As the Covid-19 pandemic continues to persist in the world the only way out of this still seem to be vaccinating most of the population. Although many private and government organizations trying their best in order to convince people about the urgency of vaccinating themselves and their loved ones, hesitancy towards vaccine still present in the population sometimes due to the lack of knowledge or even in knowledgeable chunk of the population because of the fact that never in human history any vaccine have been discovered and rolled out for general purpose usage in the population. Different vaccines are developed in different ways by different manufacturers situated in different countries above all, their working principles vary widely. So, in an ideal world sentiment towards different vaccines should be different in the population.
Sentiment analysis on social media has been performed in multiple occasions earlier by organizations to find out opinion about many health related issues in past. Which brings us to the aim of this project which is to find out that difference in opinions from people living in different part of the world about popular vaccines in use.
Collecting the tweets using takes about 5-6 hours as twitter has an hourly limit. The cleaning part takes about 1 minute but the sentiment assignment part will take about 25-30 minutes.
I am sharing the links of all those data files uploaded in my One Drive folder from where it can be downloaded in order for you to save a lot of time. After downloading place the missing files in the "submission/data" folder. The total size of all of the data files is about 80 MB.
OneDrive Link: covid19Vaccine/data
When the getTweets.py module is executed, it will ask for an encryption key, which will allow you to use my Tweeter API access keys to collect tweets. If you are authorized, you can use my tweeter tokens using the key. Otherwise, please collect a Tweeter developer account and use your own keys. Else, one is welcomed to download the data from my OneDrive and use it.