📍 Online-only event
🗓 May 12, 2020, 12:00-13:30 CET
This workshop contains material for the SSDL workshop on "Extracting Emotions (and more) from Faces with Face++ and Microsoft Azure" by Theresa Küntzler (University of Konstanz).
Images are an increasingly used data source in the social sciences. One application is to extract features from human faces using machine learning algorithms. This workshop will provide a guide on how to use APIs for this task, specifically how to access the services offered by Face++ and the Microsoft Face API. While the talk focuses on extracting emotions from facial expressions, the method can also be used for other variables of interest such as gender or age. The talk starts with a short introduction on why we should care about emotions in social sciences, why APIs are useful for the task of facial expression recognition and where to apply caution with this method. The main part will be a walkthrough, to show (1) how to gain API access credentials, (2) how to call the API from R and (3) how to handle the output.
Theresa Küntzler is PhD candidate at the Graduate School of Decision Sciences at the University of Konstanz. She specializes in information processing and statistical analysis. Her research focuses on the role the of emotions in politics, especially in election behaviour.