Git Product home page Git Product logo

covid_19_twitter_analysis's Introduction

Covid_19_Twitter_analysis

Exploratory analysis and visualisation of tweets and Covid-19 related data. An interactive dashboard is provided with insights about the socio-political and socio-economical impacts of Covid-19 and indications of various correlations between social media data and other Covid-19 related data. Submitted at #EUvsVirus Pan-European Hackathon.

Process

Coronavirus outbreak is a significant problem that society faces. Communities all around the world are studying ways to tackle the virus. In the era of big data, a vast amount of information can be found on the Web about coronavirus, such as data catalogues, web portals, public repositories and social media. The scope of this project is to provide an interface for understanding the global and national socio-political and socio-economic impacts of Covid-19 and how all these aspects correlate together. To achieve this, we used a curated dataset provided by panaceaLab that consists of almost 35 million tweets from 01/01/2020 until 22 of April and updates every two days. Due to the short duration of the hackathon, we have decided to collect a subset of 100,000 tweets per day leading to a dataset of 2.14 million tweets. In addition, we collected data regarding Covid-19 national cases and deaths, stock market indices, governmental measures and mobility measures provided by Google.

After cleaning the data, to calculate the sentiment polarity we used AllenNLP which is an open-source NLP research library and provides pretrained models. We used the model RoBERTa which is trained on the Stanford Sentiment Treebank dataset. The script is written in Python programming language and was executed in Google Colaboratory. Having obtained the needed dataset we used Microsoft Power BI to visualise the data and provide an interactive dashboard for better flexibility and understanding for the end-user.

The main challenge of our work was to obtain the needed data during the 48-hour hackathon, as it required most of our time. Furthermore, the majority of the tweets do not contain geotagged data, which made it difficult to analyse the sentiment polarity based on each country.

This hackathon was a very fruitful experience for our team. It gave us the opportunity to join the community and contribute to combating the coronavirus outbreak and provide useful information.

Data

Dataset Description Source
Covid-19 Tweets Covid-19 Twitter chatter dataset for scientific use https://github.com/thepanacealab/covid19_twitter
Google mobility Google mobility data https://www.google.com/covid19/mobility/
Governmental measures Governmental measures per country during the coronavirus outbreak https://www.bsg.ox.ac.uk/research/research-projects/coronavirus-government-response-tracker
Covid-19 cases-deaths Daily updated data on the geographic distribution of COVID-19 cases worldwide https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide

covid_19_twitter_analysis's People

Contributors

ikonstas-ds avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.