Data Science Group


  1. Prof. Przemysław Kazienko – leader
  2. Prof. Boleslaw Szymanski, RPI – Rensselaer Polytechnic Institute, USA ( – visiting professor, 2014-17
  3. prof. Adam Wierzbicki, Polish-Japanese Academy of Information Technology – visiting professor, 2015-16  (
  4. prof. Mikołaj Morzy, Poznan University of Technology – visiting professor, 2015-16 (
  5. Dr. Tomasz Kajdanowicz, post doc
  6. Dr. Piotr Bródka, post doc
  7. Dr. Radosław Michalski, post doc
  8. Dr. Jarosław Jankowski, external researcher, West Pomeranian University of Technology, Szczecin,
  9. Dr. Piotr Szymański
  10. Stanisław Saganowski, PhD student
  11. Łukasz Augustyniak, PhD student
  12. Włodzimierz Tuligłowicz, PhD student
  13. Adrian Popiel, PhD student
  14. Marcin Kulisiewicz, PhD student
  15. Roman Bartusiak, PhD student
  16. Monika Rok MSc, office

Research areas

  1. Complex Networks / Network Science
  2. Social Network Analysis (SNA)
  3. Big Data and Data Mining (DM); their industrial applications, e.g. in finances, telecommunication, medicine, trade, etc.
  4. Machine learning (ML)
  5. Classification, collective classification, relational machine learning, machine learning for networks
  6. Clustering, social community detection and evolution
  7. Multi-layer networks
  8. Diffusion processes, spread of influence
  9. Temporal Networks
  10. Sentiment Analysis
  11. Parallel processing for big data
  12. Decision support systems in medicine


  1. Analysis of data adjusted to specific domains, e.g. finances, medicine, telecommunication, commerce, including distributed, stream and large-scale environments (Big Data)
  2. Decision Support Systems (DSS)
  3. Social network analysis (SNA)
  4. Sentiment analysis and media analytics
  5. Computational social science

Significant results

Social network analysis, network-data analysis
  • A survey on social networks on the Internet
  • Application of social networks to latent knowledge acquisition in organisations
  • A GED method for identification changes in social communities evolution; prediction of evolutionary changes
  • A method for extraction of multi-layered social networks from activity data
  • Various parallel methods for large graph processing
  • Analysis of neighbourhoods in multi-layered social networks
Diffusion processes, spread of influence
  • The novel tInf method for maximizing the spread of influence in temporal social networks
  • Analysis of viral campaigns in social networks
Relational machine learning
  • Relational classification for networks using label-dependent and label-independent features
  • Relational classification for multi-layered networks with information fusion
  • Active learning and inference for classification in networks
  • Competence region modelling in relational classification
Machine learning: multi-label classification
  • A method for boosting-based multi-label classification
  • Multi-label classification using error correcting output codes
  • Classifier chains in multi-label classification
Applications of data science
  • Sentiment analysis for social media (media)
  • Algorithms for xDSL services pre-qualification (telecom)
  • Big data in banking (finances)
  • Valuation of debt portfolio (finances)
  • A relational large scale multi-label classification method for video categorization (media)
  • Social Recommender System using Multidimensional Social Network (media)
  • Evaluation of organization structure based on human communication (management)
  • Social value dynamics in customer churn (telecom)
  • Decision support systems for primary health care based on multi-population data (medicine)