Persine is an automated tool to study and reverse-engineer algorithmic recommendation systems, like YouTube videos and Amazon products.
J Soma
slides at jonathansoma.com/projects/persine
Lede Program, Columbia Journalism School
âPersine is an automated tool to study and reverse-engineer algorithmic recommendation systems, like YouTube videos and Amazon products. It has a simple interface and encourages reproducible results.â
YouTube and Amazon
YouTube, the Great Radicalizer by Zeynep Tufekci (NYT)
Childrenâs YouTube is still churning out blood, suicide and cannibalism by K.G. Ophanides (Wired)
YouTubeâs Algorithm Accused of Facilitating Paedophile Rings by Tim Cross (Videoweek)
âFiction is outperforming realityâ: how YouTubeâs algorithm distorts truth by Paul Lewis (The Guardian)
The New Zealand shooting shows how YouTube and Facebook spread hate and violent images â yet again (Washington Post)
Persine also works on Amazon, although itâs not as well tested, and Amazonâs website is kind of insane. You can see whatâs surfaced in search results, whatâs listed as recommendations on product pages or on the Amazon homepage.
Itâs also easily extendable to other websites
js4571@columbia.edu @dangerscarf