Open In Colab

Loading output library...

Import raw data && clean up


Overall stats


How sparse is the dataset? How much agree, how much disagree, how much pass? Zero is 'passed' or 'did not see the comment to vote on it'. 1 is agree, -1 is disagree

Full participants * comments matrix


Some things to notice about the matrix: comments are submitted over time, so participants who do not return will only have voted on the statements which were avialable when they arrived.

Long horizontal lines: participants who do return show up as a horizontal line sticking out into otherwise blank areas

Blank vertical lines: most likely statements which were moderated out of the conversation.

Loading output library...
Loading output library...

Is the space explained by how much people vote?


In this chart, we take the PCA coordinates and color the participant locations by the number of total votes. Hopefully, it looks random. If it doesn't, we might imagine the following scenario:

  • 1000 people vote, and there are very few controversial statements. They do not return.
  • 1 person submits a statement which is incredibly controversial.
  • 1000 more people vote, the space begins to take on structure, PCA is closely linked to vote count.

We know this scenario - that voters don't see controversial comments - happens. Polis mitigates in two ways:

  • polis eliminates participants who don't vote at least 7 times from the analysis
  • polis shows several highly controversial comments (large egeinvalue) in the first 10 comments participants see
Loading output library...
Loading output library...


Loading output library...


Loading output library...


Loading output library...


Loading output library...