Deriving and Presenting Insights from Experience Sampling Method (ESM) Data Through Network Visualization

Bachelor Thesis (2025)
Author(s)

A. Gajdos (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Esra Cemre Su de Groot – Mentor (TU Delft - Web Information Systems)

W.P. Brinkman – Graduation committee member (TU Delft - Interactive Intelligence)

Reginald Lagendijk – Graduation committee member (TU Delft - Cyber Security)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
27-06-2025
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
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

Experience Sampling Method (ESM) has emerged as a technique for capturing real-time mental health data in natural environments, offering advantages over traditional retrospective assessments by reducing recall bias and providing contextual understanding of emotional patterns. Despite its benefits, ESM remains underutilized due to limited tools for transforming complex datasets into interpretable insights for clinicians and patients. This study developed and evaluated a network graph visualization to represent behavior-emotion relationships from ESM data. Six mental health practitioners evaluated the system through structured surveys assessing usability, clinical relevance, and interpretive capability. Participants rated visualization intuitiveness at 3.8/7 and visual design at 3.2/5. Comparative evaluations were mixed, with participants rating the approach as better (n=2), equivalent (n=2), worse (n=1), or much worse (n=1) than traditional methods. Despite usability challenges related to visual complexity and dynamic node movement, participants successfully extracted clinically relevant behavior-emotion patterns. Color coding was the most effective design element, while interactive filtering functionality was crucial for pattern recognition. Network visualization shows potential for making ESM data more accessible to mental health practitioners, though design refinements addressing visual complexity and temporal dynamics integration are needed to improve clinical utility.

Files

Research_paper.pdf
(pdf | 0.419 Mb)
License info not available