SentiNet: A Word-Cloud based approach towards Social Media Sentiment Analysis

Sentiment analysis of Twitter data has become an important tool for businesses, organizations, and individuals to understand public opinions and make informed decisions. This study offers a thorough examination of sentiment analysis methods used on dataset of tweets. The intent is to reliably classify tweets as positive or negative by utilizing advanced natural language processing and machine learning approaches. The goal is to provide a useful tool for businesses, researchers, and social media managers to analyze the sentiment of tweets related to their brand or events and make informed decisions based on the analysis. Data preprocessing, feature extraction using BOW, and the use of many machine learning models, such as K-Nearest Neighbours, Decision Trees, Random Forest, Naive Bayes, and LSTM, for sentiment classification are all part of the suggested methodology. The findings of the study highlight the efficacy of sentiment analysis in determining tweet's sentiments and underscore its potential for informing targeted marketing strategies and customer relationship management in the business sector. Additionally, the paper discusses potential future research directions, emphasizing the need for integrating more sophisticated deep learning models and exploring aspect-based sentiment analysis to provide comprehensive insights.