Skip to main content

Step 3 – Analyze

Praising generates a very rich activity stream that can be used to analyze the community's activity and growth. Praise currently provides a limited set of built in analysis tools, but we are working on adding more. We also provide a standalone Python based tool called RAD - Reward Analysis & Distributions built for data analysts and data scientists that want to perform more advanced analysis.

Insights either built into Praise or provided by RAD:

  • Community health indicators such as the number of new members, the number of active members, the number of contributions, etc.
  • Top contributors and top contributions
  • Contribution categorization
  • Top contributors by contribution category
  • Community activity visualization over time
  • Quantification insights
    • Quantifier scoring distribution and spread
  • Reward insights
    • Nakamoto coefficient
    • Gini coefficient

We recommend to hold open analysis sessions after each quantification where the community can discuss the insights generated by Praise. This is a great way to build a sense of community and to foster a spirit of cooperation and mutual support.

AI powered insights

Praise is also working on building AI powered insights. These insights are generated by machine learning models that are trained on the praise data. These models are able to generate insights that are not possible to generate with traditional data analysis tools. For example, the models are able to detect the sentiment of praise and the impact of praise on the community.

Examples of AI powered insights:

  • Sentiment analysis
  • Impact analysis
  • Contribution categorization
  • Auto generated contributor profiles and bios
  • Auto generated organsation charts