Analyzing Emotions and Opinions in Social Media and Reviews Using Natural Language Processing

Authors:

R.Praveen¹,

¹ II-MCA Student,

PG Department of Computer Applications

 Nehru Memorial College (Autonomous), Puthanampatti

Affiliated to Bharathidasan University, Tiruchirappalli – 621007, India

praveen25122003@gmail.com

Dr. D. Jayachitra²

² Director – MCA and Associate Professor

PG Department of Computer Applications

 Nehru Memorial College (Autonomous), Puthanampatti

Affiliated to Bharathidasan University, Tiruchirappalli – 621007, India

 jayadchitra@gmail.com

ABSTRACT

The rapid growth of social media and online review platforms has created a large amount of user-generated text that reflects people’s emotions and opinions. Analyzing this data manually is difficult and time-consuming. This research focuses on using Natural Language Processing (NLP) techniques to automatically identify and classify sentiments expressed in social media posts and reviews. The system collects data from various platforms, preprocesses the text by cleaning and organizing it and converts it into meaningful features using methods such as Bag of Words and TF-IDF. Different machine learning and deep learning models, including Naive Bayes, Support Vector Machine (SVM), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are applied to classify the text as positive, negative, or neutral. The results show that deep learning models perform better in understanding context and complex sentence structures.

Keywords: Natural Language Processing (NLP), Sentiment Analysis, Opinion Mining, Machine Learning, Deep Learning, Social Media Analysis, Text Classification, LSTM, CNN, Support Vector Machine (SVM), Naive Bayes, Feature Extraction, TF-IDF, Word Embeddings, Emotion Detection.