Wikimedia Research - Programs - Community Health

Pew survey pewinternet.org > online-harassment Release of WikiConv dataset Jan 2019 We’re thrilled to announce the release of WikiConv—a multilingual corpus reconstructing the complete conversational history of multiple Wikipedia language editions. github.com > conversationai > wikidetox > tree > master > wikiconv Presentation video available for Conversations Gone Awry Jan 2019 Video is now available of Justine Zhang of Cornell University presenting our Conversations Gone Awry paper at ACL in June 2018. vimeo.com > 285803564 Research showcase for Conversations Gone Awry Jun 2018 We're hosting our collaborators at Cornell University and Jigsaw at the Wikimedia Research Showcase in June to present this study, along with a new corpus of English Wikipedia Talk page conversations. youtube.com > watch Machine learning is helping computers spot arguments online before they happen May 2018 ‘Hey there. It looks like you’re trying to rile someone up for no good reason?’ The Verge covers the Conversations Gone Awry study. theverge.com > machine-learning-ai-spot-arguments-online-wikipedia Scientists are building a detector for conversations likely to go bad May 2018 "Researchers say their tool can often spot when Wikipedia discussions will degenerate into personal attacks by watching for a few familiar linguistic cues." The Conversations Gone Awry study is featured in Fast.Company. fastcompany.com > scientists-are-building-a-detector-for-conversations-likely-to-go-bad Paper accepted at ACL '18: Conversations Gone Awry May 2018 A new paper on detecting early signs of conversational failure in Wikipedia talk pages, with our collaborators at Cornell University and Jigsaw, is accepted at ACL '18 and will be presented at the conference in Melbourne in July. arxiv.org > abs > 1805.05345 Characterizing Wikihounding on Wikipedia Jan 2018 The Wikimedia Foundation's Caroline Sinders talks about challenges in designing quantitative and qualitative methods to identify Wikihounding – a form of digital stalking on Wikipedia. youtu.be > L-1uzYYneUo Toxic Comment Classification Challenge Dec 2017 A new modeling challenge hosted on Kaggle by our collaborators at Jigsaw, aims to improve the performance of models to identify and classify toxic comments on English Wikipedia's talk pages. kaggle.com > c > jigsaw-toxic-comment-classification-challenge Conversation corpora, emotional robots, and battles with bias Nov 2017 Jigsaw's Lucas Dixon talks about experimental setups for doing large-scale analysis of conversations in Wikipedia, part of ongoing research on the nature and impact of harassment in Wikipedia discussion spaces. youtube.com > watch Collection of 13,500 Nastygrams Could Advance War on Trolls Jan 2017 Our work in collaboration with Jigsaw, and the release of 100,000 comments on English Wikipedia talk pages labeled for toxicity, is covered in MIT Technology Review. technologyreview.com > s > collection-of-13500-nastygrams-could-advance-war-on-trolls Detecting Personal Attacks on Wikipedia Jul 2016 Ellery Wulczyn (WMF) and Nithum Thain (Jigsaw) present preliminary results from a research collaboration aiming to develop tools to detect and understand online personal attacks on Wikipedia. youtube.com > watch WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community arxiv.org > abs > 1810.13181 http://aclweb.org/anthology/D18-1305 aclweb.org > anthology > D18-1305 Conversations Gone Awry: Detecting Early Signs of Conversational Failure arxiv.org > abs > 1805.05345 Ex machina: Personal attacks seen at scale arxiv.org > pdf > 1610.08914 https://doi.org/10.1145/3038912.3052591 doi.org > 10.1145 > 3038912.3052591 Conversations Gone Awry: Detecting Early Signs of Conversational Failure youtube.com > watch