{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:38:18Z","timestamp":1791459498751,"version":"4.3.4"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2340389"],"award-info":[{"award-number":["2340389"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Toxic interactions during code reviews can undermine teamwork and hinder productivity in software engineering (SE) teams. While prior studies explore toxicity detection and empirical investigation, they lack real-time detoxification tools to support the SE community. To address this gap, we present ToxiShield, a browser extension for GitHub pull requests that is built using three modules: i) Toxicity Filter -- to identify whether a text is toxic, ii) Communication coach -- to facilitate just-in-time fine-grained toxicity categorization with explanations, and iii) The Reframer -- that generates a revised, constructive alternative of a toxic text. For each module, we trained and evaluated multiple deep learning and Large Language Models (LLMs) to identify the best choice. A BERT-based binary detection model, trained on 38,761 code review samples, achieves 98% accuracy and an F1-score of 97% and is the selected one for the Toxicity Filter module. For the Communication Coach, prompt-tuned Claude 3.5 Sonnet achieved the best performance with 39% MCC and 42% F1 in multiclass toxicity classification with detailed reasoning. For Reframer, we evaluated five LLMs using a fine-tuning strategy on a dataset of 10,120 code review comments. The fine-tuned Llama 3.2 model achieves 95.27% style transfer accuracy, 97.03% fluency, 67.07% content preservation, and an 84% J-score. We further validated ToxiShield through a human evaluation using the Technology Acceptance Model with 10 participants, confirming its perceived usefulness and ease of adoption. ToxiShield sets a benchmark for advancing constructive communication in software engineering, driving inclusivity and healthier collaboration in open-source communities.<\/jats:p>","DOI":"10.1145\/3808130","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"2767-2789","source":"Crossref","is-referenced-by-count":2,"title":["ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0866-3696","authenticated-orcid":false,"given":"Md Awsaf Alam","family":"Anindya","sequence":"first","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Computer Science and Engineering, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2154-4498","authenticated-orcid":false,"given":"Showvik","family":"Biswas","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Computer Science and Engineering, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2763-8819","authenticated-orcid":false,"given":"Anindya","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Computer Science and Engineering, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6440-7596","authenticated-orcid":false,"given":"Jaydeb","family":"Sarker","sequence":"additional","affiliation":[{"name":"University of Nebraska Omaha, Omaha, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3178-6232","authenticated-orcid":false,"given":"Amiangshu","family":"Bosu","sequence":"additional","affiliation":[{"name":"Wayne State University, Computer Science, Detroit, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Md Awsaf Alam Anindya Showvik Biswas Anindya Iqbal Jaydeb Sarker and Amiangshu Bosu. 2026. ToxiShield: Replication Package. https:\/\/github.com\/WSU-SEAL\/ToxiShield"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM64174.2025.00016"},{"key":"e_1_2_1_3_1","volume-title":"Using thematic analysis in psychology. Qualitative research in psychology 3, 2","author":"Braun Virginia","year":"2006","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3, 2 (2006), 77-101."},{"key":"e_1_2_1_4_1","volume-title":"SIGOPEN 2016","author":"Andr\u00e9 Carillo Kevin Daniel","year":"2016","unstructured":"Kevin Daniel Andr\u00e9 Carillo, Josianne Marsan, and Bogdan Negoita. 2016. Towards developing a theory of toxicity in the context of free\/open source software & peer production communities. SIGOPEN 2016 (2016)."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 137-144","author":"Dekel Ofer","year":"2010","unstructured":"Ofer Dekel and Ohad Shamir. 2010. Multiclass-multilabel classification with more classes than examples. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 137-144."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Tanni Dev Sayma Sultana and Amiangshu Bosu. 2025. Beyond Binary Moderation: Identifying Fine-Grained Sexist and Misogynistic Behavior on GitHub with Large Language Models. In 2025 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) (Honolulu Hawai USA USA). 1-12. doi:10.1109\/ESEM64174.2025.00059 10.1109\/ESEM64174.2025.00059","DOI":"10.1109\/ESEM64174.2025.00059"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380414"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643991.3644887"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613077"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Ramtin Ehsani Rezvaneh Rezapour and Preetha Chatterjee. 