🧑‍🔬 Nithum Thain

Affiliations

• Google (United States) · Mountain View, United States — current · 2018–2026 on 17 papers
• Athens University of Economics and Business · Athens, Greece — 2019–2023 on 3 papers
• University of Oxford · Oxford, United Kingdom — 2020–2022 on 2 papers
• Cornell University · Ithaca, United States — 2018 on 2 papers
• Wikimedia Foundation · San Francisco, United States — 2018 on 2 papers
• McGill University · Montreal, Canada — 2009–2014 on 3 papers
• Queen's University · Kingston, Canada — 2006–2007 on 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

Topics

Bias, fairness & safety2Dialogue systems1

Papers

The most cited first (OpenAlex and our library).

1. Conversations Gone Awry: Detecting Early Signs of Conversational Failure (2018 · 250 citations)
   Most work on online toxicity flags harmful comments only after they appear. This paper instead asks whether the opening of a seemingly civil conversation can reveal that it will later turn into a personal attack, early enough for intervention. The authors rebuilt about 50 million conversations from English Wikipedia…
2. Toxicity Detection: Does Context Really Matter? (2020 · 198 citations)
   Most toxicity datasets and classifiers judge each comment in isolation, even though a reply's meaning often depends on what it answers.

Co-authors here

7 co-authors with a page, the most papers together first.

• Lucas Dixon ×2
• Cristian Danescu-Niculescu-Mizil
• Ion Androutsopoulos
• Jeffrey Sorensen
• John Pavlopoulos
• Jonathan Chang
• Justine Zhang

Cited by

Papers of our library cite their works 156 times (of the 140 884 papers whose bibliographies we read); 6 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nithum-thain/