Home > Research > Web & User Data Processing

Web & User
Data Processing

On this page

Purpose
Head & team
Projects & Grants
Publications
Tools
News

Purpose

The online activity of users produces a huge volume of behavioural data, which can be processed to provide useful knowledge and applications that make digital spaces more convenient, safe and impactful. This involves a range of methods, mostly based on AI.

In the Web and User Data Processing group, we combat false information and online malicious behaviour. We strive to create an extensive infrastructure for collecting online content in large volumes. This content is then monitored by AI-based methods to detect signs of false information and online malicious behaviour. We also make use of information retrieval and recommendations, mostly for e-commerce applications. Our research delivers innovative methods that improve customer experience and business goals. These methods can also reveal connections in our partners’ data to improve their processes and offer personalized services to their customers.

RESEARCH AREAS OF INTEREST:

Misinformation analysis and characterization

Machine learning based detection and prediction methods

Interpretation and explanation of machine learning models

User behaviour modelling and segmentation

Team

Jakub Šimko

Lead and Researcher

Mária Bieliková

Lead and Researcher

Michal Kompan

Lead and Researcher

Ján Čegiň

Researcher

Andrea Hrčková

Researcher

Martin Hyben

AI Specialist

Dominik Macko

Researcher

Róbert Móro

Researcher

Branislav Pecher

Researcher

Ivan Srba

Researcher

Matúš Tibenský

AI Specialist

Adrián Bindas

Research Engineer

Samuel Budai

Research Engineer

Marek Havrila

Research Engineer

Dominik Hornáček

Research Engineer

Filip Hossner

Research Engineer

Ján Jakubčík

Research Engineer

Jakub Kopál

Research Engineer

Lívia Kostová

Research Engineer

Šimon Liška

Research Engineer

Tomáš Matejov

Research Engineer

Matej Mosnár

Research Engineer

Peter Sakalík

Research Engineer

Tomáš Sako

Research Engineer

Andrej Šutý

Research Engineer

Matúš Tuna

Research Engineer

Róbert Belanec

PhD Student

Santiago de Leon

PhD Student MSCA Doctoral Network

Adam Škurla

PhD Student

Jozef Barut

Research Intern

Michal Spiegel

Research Intern

Aneta Žugecová

Volunteer

Former members

Adam Naňo

Research Intern 6/2025-8/2025

Andrew Pulver

Research Intern 4/2025-8/2025

Ivan Novgorodtsev

Research Engineer 10/2022-06/2025

Matej Čief

PhD Student 09/2021-06/2025

Richard Bača

Research Intern 07/2024-09/2024

Tomáš Remiš

Research Intern 07/2023-08/2023, 07/2024-08/2024

Ivan Kačala

Research Engineer 01/2024-08/2024

Niranjanaa Udaya Kumar Sumitra

Research Engineer 11/2025-12/2025

Sneha Pareek

Research Intern 05/2024-07/2024

Roman Matúš Labuš

Research Intern 07/2023-07/2024

Jakub Fedorko

Research Engineer 09/2022-06/2024

Pavol Návrat

Researcher 09/2020-06/2024

Martin Melišek

Research Intern 03/2022-05/2024

Rastislav Papšo

PhD Student 09/2022-12/2023

Ivan Agarský

PhD Student 09/2022-10/2023

Timotej Smoleň

Research Intern 06/2022-04/2023

Timo Hromádka

Research Intern 07/2022-01/2023

Matúš Tomlein

Researcher 10/2020-04/2022

Elena Štefancová

Researcher 10/2020-08/2021

Research & Innovation Projects

CEDMO 2.0: Central European Digital Media Observatory

In the wake of escalating disinformation challenges across Central Europe, CEDMO 2.0 emerges as a strategic initiative of government, media, industry and NGO entities. Building upon the success of its…

vera.ai: VERification Assisted by Artificial Intelligence

vera.ai is a Horizon Europe project aimed at basic and applied research of AI methods to fight false information. The vera.ai project focuses on textual, multilingual and multimodal content, and…

AI-CODE: AI services for Continuous trust in emerging Digital Environments

AI-CODE is a Horizon Europe project aiming to research and develop novel generative-AI-based solutions dedicated to media professionals and thus support creation and dissemination of trustful and credible online content….

VIGILANT: Vital IntelliGence to Investigate ILlegAl DisiNformaTion

VIGILANT is a Horizon Europe project aimed at application of data collection and AI-based web content analysis methods to support police authorities in investigations of disinformation-related crime. In this project,…

Eyes4ICU: Eyes for Information, Communication and Understanding

Eyes4ICU is a Marie-Skłodowska-Curie Doctoral Network within the Horizon Europe program. A network of seven universities and research institutions trains 12 doctoral students. It is aimed at exploration of novel…

AI4Europe: The unified platform for boosting European AI academic and industrial research

KInIT joins forces with 23 prominent European institutions to build a better artificial intelligence platform supporting daily needs of academic and industrial AI researchers. In this project, we primarily focus…

DisAI: Improving scientific excellence of KInIT in AI and language technologies to fight disinformation

We succeeded in Horizon Europe’s Twinning scheme and joined forces with leading research institutions in natural language processing and disinformation combating. German Research Center for Artificial Intelligence (DFKI), University of…

