Tools
Tools
Dhawan, Samarth Krishna (2022) Machine Learning Framework For Predicting Empathy Using Eye Tracking and Facial Expressions. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Empathy is one of the most important human emotion that facilitates a bond. This research provides a novel machine learning framework that combines eye tracking and facial expressions to predict empathy. The objective of this research is to help with recruitment of highly empathetic people in the medical and psychology domain for more empahtetic nurses and therapists. Features used were heatmaps from eye tracking and emotion detection from facial expressions were extracted which were given as inputs along age, sex, memory test score, blink percentage, blink mean, blink standard deviation, saccade percentage, saccade mean, saccade, average distance from left eye and average distance from right eye standard deviation to 3 machine learning models; Random Forest, Gradient Boosting and Logistic Regression. Logistic regression outperformed the other models with an F1-score of 0.74 while, Gradient boosting was the worst performing model with an F1-score of 0.4 and Random Forest had an F1-score of 0.5. YOLOv5 and Principal Component Analysis were also used to prepare the data and extract the right features for this model.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science B Philosophy. Psychology. Religion > Psychology > Emotions R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 24 Jan 2023 11:39 |
| Last Modified: | 03 Mar 2023 16:46 |
| URI: | https://norma.ncirl.ie/id/eprint/6109 |
Actions (login required)
 |
View Item |