TwitPlat

What is Twitplat?

Twitplat is a platform we conceived, designed, and developed that contains a large volume of publicly available, geolocated Twitter data.​ We can use this big data to learn about attitudes, events, and behaviours around the world, and how they might differ according to location and/or time.

Because of our geolocation algorithm allowing us to geolocate data to a very fine scale, the Twitplat database holds:

  • 2.3 billion geolocated tweets to every UN recognized country (and every city in the world with over 100,000 inhabitants)
  • 500 million tweets geolocated to a city or state in the USA (and every United States city with over 5,000 inhabitants)
  • Every Australian suburb, city and region
  • 10 years of data (2012-2021 inclusive)
  • Timestamped to the second

No other algorithm known provides such fine-scale variation in location, and it is this variation that provides us with the unique ability to examine socio-structural correlates of behaviour across time and place. With these data we are able to analyze aggregate patterns of behavior across time and place.

We use these data to understand how things like income inequality, gender inequality, and climate affect important aspects of human psychology. We can also link these data to crime statistics, to see if online chatter can prospectively predict real-world crime.

Access Twitplat

Twitplat is now freely available to use for research purposes. When using Twitplat, please ensure to acknowledge and cite Dr. Khandis Blake.

https://twitplat2.researchsoftware.unimelb.edu.au/
Username: gen_pub
Password: Hairyfish865

What Can Twitplat Be Used For?

Here are some questions we’ve answered using Twitplat:

And here are some questions we are answering right now:

  • Do prescriptive and descriptive gender ideology shift as a function of mating market ecologies?
  • How does gender and income inequality affect support for women in STEM?
  • What is the relationship between inequality and eating disorder prevalence?