SENTIMENT ANALYSIS ON COMMENT USING MACHINE LEARNING

Computer Engineering

In this work, I present a methodology that uses social media to analyze a person's sentiment and emotion. Face-book is utilizing machine learning. This initiative will assist them in understanding their situation and improving their emotional stability. The goal of this study is to retrieve and pre-process social media data in order to do sentiment analysis, which is a type of natural language processing. For improved sentiment analysis, the most important aspect of this article is to demonstrate how people feel about certain social media statuses, which will be used to classify them. The amount of data created has continually increased, and an ever-increasing variety of data types are being stored in unstructured or semi-structured pages: arranged configurations. Slant Analysis is a technique for extracting emotional information from online data. Assumption testing allows computers to automate human-like tasks by making decisions based on assumptions made in comments or posts on social media sites. In this research, we used five different machine learning approaches to assess the sentiments of Face-book comments: Nave Byes, SVM, Random Forest, KNN, and Decision tree. Different performance measures such as Precision, Recall, and F1-score were used to evaluate these five classifiers.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.