Decoding Twitter: Sentiment Analysis with Machine Learning
VIVEK KUMAR YADAV · International Journal For Multidisciplinary Research · 2024
This research undertakes a comprehensive examination of sentiment analysis on Twitter, leveraging the power of machine learning methodologies. With a focus on decoding the intricate landscape of emotions within the Twitterverse, the study aims to provide valuable insights into understanding sentiments expressed in this dynamic social media platform. The primary objective is to employ machine learning techniques to unravel the underlying sentiments, encompassing positive, negative, and neutral tones within the brevity of Twitter communication. The methodology involves the collection of a diverse dataset of tweets, followed by meticulous preprocessing steps to handle noise, eliminate irrelevant information, and perform tokenization. Feature extraction techniques, such as TF-IDF, are employed to convert textual data into numerical vectors, facilitating the subsequent application of various machine learning models. These models, ranging from traditional approaches like Naive Bayes to advanced ones like Support Vector Machines, are implemented and rigorously evaluated based on key performance metrics such as accuracy, precision, recall, and F1 score.