Architectures of Choice

Vol.1: Youtube
Any interface to a vast catalog of media is, explicitly or not, an ordering of choices. This project presents a series of experiments in mapping recommendations on the YouTube platform. It acts as a starting point towards a visual understanding of how choice is directed, generated, and controlled by algorithmic systems.

Further reading:

Marenko, B. and Benqué, D. (2019) ‘Speculative diagrams: Experiments in mapping Youtube’, in Method & Critique; frictions and shifts in RTD. Research Through Design, TU Delft. PDF [930KB]

Scraping

Three probes gather Youtube recommendation data and store them in a graph database.

Visualisation

Attempts to visualise data from the graph using tools such as:

  • Neo4j browser
  • Python: matplotlib, networkx, datashader
  • Mermaid.js
  • Gephi

mermaid Mermaid.js SVG (may take time to load, wait a few seconds if you are seeing a wall of text)

Traces

These are focused visualisations of single paths through Youtube, showing details of each video such as title, author, and views. They are shown as static images of short traces, and animations of much longer ones.

2018

Gitlab

Research Log

Initial development (Scraping and Visualisation sections) was a Supra Systems Studio project, in partnership with BBC R&D.