Tools
Tools
Patil, Rajat (2023) Exploring Deep Learning Models for Sentiment Analysis on Tesla News. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Sentiment analysis has been a significant area of research in natural language processing, and selecting the appropriate model is crucial. Three major models—the Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN)—as well as experimentation with various grams will be used in this thesis as classifiers for the Lexicon Bert model (LeBERT). It was discovered that LSTM was exhibiting encouraging results for the Trigram and CNN for the Unigram and bigram after closely examining the model accuracy data. Overall, it was shown that the CNN model combined with the leBERT model as a classifier provided a flexible alternative with a wider range of gram configurations. For sentiment analysis tasks, the model’s flexibility is essential. The results show that CNN works well for sentiment analysis. This thesis will offer significant new perspectives in the field of sentiment analysis.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Subhnil, Shubham UNSPECIFIED |
| Uncontrolled Keywords: | Sentiment analysis; NLP; LeBERT; LSTM; RNN; CNN; Unigram; Bigram; Trigram |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Motor Industry |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 20 May 2025 13:13 |
| Last Modified: | 20 May 2025 13:13 |
| URI: | https://norma.ncirl.ie/id/eprint/7585 |
Actions (login required)
 |
View Item |