Dr. Svetlana Kiritchenko is a senior research scientist at the National Research Council Canada. She received her Ph.D. in Computer Science from the University of Ottawa (Canada) and her M.Sc. in Applied Mathematics and Computer Science from Moscow State University (Russia). She primarily works in the areas of Computational Linguistics and Natural Language Processing (NLP). Her research interests include ethics and fairness in NLP, sentiment and emotion analysis, text classification, social media analysis, and medical informatics. She has also done work in hierarchical text classification and semi-supervised learning. As part of the NRC-Canada team, she has developed several text classification systems (for sentiment analysis and health-related social media mining) that ranked first in international shared task competitions. She has co-organized the 2019 Canada-United Kingdom Symposium on Ethics in AI, several graduate student symposia at Canadian conferences on AI, and several shared tasks at the international workshops on Semantic Evaluation (SemEval). She has served as reviewer for major NLP and AI conferences and journals and as area chair and senior area chair for NAACL-2022, EACL-2021, and *SEM-2018.

Email: svetlana <dot> kiritchenko <at> nrc-cnrc <dot> gc <dot> ca


News and Announcements:

  • A survey of NLP research on automatic abuse detection with a focus on ethical challenges, organized around eight established ethical principles: privacy, accountability, safety and security, transparency and explainability, fairness and non-discrimination, human control of technology, professional responsibility, and promotion of human values:
    Svetlana Kiritchenko, Isar Nejadgholi, and Kathleen C. Fraser. Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective. Journal of Artificial Intelligence Research, 71: 431-478, July 2021. [pdf]
  • Equity Evaluation Corpus: 8,640 English sentences carefully chosen to tease out biases towards certain races and genders. We use the dataset to examine 219 automatic sentiment analysis systems that took part in a recent shared task, SemEval-2018 Task 1 'Affect in Tweets'
    Svetlana Kiritchenko and Saif M. Mohammad. Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems. In Proceedings of *Sem, New Orleans, LA, USA, June 2018 [pdf] [data]