Publication Date

Fall 2023

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)


Computer Science

First Advisor

Nada Attar

Second Advisor

Reem Albaghli

Third Advisor

Faranak Abri


Refugee Bias, Eye-Tracking Study, Ethnic Prejudice, Human-Computer Interaction, Facial Feature Influence, Implicit Bias Detection


The challenges that refugees in various regions encounter are common knowledge. One such challenge is a bias among refugees on ethnocentric grounds. In particular, there are various articles that have pointed out the struggles faced by Syrian refugees in countries like Europe as a result of implicit bias. In fact, the media coverage of Syrian crises and the government responses to the same shed negative light on the refugees themselves. On the contrary, the media coverage of Ukrainian crises is very different with lesser restrictions from the governments.

This research attempts to identify the extent of implicit bias between Ukrainian and Syrian refugees among people. Using eye-tracking equipment, we assessed participants’ decisions in specific situations and analyzed the obtained pupil size to understand their inclination towards refugees from respective backgrounds. We utilized original images of refugees from both countries and Ordinary Procrustes Analysis (OPA) to manipulate other images through face swapping before or during tasks. Our study examined whether participants demonstrated biases towards refugees observed in the media and if face swapping influenced their decisions. The results showed that participants donated more when presented with authentic information about real individuals and did not display bias towards a specific ethnicity. We found a positive correlation between pupil size and donation amount when participants viewed real refugee images, but no correlation when the face was swapped before or during the task. This study provides insight into measuring biases and encourages thoughtful interaction with images of refugees as a stimulus.

Available for download on Friday, December 20, 2024