Tools
Tools
Ali, Nouman (2024) Sentiment Analysis Using Text and Facial Emotions. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (937kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Sentiment analysis, an important area in natural language processing and computer vision, is focused on the problem of understanding emotions in textual and visual data. Specifically, this report focuses on the multimodal sentiment analysis (MSA) approach based on text and face data for sentiment classification. The global sentiment analysis market is currently at 3.3 billion dollars and expected to grow at 14.8% through 2027 emphasizing its need in fields. This study explores traditional and advanced models: DTs, RFs, RNNs, BiLSTMs have been employed for text analysis using TF-IDF and CNNs with pretrained ResNet50V2 for FER. Findings show that Random Forest yielded the highest accuracy of 71.1% and ResNet50V2 yielded the best prediction accuracy of 60.13% in text classification and facial sentiment detection, respectively. Consequently, the study points at the possibility of enhancing sentiment prediction through the integration of modalities. Further studies need to be conducted to improve results interpretability, as well as expand fusion methods, generative models, and real-time systems.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Trinh, Anh Duong UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing B Philosophy. Psychology. Religion > Psychology > Emotions Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Artificial Intelligence |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 19 Jun 2025 15:20 |
| Last Modified: | 19 Jun 2025 15:20 |
| URI: | https://norma.ncirl.ie/id/eprint/7941 |
Actions (login required)
 |
View Item |