its engineering → Collaboration in software development; Integrated  \nand visual development environments; • Computing methodologies → Supervised learning. Additional Key Words and Phrases: misogyny, sexism, discrimination, hate speech, pejorative ACM Reference Format:  \nSayma Sultana, Jaydeb Sarker, Farzana Israt, Rajshakhar Paul, and Amiangshu Bosu. 2025. Automated Identification of Sexual Orientation and Gender Identity Discriminatory Texts from Issue Comments. ACM Trans. Softw. Eng. Methodol. 34, 0, Article 0 ( 2025), 31 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n[Warning: This paper contains examples of language that some people may find offensive or upsetting.](Warning: This paper contains examples of language that some people may find offensive or upsetting.)  \n1 Introduction  \nAccording to the 2023 Stack Overflow developer survey [61], only 5.1% of the professional developers around the world identify as women compared to 91.8% identifying as men. In an industry dominated by straight men, many software developers harbor sexist, misogynist, and anti-LGBTQ+ beliefs and  \nAuthors’ Contact Information: Sayma Sultana, [sayma@wayne.edu](sayma@wayne.edu), Wayne State University, Detroit, Michigan, USA; Jaydeb Sarker, [jsarker@unomaha.edu](jsarker@unomaha.edu), University of Nebraska Omaha, Omaha, Nebraska, USA; Farzana Israt, farzanaisrat@wayne. edu, Wayne State University, Detroit, Michigan, USA; Rajshakhar Paul, rpaul@wayne.edu, Idaho State University, Pocatello, Idaho, USA; Amiangshu Bosu, [amiangshu.bosu@wayne.edu](amiangshu.bosu@wayne.edu), Wayne State University, Detroit, Michigan, USA.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, req","cbCaicxHiNjXKTtu","https://ap.wps.com/l/cbCaicxHiNjXKTtu","pdf",835165,31,"English","# Introduction\n## Motivation and background\n## Related work on sexism, misogyny, and LGBTQ+ discrimination\n# Methodology\n## SGID4SE overview\n## Preprocessing and model strategies\n# Evaluation\n## Cross-validation results and best configuration\n# Conclusion\n## Dataset and research implications","[{\"question\":\"Why is automated identification of SGID discriminatory texts necessary in FLOSS communities?\",\"answer\":\"The study argues that the volume of communications makes manual inspection infeasible, and discriminatory messages create barriers for women and LGBTQ+ contributors.\"},{\"question\":\"What is SGID4SE and how does it work?\",\"answer\":\"SGID4SE is a supervised learning tool that applies six preprocessing steps, uses ten state-of-the-art algorithms, and includes six strategies to strengthen minority-class performance.\"},{\"question\":\"Which model performed best in the SGID classification results?\",\"answer\":\"The BERT-based model achieved the best SGID performance with 85.9% precision, 80.0% recall, and 82.9% F1-score under ten-fold cross-validation.\"}]","Automated Identification of Sexual Orientation and Gender Identity Discriminatory Texts from Issue Comments - Research | PDF",78]