Ontology-Based Method for Analysis of Inconsistency Factors in Emotion Recognition

Presenter Information

Teresa Zawadzka, Faculty of Electronics, Telecommunications and Informatics and Digital Technologies Center, Gdansk University of Technology, PolandFollow
Wojciech Waloszek, Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, PolandFollow
Michał Zawadzki, Independent Researcher, Gdansk, PolandFollow

Abstract

In the paper the problem of inconsistency in emotion recognition is approached. One of the existing challenges is the exploration of factors, which can influence the inconsistency. Therefore the aim of the paper is to present a method that allows capturing knowledge of what factors and what values of these factors influence the inconsistencies between recognized emotional states. The high-level, semi-automatic method allowing to recognize these factors is presented. The input of the method is the structured dataset and the output is the set of rules identifying when recognized emotional states are consistent or not. The presented method is validated for the dataset prepared for emotion recognition from face expressions using various methods.

Recommended Citation

Zawadzka, T., Waloszek, W., & Zawadzki, M. (2023). Ontology-Based Method for Analysis of Inconsistency Factors in Emotion Recognition. In A. R. da Silva, M. M. da Silva, J. Estima, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Information Systems Development, Organizational Aspects and Societal Trends (ISD2023 Proceedings). Lisbon, Portugal: Instituto Superior Técnico. ISBN: 978-989-33-5509-1. https://doi.org/10.62036/ISD.2023.48

Paper Type

Poster

DOI

10.62036/ISD.2023.48