1. Sentiment Analysis of Twitter Data using Machine Learning: A Case Study of SVM Algorithm
- Author
-
simran Garg, Devang Chaturvedi, Tanya Jain, Anju Mishra, and Anjali Kapoor
- Abstract
This project report describes the use of machine learning algorithms for sentiment analysis of Twitter data. The dataset is collected from Twitter using API key and pre-processed using various Natural Language Processing (NLP) techniques such as stop word removal, punctuation removal, tokenization, stemming, and lemmatization. The pre-processed data is then split into training and testing sets and subjected to feature extraction using count vectorization. Support Vector Machine (SVM) algorithm is implemented for classification and performance metrics such as accuracy, precision, recall, and F1-score are analyzed. The output is visualized using graphs and the project is implemented in a web application using Flask. The report discusses the existing and proposed systems for sentiment analysis, highlighting the advantages and disadvantages of using SVM algorithm. The methodology for model building and testing is also presented in detail. Additionally, the report presents a case study of Vader, a sentiment analysis tool, and its performance on Twitter data. The project report concludes with a discussion on the future scope of the project such as improving the accuracy of the model and incorporating real-time analysis. The report provides a comprehensive overview of sentiment analysis using machine learning algorithms on Twitter data, highlighting the importance and relevance of this field in today's digital age. Overall, the project report serves as a valuable resource for anyone interested in sentiment analysis and machine learning on social media data.
- Published
- 2023
- Full Text
- View/download PDF