ExU: AI Models for Examining Multilingual Disinformation Narratives and Understanding their Spread

Rumor stance classification and claim retrieval are vital in combating disinformation. They help assess information credibility by determining its stance on a claim. These tasks streamline fact-checking, making it efficient…

Selected publications

A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness

Pecher, B., Srba, I., Bielikova, M. – ACM Computing Surveys (ACM CSUR), August 2024

Pecher, B., Srba, I., Bielikova, M. Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning or few-shot learning, aims to effectively train a model using only a…

An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes

Tomlein, M., Pecher, B., Simko, J., Srba, I., Moro, R., Stefancova, E., Kompan, M., Hrckova, A., Podrouzek, J., Bielikova, M. – RecSys ’21: Fifteenth ACM Conference on Recommender Systems, 28 June 2021

The negative effects of misinformation filter bubbles in adaptive systems have been known to researchers for some time. Several studies investigated, most prominently on YouTube, how fast a user can…

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness

Cegin, J., Simko, J., Brusilovsky, P., – Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing,

The emergence of generative large language models (LLMs) raises the question: what will be its impact on crowdsourcing? Traditionally, crowdsourcing has been used for acquiring solutions to a wide variety…

MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark

Macko, D., Moro, R., Uchendu, A,, Lucas, J., Yamashita, M., Pikuliak, M., Srba, I., Le, T., Lee, D., Simko, J., Bielikova, M. – Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing – EMNLP 2023,

There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual…

Other notable publications

Auditing YouTube’s Recommendation Algorithm for Misinformation Filter Bubbles

Srba, I., Moro, R., Tomlein, M., Pecher, B., Simko, J., Stefancova, E., Kompan, M., Hrckova, A., Podrouzek, J., Gavornik, A., Bielikova, M. – ACM Transactions on Recommender Systems (ACM TORS), 2023

Addressing False Information and Abusive Language in Digital Space Using Intelligent Approaches

Machova, K., Srba, I., Sarnovsky, M., Paralic, J., Maslej Kresanova, V., Hrckova, A., Kompan, M., Simko, M., Blaho, R., Chuda, D., Bielikova, M., Navrat, P. – Towards Digital Intelligence Society. DISA 2020. Advances in Intelligent Systems and Computing. Springer, 2020

A study of fake news reading and annotating in social media context

Simko, J., Racsko, P., Tomlein, M., Hanakova, M, Moro, R., Bielikova, M. – New Review of Hypermedia and Multimedia, 9 February 2021

Analysis of selected regulations proposed by the European Commission and technological solutions in relation to the dissemination of disinformation and the behaviour of online platforms

Mesarcik, M., Moro, R., Kompan, M., Podrouzek, J., Simko, J., Bielikova, M. – Study prepared by KInIT based on an order from Miriam Lexmann, Member of the European Parliament. , 2022

Behavior-Based Customer Demography Prediction in E-Commerce

Urbancokova, V., Kompan, M., Trebulova, Z., Bielikova, M. – Journal of Electronic Commerce Research, 2020

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation

Cegin, J., Pecher, B., Simko, J., Srba, I., Bielikova, M., Brusilovsky, P. – Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) – ACL 2024,

Learning action embeddings for off-policy evaluation

Cief, M., Golebiowski, J., Schmidt, P., Abedjan, Z., Bekasov, A. – 46th European Conference on Information Retrieval,

Multilingual Previously Fact-Checked Claim Retrieval

Pikuliak, M., Srba, I., Moro, R., Hromadka, T., Smoleň, T., Melišek, M., Vykopal, I., Simko, J., Podroužek, J., Bielikova, M. – Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing – EMNLP 2023,

Tools

Monant: Universal and Extensible Platform for Monitoring Online Environment

To monitor online content, especially to tackle false information, KInIT internally develops a data collection platform called Monant. The primary aim of the Monant platform is to be a universal…

Web disinformation annotation tool

In order to create effective AI tools for tackling disinformation, one has to first collect reliable training data. For the Slovak language, datasets are lacking. Therefore, KInIT developed and maintains…

News

Our AI tools will support the Central European fact-checkers

The impact of disinformation in Central Europe became alarming during the COVID-19 pandemic and even more so after the start of the war in Ukraine in 2022. There are many…

Four successful Horizon Europe project proposals for KInIT

KInIT succeeded in two more Horizon Europe calls. We are thrilled to announce that another two projects were evaluated by the European Commission as projects with the highest rating and…

A unique solution to combat misinformation from Slovakia

Bratislava, 25.4.2022 – The strength, breadth and potential harmfulness of misinformation in the online environment have been especially noticeable during the COVID-19 pandemic and in connection with the war in…

IJCAI 2022: Highlights from the conference and its doctoral consortium

Branislav Pecher is one of our PhD students. He is a member of the Web & User Data Processing team where he focuses on machine learning models that involve only…

European Commission Representation in Slovakia: Discussion on legislation against disinformation

Online platforms have fundamentally changed the way we access information. According to the Reuters Institute study of 2021, 56% of respondents use social media as a news source in Slovakia….

Summer school from DeepMind: the one you shouldn’t miss if you are in the machine learning field

Matej Čief is one of our PhD students. He is a member of the Web & User Data Processing team where he focuses on recommender systems. At the beginning of…