Comparative Analysis of Machine Learning Algorithms for Emotion Classification
Ashish Deshmukh, Aniket Dhage, Ritika Gadapa, Sanika Butle, Anuradha Yenkikar, Nilesh P. Sable · 2024
In this generation, social media platforms such as Twitter, Instagram and also e-commerce websites have become an integral part of our society. Social media is used for communication and it is also a platform where the users can express their thoughts and feelings. Also, users share their reviews on e-commerce websites. To analyze what exactly is the emotion of the user our machine learning models explores the sentiment analysis techniques for predicting emotions from the given text data. It follows a series of steps, starting with importing libraries, acquiring datasets, visualization, pre-processing, and model building. The data is used to train on a variety of models, including LSTM, Naive Bayes, Random Forest, Gradient Boosting, and SVM. The performance of each model is evaluated using metrics like accuracy, precision, recall, and F1-score. Comparative analysis is conducted to determine the most effective model for emotion prediction. Furthermore, the research investigates emotion prediction for huge datasets and provides a procedure for exporting trained models for future usage. It provides insights into the performance of various machine learning algorithms in sentiment analysis, hence contributing to the understanding and interpreting emotions from textual data on various platforms.