Using social media mining for estimating theory of planned behaviour parameters

Abstract

In this position paper we present the scenario of making interventions for increasing the classical music concert-going behaviour of end users. Within the FP7 Phenicx project we are developing a personalized persuasive system that attempts at changing the concert-going behaviour of users. The system is based on the theory of planned behaviour user model for predicting whether a user will attend a concert or not. Our goal is to develop a machine learning algorithm that will extract the user model parameters unobtrusively from the micro-blogs of the users. We plan to perform a user study to build the training dataset and to test the system on real users within the project.