Data Mining & Opinion Dynamics. Methods and Challenges


25 janvier 2019    
09:30 - 17:00



H2020 Odycceus Workshop

The meeting takes place in salle du Conseil (5th floor)
[register before January 22nd]

Social media and the digitization of news and discussion fora are having far-reaching effects on the way individuals and communities communicate, organize, and express themselves. Can the information circulating on these platforms be tapped to better understand and analyse the enormous problems facing our contemporary society? Could this help us to better monitor the growing number of social crises due to cultural differences and diverging world-views? Would this facilitate early detection and perhaps even ways to resolve conflicts before they lead to violence? The H2020 ODYCCEUS project answers all these questions affirmatively. This project aims at developing the conceptual foundations, methodologies, and tools to translate this bold vision into reality and demonstrate its power in a large number of cases. This workshop will focus on two main issues underlying this project: methods and impact.
The morning section will focus on the methods. In particular, the workshop aims at discussing the potential combination of text mining and text analysis for the study of opinion dynamics. The development of digital media sources, of web 2.0 arena and of social media invites to consider new methods for the analysis of heterogeneous corpora, massive data and loosely structured texts. A better integration of text mining and text analysis methods is necessary in order to develop a substantial understanding of social and cultural discourse productions in the digital sphere.
The afternoon section will focus on the challenges and perspectives of studies of opinion dynamics base on data mining, especially with data extracted from the web. In recent years, several laboratories (often called Media Labs) have concentrated their activities mainly on building tools and methods for optimizing this kind of analysis and for generating studies useful for the researcher as well as for the decision maker. A round table will gather researchers that are carrying out leading initiatives in this field. They will be invited to briefly present their activities and exchange between them and with the public about the main challenges and perspectives of this innovative research field connecting the scientist, the politician and the citizen.

Text Mining and Text Analysis. Opening Up Integrated Methods for Studying Opinion Dynamics

9:15am Opening remarks
9:30am First session

– How does this make you feel? Using common-sense knowledge to link events to the emotional reaction they may trigger – Alexandra Balahur (European Media Monitor, Joint Research Centre, European Commission, Ispra)
– The Combination of Qualitative and Quantitative Methods to the Safeguarding of the Intangible Heritage: the Case of Textiles and Mining – Eric Kergosien (EA GERiiCO, University of Lille)

10:50am Second session

– Extracting Semantic Frames – Katrien Beuls (Artificial Intelligence Lab, VUB, Brussels)
– History and Digital Text Analysis – Massimo Warglien & Rocco Tripodi (Department of Management, University of Venice Ca’ Foscari)
– Space-Time Analysis in the News – Claude Grasland (CIST, University Paris Diderot, Paris)

11h50 Concluding remarks

Justus Uitermark (Faculty of Social and Behavioural Sciences, UvA, Amsterdam)

Data Mining for Studying Opinion Dynamics. Challenges and Perspectives

2pm Opening remarks

Presentation of the H2020 Odycceus, Eckehard Olbrich, Max Planck Institute, Leipzig

2:30pm Round Table

Chair: Luc Steels, University of Venice Ca’ Foscari
Alexandra Balahur, European Media Monitor
Dominique Cardon, Director, Media Lab, Sciences Po Paris
Jean Carrive, Research Lab, Institut National de l’Audiovisuel (French National Audiovisual Institute)
Denis Teyssou, Responsable, Media Lab, Agence France Presse

4pm Discussion with the participants
5pm End of meeting