Twitter Sentiment Analysis Techniques

Nowadays, social media networks are used by people incredibly frequently. They write articles, send private and public messages, pictures, and videos. In the realm of social networking, Tweeter is one of the most well-liked and often used social networks. Because of this, it's crucial to examine tweets in order to comprehend how people respond to a particular topic. For a variety of reasons, including corporate marketing, politics, studying public behavior, and data collection, it is essential to comprehend the emotion of tweets. Opinion study of Twitter text can help politicians and marketers better grasp how customers react to new product launches and marketing efforts. Particularly, Twitter is kind of the select few public sites where persons go for trustworthy data and is frequently used authoritatively by many people. This work uses a number of machine learning techniques to analyze tweets for sentiment using the terms in the tweets as input. The dataset that was used came from Kaggle. With layers for CNN, LSTM, BILSTM, and embedding, a deep learning model has been created. As part of the analysis, Support Vector Machine (SVM), K Nearest Neighbor (KNN), Logistic Regression, Decision-Tree, Random Forest Method, and a deep learning architecture were used