When: Tuesday, April 24, 2018 from 15.00 to 16.30

Agenda: A general introduction to scraping, social data, APIs, and the collection of digital trace data. Includes an overview of INCA (Infrastructure for Content Analysis).
Presenters: Dr. Damian Trilling and Dr. Theo Araujo

This lecture is part of the general sessions on Machine Learning,  which will discuss Machine Learning, Big Data and related topics from a theoretical and methodological perspective. These sessions will provide an in-depth understanding of these methods, including retrieval of data via APIs and their analysis using supervised methods (e.g., classifiers) and unsupervised methods (e.g., topic models). We will show examples and reflect upon opportunities and limitations for communication research. Participants should, at the end of these sessions, have strong understanding of these methods, and the ability to decide whether, and if so, how to apply them into their own research lines, including how to take part in (or coordinate) projects that use these methods.