2025. Analyzing Toxicity in Open Source Software Communications Using Psycholinguistics and Moral Foundations Theory. (2025) 1-8. doi:10.1109\/NLBSE66842.2025. 00006 10.1109\/NLBSE66842.2025.00006","DOI":"10.1109\/NLBSE66842.2025"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03195514"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479497"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111935"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11330"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.647"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555183"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00237"},{"key":"e_1_2_1_19_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_2_1_20_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3744916"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3786164.3788447"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645200"},{"key":"e_1_2_1_24_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022), 22199-22213."},{"key":"e_1_2_1_25_1","volume-title":"Seventeenth Symposium on Usable Privacy and Security (SOUPS 2021). USENIX Association, 299-318. https:\/\/www.usenix.org\/ conference\/soups2021\/presentation\/kumar","author":"Kumar Deepak","year":"2021","unstructured":"Deepak Kumar, Patrick Gage Kelley, Sunny Consolvo, Joshua Mason, Elie Bursztein, Zakir Durumeric, Kurt Thomas, and Michael Bailey. 2021. Designing Toxic Content Classification for a Diversity of Perspectives. In Seventeenth Symposium on Usable Privacy and Security (SOUPS 2021). USENIX Association, 299-318. https:\/\/www.usenix.org\/ conference\/soups2021\/presentation\/kumar"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Qingxiong Ma and Liping Liu. 2005. The Technology Acceptance Model. doi:10.4018\/9781591404743.ch006.ch000 10.4018\/9781591404743.ch006.ch000","DOI":"10.4018\/9781591404743.ch006.ch000"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510111"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639476.3639777"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.04563"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-9651-6_18"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474097"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09960-w"},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","first-page":"15802","DOI":"10.63317\/56xihte7mqb8","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024","author":"Ostheimer Phil Sidney","year":"2024","unstructured":"Phil Sidney Ostheimer, Mayank Kumar Nagda, Marius Kloft, and Sophie Fellenz. 2024. Text Style Transfer Evaluation Using Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ELRA and ICCL, Torino, Italia, 15802-15822. https:\/\/ aclanthology.org\/2024.lrec-main.1373\/"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1080"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510458.3513019"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660780"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377816.3381732"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.407"},{"key":"e_1_2_1_41_1","volume-title":"Prompt Engineering Guide. https:\/\/github.com\/dair-ai\/Prompt-Engineering-Guide (12","author":"Saravia Elvis","year":"2022","unstructured":"Elvis Saravia. 2022. Prompt Engineering Guide. https:\/\/github.com\/dair-ai\/Prompt-Engineering-Guide (12 2022)."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM56168.2023.10304855"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC51365.2020.00030"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715744"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583562"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2007.03.086"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757739"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.603"},{"key":"e_1_2_1_49_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3108032"},{"key":"e_1_2_1_51_1","volume-title":"Refining the test phase of usability evaluation: how many subjects is enough? Human factors 34, 4","author":"Virzi Robert A","year":"1992","unstructured":"Robert A Virzi. 1992. Refining the test phase of usability evaluation: how many subjects is enough? Human factors 34, 4 (1992), 457-468."},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","unstructured":"Zhiqiang Wang Yiran Pang and Yanbin Lin. 2023. Large Language Models Are Zero-Shot Text Classifiers. doi:10. 48550\/ARXIV.2312.01044 10.48550\/ARXIV.2312.01044","DOI":"10.48550\/ARXIV.2312.01044"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1427"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808130","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:08:44Z","timestamp":1782842924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":56,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808130"],"URL":"https:\/\/doi.org\/10.1145\/3808130","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}