Dr. Marina Sokolova* PhD MSc


Dr. Marina Sokolova* PhD MSc
Adjunct Professor

Researcher, Institute for Big Data Analytics (IBDA)
Dalhousie University

Work E-mail: sokolova@uottawa.ca

Marina Sokolova


Dr. Sokolova works in Text Data Mining and Machine Learning. She is a faculty member at University of Ottawa, Faculty of Medicine and School of Electrical Engineering and Computer Science. Dr. Sokolova obtained her PhD from the School of Information Technology and Engineering, University of Ottawa in 2006. She has been awarded with grants and merit-based awards from Natural Sciences and Engineering Research Council, Canadian Institutes of Health Research,and Japan Society for the Promotion of Science. She is a member of program committees of international conferences on Artificial Intelligence and reviews for international journals in the field of Text Data Mining and participated in The Agenda with Steve Paikin (TVO). She is also on the Editorial Board of Computational Intelligence, a leading international journal in AI.

Development of automated methods for Social Mining is a challenging task, especially when the methods apply to big volumes of ever-changing data, a phenomenon which is called Big Data. Our goal is to design and deploy the methods that work well with variety of content and context. Part of our research focuses on design and development of automated methods for analysis of user-the funds written Web content and protection of privacy of users. These methods are used to find and extract information from social media, including details pertaining to personal health information and public health. We build methods for automated sentiment analysis and opinion mining from contents of user messages. We also work on extraction and analysis of personal health information posted in social media (e.g., Twitter, social networks, medical forums).

In 2015 - 2019, she served on the Executive of the Canadian Association for Artificial Intelligence (CAIACD). In 2020, Dr. Sokolova received a Distinguished Service Award from the Canadian Association for Artificial Intelligence.

June 17, 2020, Marina was invited for a Fireside Chat with Alumni, MILA

Selected publications:

Ahmad Pesaranghader, Stan Matwin, Marina Sokolova, Ali Pesaranghader.deepBioWSD: effective deep neural word sense disambiguation of biomedical text data, Journal of the American Medical Informatics Association 26 (5), 438-446, 2019.

Qufei Chen and Marina Sokolova, Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries, 2018, https://arxiv.org/abs/1805.00352

Marina Sokolova, Big Text Advantages and Challenges: Classification Perspective, I. J. Data Science and Analytics 5(1):1-10 (2018). Invited article.

Yasser Jafer, Stan Matwin, Marina Sokolova, A Multi-dimensional Privacy-aware Evaluation Function in Automatic Feature Selection, Transactions on Data Privacy 10, 145-174, 2017.

Marina Sokolova, Stan Matwin, Personal Privacy Protection in the Age of Big Data, Challenges in Computational Statistics and Data Mining, 365 - 380, Springer, 2016.

Ahmad Pesaranghader, Stan Matwin, Marina Sokolova and Robert G. Beiko “simDEF: definition-based semantic similarity measure of gene ontology terms for functional similarity analysis of genes”, Bioinformatics 32(9), p.p. 1380 – 1387, Oxford, 2016.

Naveen Kumar Parachur Cotha and Marina Sokolova, “Multi-Label Learning in Classification of Patients’ Quasi-Identifiers”, Progress in Artificial Intelligence, 4 (3–4), p.p. 37 – 48, Springer, 2015.

Victoria Bobicev, Marina Sokolova, Michael Oakes, “What goes around comes around: Learning Senti- ments in Online Medical Forums”, Cognitive Computation 7(5), p.p. 609 – 621, Springer, 2015.

Tanveer Ali, David Schramm, Marina Sokolova, Diana Inkpen.Can i hear you? Sentiment analysis on medical forums.Proceedings of the 6th International Joint Conference on Natural LanguageProcessing.2013.

Marina Sokolova and Guy Lapalme, “Learning opinions in user-generated Web content”, Journal of Natural Language Engineering, Cambridge University Press, 17(4), pp. 541–567, 2011.

Khaled El Emam, Emilio Neri, Elizabeth Jonker, Marina Sokolova, Liam Peyton, Angelica Neisa, Teresa Scasa,“The Inadvertent Disclosure of Personal Health Information through Peer-to-peer File Sharing Pro- grams”, Journal of the American Medical Informatics Association, 17, p.p. 148–158, BMJ Publishing Group, 2010.

Marina Sokolova and Guy Lapalme, “A Systematic Analysis of Performance Measures for Classification Tasks”, Information Processing & Management, 45, p. 427–437, Elsevier, 2009.

Marina Sokolova, Nathalie Japkowicz, Stan Szpakowicz.Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation.Australasian joint conference on artificial intelligence, 1015-1021, Springer, 2006.

Fields of Interest

  • Health Information
  • Text Data Mining
  • Data Mining
Back to top