{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:55:55Z","timestamp":1766159755082,"version":"build-2065373602"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIES"],"abstract":"<jats:p>The development of Open-Source Software (OSS) is not only a\ntechnical challenge, but also a social one due to the\ndiverse mixture of contributors. To this aim, social-coding\nplatforms, such as GitHub, provide the infrastructure\nneeded to host and develop the code, but also the support\nfor enabling the community's collaboration, which is driven\nby non-coding contributions, such as issues (i.e., change\nproposals or bug reports) or comments to existing\ncontributions. As with any other social endeavor, this\ndevelopment process faces ethical challenges, which may put\nin risk the project's sustainability. To foster a\nproductive and positive environment, OSS projects are\nincreasingly deploying codes of conduct, which define rules\nto ensure a respectful and inclusive participatory\nenvironment, with the Contributor Covenant being the main\nmodel to follow. However, monitoring and enforcing these\ncodes of conduct is a challenging task, due to the\nlimitations of current approaches. In this paper, we\npropose an approach to classify the ethical quality of\nnon-coding contributions in OSS projects by relying on\nLarge Language Models (LLM), a promising technology for\ntext classification tasks. We defined a set of ethical\nmetrics based on the Contributor Covenant and developed a\nclassification approach to assess ethical behavior in OSS\nnon-coding contributions, using prompt engineering to guide\nthe model's output.<\/jats:p>","DOI":"10.1609\/aies.v8i1.36578","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:14:58Z","timestamp":1760534098000},"page":"643-652","source":"Crossref","is-referenced-by-count":1,"title":["Ethical Classification of Non-Coding Contributions in Open-Source Projects via Large Language Models"],"prefix":"10.1609","volume":"8","author":[{"given":"Sergio","family":"Cobos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier Luis","family":"C\u00e1novas Izquierdo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2025,10,15]]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36578\/38716","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36578\/38716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:14:58Z","timestamp":1760534098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1609\/aies.v8i1.36578","relation":{},"ISSN":["3065-8365"],"issn-type":[{"value":"3065-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}