SENTIMENT ANALYSIS ON TWITTER WITH RANDOM FOREST CLASSIFIER ALGORITHM

Abstract

Abstract— Social media platforms like Twitter have become valuable sources for sentiment analysis due to the vast amount of user-generated content. In this project, we propose a sentiment analysis framework using the Random Forest machine learning algorithm to classify tweets into positive, negative, or neutral sentiments. The framework involves preprocessing steps such as tokenization, stop-word removal, and stemming to clean the text data. Then, features are extracted from the preprocessed tweets, including bag-of-words representations and TF-IDF vectors. These features are used to train a Random Forest classifier, which learns to predict the sentiment of new tweets. Twitter sentiment analysis has gained significant attention for its applications in various domains such as marketing, public opinion mining, and brand reputation management. Sentiment analysis involves the use of natural language processing (NLP) techniques to automatically determine the sentiment expressed in a given text, such as positive, negative, or neutral. The proposed framework leverages the ensemble learning capabilities of Random Forest to handle high-dimensional feature spaces and non-linear relationships between tweet features and sentiments. By utilizing a large dataset of labeled tweets, the model learns to capture subtle nuances in language and context, enabling it to accurately classify sentiment even in noisy and ambiguous text. The performance of the model is evaluated using metrics like accuracy, precision, recall, and F1-score. Our experimental results demonstrate the effectiveness of the Random Forest algorithm in accurately classifying sentiment in Twitter data, making it a promising approach for sentiment analysis tasks.