Mr. Mark Ledwich
Data Engineer and Amateur Researcher
(Unaffiliated)

YouTube's recommendation algorithm is frequently characterized by journalists and researchers as radicalizing users to the far-right, but the evidence to date has been weak. We used data collected from the YouTube website to analyze the balance in recommendation impressions to see if it is favoring more extreme content. 768 US political channels were categorized into culturally relevant orientations and sub-cultures and 23M recommendations for recent videos were recorded during November-December 2019. We found that the late 2019 recommendation algorithm actively discourages viewers from being presented with fringe content. The algorithm is shown to favor mainstream media and cable news content over independent YouTube channels with a slant towards partisan political channels like Fox News and Last Week Tonight.

Slides

Slides for the talk in PPTX format.

Source code and links to data: https://github.com/markledwich2/YouTubeNetworks
Paper: https://arxiv.org/pdf/1912.11211.pdfi
Interactive Viz: https://www.recfluence.net/

Video:

To access the live webcast of the talk (active at 16:28 of the day of the presentation) and the archived version of the talk, use the URL SU-EE380-20200108200108. This is a first class reference and can be transmitted by email, Twitter, etc.

A URL referencing a YouTube view of the lecture will be posted HERE a week or so following the presentation.

About the Speaker:

I am a software engineer specializing in data engineering and visualization with an interest in open science. I decided to build recfluence.net after noticing Google's lack of transparency about their recommendation system and the uninformed narratives created by some researchers and media. I have enjoyed my short experience performing independent research and am surprised at the level of interest it has received. I have open-sourced recfluence.net and the data in the hope it will be a non-trivial contribution to public knowledge.