Turkish Presidential Elections TRT Publicity Speech Facial Expression Analysis

TL;DR

This study analyzes facial expressions of Turkish presidential candidates during speeches using FaceReader and 3D modeling, providing publicly available data for research.

Contribution

It introduces a method for detailed facial expression analysis during speeches using 3D modeling and makes the data publicly accessible.

Findings

Facial expressions were successfully tracked during speeches.

Over 500 landmark points were analyzed for each candidate.

The data and videos are publicly available for further research.

Abstract

In this paper, facial expressions of the three Turkish presidential candidates Demirtas, Erdogan and Ihsanoglu (in alphabetical order) are analyzed during the publicity speeches featured at TRT (Turkish Radio and Television) on 03.08.2014. FaceReader is used for the analysis where 3D modeling of the face is achieved using the active appearance models (AAM). Over 500 landmark points are tracked and analyzed for obtaining the facial expressions during the whole speech. All source videos and the data are publicly available for research purposes.