Summer School on Methods for Computational Social Science

I just arrived home after an incredible week in Sant’Antioco for the Summer School on Methods for Computational Social Science. This was the first edition of a series of three and focused on methods for capturing, analyzing and modeling digital trace data. The agenda, perfectly designed by Claudia Wagner, Nicola Perra, and David Brodesser, included very motivating keynotes and lectures by excellent computational social scientists (e.g. Alex Vespignani, Ciro CatuttoTina Eliassi-Rad, Ancsa Hannák, Rossano Schifanella, Milena Tsvetkova, Bruno Ribeiro or Andrea Baronchelli) and very nice social events in beautiful locations which really helped socialize with old and new colleagues.

Photo: Olga Zagorova

Participants also had to applied concepts from keynotes/lectures within a small group project. My group with Raquel Rosés, Richard Janis Goldschmidt, Matteo Ottaviani and Matteo Manca decided to address the Andrea Baronchelli’s proposal: The dynamics of a social convention. This proposal was motivated by the increasing attention that Bitcoin has received and originally aimed to correlate the price of Bitcoin with mainstream and social media signals (Google Trends, Wikipedia, etc). Given that we found some previous studies in this direction, we opted to use these social media signals to speculate in the Bitcoin market with a state of the art model to anticipate stock market movements with data from Google and Wikipedia. Our results were clear and aligned with the motto of the Summer School: avoid data-driven actions with no theoretical basis 😃

One thought on “Summer School on Methods for Computational Social Science

  1. Pingback: SocInfo2017

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s