Tools
Tools
Sardana, Bhumika (2023) Sentimental analysis for Hinenglish-code mixed data using advanced word embeddings. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (2MB) | Preview |
Abstract
This study investigates the usefulness of combining machine learning models for sentiment analysis with coded mixed language. It primarily focuses on the Hindi and English language commonly referred to as ’Hinglish’.
This research addresses the application of novel neural network architectures, such as convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. It focuses on better interpretation of text in Hinglish texts. This paper shows how these advanced models and traditional NLP techniques such as TF-IDF vectorization improve the accuracy of emotion classification using comprehensive datasets. This shows that it significantly improves the performance by the combination proposed. This result highlights the superiority of certain embeddings such as her MURIL and BERT in processing code-mixed languages and provides insight into their context understanding abilities.
Overall, this study also shows practical implications for improving sentiment analysis tools. It could help to be more inclusive of linguistically diverse environments.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Tomer, Vikas 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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 21 May 2025 10:50 |
| Last Modified: | 21 May 2025 10:50 |
| URI: | https://norma.ncirl.ie/id/eprint/7602 |
Actions (login required)
 |
View Item |