Petra's picture

Petra Kralj Novak

PhD, Assistant professor at Central European University, Wien, Austria and researcher at the Department of Knowledge Technologies, Jožef Stefan Institute

See my other web page at Department of Network and Data Science at Central European University.

Short CV

I am an assistant professor at the Department of Network and Data Science at Central European University, Wien, Austria and a part time researcher at the Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia. I am secretary and treasurer of the EurAI member society SLAIS – Slovenian Artificial Intelligence Society (2007-2009, 2018-).

My research belongs to the wide area of knowledge discovery from databases. I started working in this field in 2005, with my BSc in Computer and information science form University of Ljubljana, Slovenia. I received my PhD at the Jožef Stefan International Postgraduate School in Slovenia in 2009 under the supervision of prof. Nada Lavrač. The main findings of my thesis entitled Supervised Descriptive Rule Induction are published in Journal of Machine Learning Research and in Encyclopedia of Machine Learning.

My current research focuses on social media analysis. I combine machile nearning techniques with network analysis to investigate the sentiment and hate speech of online informal messages. Avant-garde research in analyzing the role of emojis in conveying sentiment was published in P. Kralj Novak, et al. "Sentiment of emojis" (2015) and is the main reference for current research in the analysis of emoji. I gave invited talks at scientific, industrial, and educational institutions and events on three continents.

I collaborated in several national (Slovenian) and European research projects. I am the coordinator of the European Union REC AG project IMSyPP: Innovative Monitoring Systems and Prevention Policies of Online Hate Speech (2020-2022). I act as a reviewer of European projects and I am a member of the expert group at DGCNECT for the preparation of a research agenda in the field of "Digital media and human well-being".

I have participated in the organization of several scientific events in Slovenia and abroad. I am co-chairing the program committee of the ECML PKDD 2022 (The European Conference on Machine Learning & Principlesand Practice of Knowledge Discovery in Databases), Grenoble, France. I was program committee co-chair of Discovery Science 2018, and I am guest editing a Machine Learning Journal special issue.



  • Round table: Regulacija neprimernega govora na družbenih omrežjih, University of Ljubljana, May 20, 2021
  • Tackling hate speech on Slovenian Twitter: invited talk at Language Technology vs. Disinformation, organized by DG Connect, November 24, 2020
  • Complex Networks with Texts, NetSci2020 school, September 17, 2020
  • Sentiment and stance analysis of social media : invited talk at Data and Complexity Day @Ca'Foscari Conference, November 12, 2018, Venice, Italy.
  • Social media stance mining applications : invited talk at Southern Data Science Conference, April 14, 2018, Atlanta, GA, USA.
  • Deep learning for natural language sentiment and affect: tutorial at ECML PKDD 2018, September 14th, 2018, Dublin, Ireland.
  • Social media stance mining applications : invited talk at Southern Data Science Conference, October 18, 2018, Orlando, Florida, USA.
  • Emojis, sentiment and stance in social media : invited talk at 21st International Conference, DS 2018 Limassol, Cyprus, October 29-31, 2018.
  • Sentiment of emojis : invited talk at the 4th Conference on CMC and Social Media Corpora for the Humanities, 27-28 September 2016, Ljubljana, Slovenia.

Selected publications ( Google Scholar | COBISS)

  • Petra Kralj Novak, Jasmina Smailović, Borut Sluban, Igor Mozetič
  • Sentiment of Emojis
  • PLoS ONE 10(12): e0144296, doi:10.1371/journal.pone.0144296, 2015
  • Fabiana Zollo, Petra Kralj Novak, Michela Del Vicario, Alessandro Bessi, Igor Mozetič, Antonio Scala, Guido Caldarelli, Walter Quattrociocchi
  • Emotional dynamics in the age of misinformation
  • PLoS ONE 10(9): e0138740. doi:10.1371/journal.pone.0138740, 2015