Event Details
Covid-19 Twitter Sentiment Analysis Using Machine Learning
Presenter: Muhammad Ali Shaikh
Supervisor:
Date: Wed, September 7, 2022
Time: 08:15:00 - 09:15:00
Place: via Zoom - please see link below
ABSTRACT
Join Zoom Meeting
Register in advance for this meeting:
https://uvic.zoom.us/j/84630359864?pwd=YzVTRW5GR2srTVFiZEhsZ3hTSzV5dz09
After registering, you will receive a confirmation email containing information about joining the meeting.
Meeting ID:
846 3035 9864
Note: Please log in to Zoom via SSO and your UVic Netlink ID.
One tap mobile
+16475580588,,84630359864# Canada
+17789072071,,84630359864# Canada
Dial by your location
+1 647 558 0588 Canada
+1 778 907 2071 Canada
ABSTRACT
The Internet is widely used by almost everyone. People are choosing social media applications to voice their thoughts and concerns given the daily growth of these platforms. They can be used to collect and analyze public sentiments for purchasing products, diseases, political debates, and socio economic developments. Businesses, governments, and individuals can benefit from analyzing these sentiments. Twitter is a massive, rapidly growing platform where users share their opinions on politics, sports, products, and other topics. Therefore, Twitter tweets are very useful for determining public sentiments.
Sentiment analysis is a method of determining if text indicates a negative, positive or neutral emotion. This report presents automated sentiment analysis of Covid-19 tweets using Machine Learning (ML). The ML classifiers used are Naive Bayes (NB), Simple Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The classifiers were implemented in Jupyter notebook using the Python programing language. Accuracy, f-measure, recall, precision, and time are considered as performance metrics. The results obtained indicate that the DT classifier is the best in terms of these metrics.