Thesis Abstract

Abstract
The rise of social media platforms has led to an explosion of user-generated content, providing a vast amount of data that can be analyzed to gain valuable insights into public opinions, sentiments, and trends. Sentiment analysis, a subfield of natural language processing, aims to computationally identify and extract subjective information from text data. In this thesis, we focus on the development of a machine learning algorithm for sentiment analysis in social media data. The objective of this research is to create a robust and accurate sentiment analysis algorithm that can effectively process the unstructured text data obtained from social media platforms. To achieve this goal, we first conduct a comprehensive literature review to explore existing techniques and methodologies in sentiment analysis, machine learning, and natural language processing. The literature review serves as the foundation for the development of our algorithm. In the research methodology chapter, we outline the process of data collection, preprocessing, feature extraction, model selection, training, and evaluation. We discuss the various machine learning algorithms considered for sentiment analysis, such as Support Vector Machines, Naive Bayes, and Recurrent Neural Networks. We also explore the use of word embeddings and sentiment lexicons to enhance the performance of the algorithm. In the discussion of findings chapter, we present the results of experiments conducted on a real-world social media dataset. We evaluate the performance of our algorithm in terms of accuracy, precision, recall, and F1 score. We compare the results with baseline models and analyze the strengths and limitations of our approach. Finally, in the conclusion and summary chapter, we provide a summary of the key findings, discuss the implications of the research, and suggest areas for future work. We highlight the significance of developing a reliable sentiment analysis algorithm for social media data and its potential applications in marketing, customer feedback analysis, and social listening. Overall, this thesis contributes to the field of sentiment analysis by proposing a novel machine learning algorithm tailored for analyzing sentiments in social media data. The research findings demonstrate the feasibility and effectiveness of the proposed approach, paving the way for further advancements in sentiment analysis techniques for social media analytics.

Thesis Overview