Sender Context in Contemporary Emotion Recognition Systems and Databases: a Systematic Review

Exploring the use of Personal Details for Recognizing Emotions

Bachelor Thesis (2026)
Author(s)

C. Vasilev (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

B.J.W. Dudzik – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

S. Mukherjee – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

S. Tan – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2026
Language
English
Graduation Date
22-06-2026
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
11
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Recent studies on emotion recognition have extensively recorded the unreliability of recognizing emotions using only facial features of a target expressor of emotion. As a response, context-aware emotion recognition (CAER) systems have become more prevalent in contemporary emotion recognition research. This systematic review focuses on context related to the expressors of emotions, also known as senders. Such context includes age, culture and personality. More specifically this study examines how this context is represented in contemporary emotion-recognition datasets and how well it is integrated into CAER systems. Studies were collected from different literature databases and filtered using a hybrid AI-assisted and manual screening process. The results were limited to only papers from 2019 to prevent overlap with previous studies in this field. Only 8 such papers were found and included in the study. From these results a clear gap was found between the sender-context information available in datasets and its exploitation in recognition systems. Additionally, fairness was identified as a blind-spot in both databases and systems.

Files

Christo_Vasilev_Final.pdf
(pdf | 0.536 Mb)
License info not available