Supervisor
Dr. Muhammad Iqbal
Programme
MSc in Data Analytics
Subject
Computer Science
Department
Computer Science
Abstract
This study explores the combination of sentiment analysis with vader-lexicon and semantic analysis with latent dirichlet allocation to identify real-life events, particularly in the context of Twitter datasets. While sentiment analysis alone may not provide accurate guidance, the inclusion of semantic analysis enhances the research process by helping to identify relevant news articles and comprehend brand perception on social media. Furthermore, the study fine-tunes the RoBERTa model specifically for question-answering tasks
Date of Award
Spring 5-2024
Full Publication Date
5-2024
Access Rights
open access
Document Type
Capstone Project
Resource Type
thesis
Recommended Citation
Timur, Kagan, "Data Analysis of Twitter’s Nasdaq100 Sentiments and Topics as Indicators for News Articles Retrieval: Fine-Tuning RoBERTa and RAG" (2024). ICT. 48.
https://arc.cct.ie/ict/48