• Ashutosh Tiwari
• Shreyas Chikhalikar
• Anup Singh
• Dakshata Argade

Twitter claims that 53% of its users are likely to try new products. In such a scenario, Twitter can be a good medium to advertise a new product. The success of such a product can be determined by the reviews given by Twitter users. As a result, Twitter can be influential in determining the user’s opinion about the product. Machine Learning (ML) can be used to perform Twitter Sentiment Analysis (TSA) to extract meaningful information from the tweets. The objective of the project is to determine which Machine Learning algorithm performs better on Twitter data for Sentiment Analysis (SA). This is done by a technique called Natural Language Processing (NLP). The ML algorithm implemented are Logistic Regression (LR) and Naïve Bayes (NB). The training and validation testing are performed on a dataset obtained from Natural Language Toolkit (NLTK). The final testing is performed on a completely different dataset to eradicate any bias originating from the training dataset. The efficiency of both the algorithms are compared and Naïve Bayes outperformed Logistic Regression in terms of efficiency. This result is in accordance with the result of research previously conducted on the same topic.

Twitter Sentiment Analysis, Machine Learning, Natural Language Processing, Natural Language Toolkit, Logistic Regression, Naïve Bayes

"Comparative Analysis of Different Machine Learning Algorithms for Twitter Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 3, page no.g353-g359, March-2022, Available :http://www.jetir.org/papers/JETIR2203647.pdf

"Comparative Analysis of Different Machine Learning Algorithms for Twitter Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 3, page no. ppg353-g359, March-2022, Available at : http://www.jetir.org/papers/JETIR2203647.pdf