Professor Kalina Bontcheva

School of Computer Science

Professor of Text Analytics

Member of the Natural Language Processing (NLP) research group

k.bontcheva@sheffield.ac.uk

Full contact details

Professor Kalina Bontcheva
School of Computer Science
Regent Court (CS)
211 Portobello
Sheffield
S1 4DP
Profile

Kalina Bontcheva is a professor of natural language processing (NLP) in the School of Computer Science at the University of Sheffield, co-affiliated with Sheffield’s Center for Freedom of the Media. Her research lies at the intersection of NLP, computational social media analysis, and web science, with applications to digital humanities, social science, digital journalism, business intelligence, and data science.

Between 2014 and 2016 Kalina conceived and led the PHEME international project, which was amongst the first EU projects to study computational methods for the detection and tracking of disinformation in social media. She is currently the scientific director of the veraAI project, and previously the WeVerify, SoBigData++ and SoBigData international projects. Since 2015 Kalina has also been working on real-time social media analysis around United Kingdom general elections and the Brexit referendum, and on monitoring and analysis of online abuse towards UK politicians. She co-authored the ITU/UNESCO study "Balancing Act: Countering Digital Disinformation While Respecting Freedom of Expression", two UNESCO policy briefs on Combating the COVID-19 Disinfodemic, and the UNESCO study "The Chilling: Global trends in online violence against women journalists".

Kalina’s research on online disinformation and abuse of target public figures (especially MPs and female journalists) has been covered by many UK media organisations (incl. the BBC, ITV, the Guardian and Buzzfeed UK) with reach exceeding 17.7 million. This includes real-time analysis of political engagement on social media for the 2015 UK general elections and the UK EU membership referendum;  analysing Twitter abuse towards politicians in the 2017 UK general election campaign; commentary on the role of Russian bots and sock-puppet accounts in the UK EU membership referendum campaign;  and online abuse towards UK MPs (2019 election), which was featured on the news and in this accompanying BBC article.

Since 2006 Kalina has been awarded 17 grants as a PI (seven of these as a sole investigator), with a total award value for her team exceeding £8.8 million, from diverse funding sources: EU funding (Frameworks 6 and 7, Horizon 2020, and Horizon Europe), UK EPSRC and ESRC funding councils, a Google Faculty Award, a Google Digital News Grant, a UK Department of Health and Social Care grant, and two active grants from the UK Foreign, Commonwealth & Development Office (FCDO).

Research interests

Social media, misinformation, and abuse analysis – AI-generated misinformation detection; machine learning methods for misinformation and disinformation detection, online abuse analysis, and hate speech detection; large-scale, real-time analysis of social media content; longitudinal research on online abuse.

Publications

There has been a problem showing this information. Please try again later.

Grants
Professional activities and memberships

Member of the Natural Language Processing research group