This monthly event will take place at Centre Marc Bloch in Stadtmitte and will be aimed at scholars in the Berlin/Brandenburg area interested in issues related to computational social science and is also thought as an opportunity to foster a local community in this regard.
For the first session, on Wednesday April 6th, from 5 to 6pm, to be followed by a buffet, we will receive Julien Velcin and Gaël Poux-Médard on “Different ways for modeling time with textual data” (see details below).
The program for this year will be finalized soon. If you are interested in hearing about upcoming sessions, you can subscribe to our mailing list by sending an email to css-seminar-subscribe@cmb.hu-berlin.de. You will receive a first email from the mailing list, which you will need to confirm to finalise the subscription process.
Seminar series in Computational Social Science – Centre Marc Bloch Berlin
Session 1: Wed April 6th, 5-6pm, Centre Marc Bloch, Friedrichstr 191 Berlin, (U Stadtmitte), Georg-Simmel Room, 3rd floor.
Different ways for modeling time with textual data
Julien Velcin and Gaël Poux-Médard (Lyon)
Textual corpora are usually not static over time: as new documents get published (e.g., news, scientific articles, tweets), topics of interest may change. Describing their rise and fall over time has generated substantial research over the last decade. Better, it turns out that considering the temporal dimension of textual modeling improves the automated description of these corpora.
Over the years, researchers of the ERIC lab have developed several models to explore this paradigm. Early works simply run static models on different time slices. More elaborate approaches consider that models estimated on each time slice are not independent from each other. Even more elaborate approaches go further, get rid of time discretization and model time as a continuous variable along with textual content.
Our talk will present an overview of these approaches, also illustrating our lab’s recent progresses in this regard – especially in terms of tracking topics over time or for studying how pieces of information interact to trigger new information on social media.
About the speakers
Julien VELCIN (@jvelcin)
Julien Velcin is Professor of Computer Science at the University Lumière Lyon 2 (France). He works at the ERIC Lab in the Data Mining & Decision team on topics related to artificial intelligence, machine learning and natural language processing. More precisely, his research aims at designing new models and algorithms to deal with information networks. One of his favorite application field is the analysis of topics and opinion that flow through the social media.
Gaël POUX-MÉDARD
Gaël Poux-Médard obtained a bachelor in physics at the University Lyon 1 (France), and two M.Sc degrees in “Physics of complex systems” and in “Digital Humanities” at the Ecole Normale Supérieure (ENS) of Lyon in 2019. He worked as intern at the Università Rovira i Virgilli (Tarragona, Spain) and at the CNR-ISC (Rome, Italy). Then, he started a PhD in Computer Science on “interactions in information spread” at the University Lyon 2.