Hybra Data Analysis Ecosystem

During the past few years, social science have applied more and more of trace data. Trace data is large scale data set of the actions of people, for example Twitter activity around particular hashtag.

HYBRA focuses on working with trace data from social media (Facebook, Twitter) and major Finnish newspapers and support

  • data collection
  • data wrangling
  • data analysis
  • documenting and reporting the findings

Philosphy and vision

We believe that many computational tools have been developed with an analysis strategy in mind. This helps to make the user experience smooth and help researchers a lot to work with that given analysis strategy. However, researcher is often bounded by do that analysis strategy and their creativity is bounded by the tools.

If you have a hammer everything looks like a nail. We want to avoid this and unleash the researchers to innovate with digital methods.

This means that a set of helper functions to support the data collection, wrangling and basic visualization is what is needed. We created these common tasks as programming libraries. It means there's a learnign curve: to utilize HYBRA, Python is required.

We believe that tooled with power of Python (and R) and HYBRA, researchers can create novel research approaches. The HYBRA smootheness many of the trivial tasks so researchers can focus on most valued-add activites in the analysis.

Components

  • Hybra Core is the library to work with data: it helps to wrangle, visualize and analyze the data. We use it often through JuPyter Notebooks, but it also works in a standalone Python environment.
  • Hybra Some Collector works with Facebook API to load Facebook data from groups, events and pages and outputs data in HYBRA compatible format.
  • Hybra Media Collector parses several Finnish media sites and produces data in a HYBRA compatible format for data analysis.

Thanks

  • Academy of Finland
    • Racisms and public communications in the hybrid media environment (HYBRA) project uses this tool as its primary computational data analysis environment.
  • Kone Foundation
    • Matti Nelimarkka's work on mainstreaming this tool was supported by Digital Humanities of Public Policy Making.
  • Sanoma Foundation
    • Early work towards this ecosystem was done in Digivaalit 2015 project.