This paper is published in Volume-7, Issue-4, 2021
Area
Data Science
Author
Mohammed Mafaz
Org/Univ
Loyola College, Chennai, Tamil Nadu, India
Pub. Date
05 August, 2021
Paper ID
V7I4-1657
Publisher
Keywords
Social Media, Sentiment Analysis, Web Scraping, Naive Bayes, Bert, Neural Network

Citationsacebook

IEEE
Mohammed Mafaz. Analyzing tweets to classify the opinions of people living in Chennai with respect to the city, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Mohammed Mafaz (2021). Analyzing tweets to classify the opinions of people living in Chennai with respect to the city. International Journal of Advance Research, Ideas and Innovations in Technology, 7(4) www.IJARIIT.com.

MLA
Mohammed Mafaz. "Analyzing tweets to classify the opinions of people living in Chennai with respect to the city." International Journal of Advance Research, Ideas and Innovations in Technology 7.4 (2021). www.IJARIIT.com.

Abstract

This project helps to analyze the public opinion in social media towards Chennai city by the people who live in the city. It presents a comprehensive review of local people who tweet, retweet, like on Twitter about Chennai. For completeness, it includes introductions to social media web scraping, storage, data cleaning, and some sentiment analysis tools. This project also provides a comparative study where we use three different sentiment analysis tools: Naive Bayes, Bert, and Neural Network. Analyzing social media, in particular, Twitter feeds for sentiment analysis, has become a major research activity due to the availability of web-based APIs provided by Twitter services. This project provides a review of leading software tools and how to use web scraping, cleanse using Bert and comparing the tweets with three different tools and showing them in graph and finding out which gives the best accuracy and presenting it to the CHENNAI SMART CITY LTD which comes under the GREATER CHENNAI CORPORATION. The data retrieval techniques that are presented in this paper are valid at the time of doing this project (April 2021), because they are subject to change since social media web scraping APIs are rapidly changing.