Psychologically-driven Personalization

Abstract:
In this talk we will present our research in the domain of psychologically-driven personalized systems. In order to be truly personalized a system needs to understand the user. Current systems employ data-driven models, such as recommendations based on past ratings, clicks or purchases. However, psychologically-grounded models appear to have potential for better personalized systems. We will cover models of emotions and personality, the unobtrusive acquisition thereof through social media crawling, video processing and machine learning and their use in personalization algorithms.

Short Bio:
Marko Tkalčič is Assistant Professor at the Faculty of Computer Science at the Free University in Bolzano, Italy. He received his PhD from the Faculty of Electrical Engineering at the University of Ljubljana in 2011. After a postdoc at the University of Ljubljana, he worked as a postdoc at the Johannes Kepler University in Linz, Austria from 2013 to 2015. From 2016 he is with the Free University of Bolzano. His research explores ways in which psychologically-motivated user characteristics, such as emotions and personality, can be used to improve personalized systems. It employs methods such as user studies and machine learning.

The seminar will be held in English.