From Editors to Algorithms

TLDR

Facebook’s News Feed has become a dominant source of news, yet its opaque, constantly evolving story‑selection algorithm and trade‑secret status obscure the values guiding its curation. The study aims to identify core algorithmic values driving Facebook News Feed story selection by analyzing the platform’s patents, press releases, and SEC filings. Using material culture analysis, the authors rank these values, compare them with traditional news values, and assess the implications of their dominance. The analysis identifies nine News Feed values—friend relationships, user interests, prior engagement, implicit preferences, post age, platform priorities, page relationships, negative preferences, and content quality—where friend relationships exert overarching influence on all other values.

Abstract

Facebook's News Feed is an emerging, influential force in our personal information flows, especially where news information is concerned. However, as the News Feed's story selection mechanism starts to supplant traditional editorial story selection, we have no window into its story curation process that is parallel to our extensive knowledge of the news values that drive traditional editorial curation. The sensitive, trade-secret nature of the News Feed and its constant updates and modifications make a traditional, computer science-based examination of this algorithmic giant difficult, if not impossible. This study takes an alternative approach, using a content analysis of Facebook's own patents, press releases, and Securities and Exchange Commission filings to identify a core set of algorithmic values that drive story selection on the Facebook News Feed. Informed by the principles of material culture analysis, it ranks these values to create a window into Facebook's curation process, and compares and contrasts Facebook's story selection values with traditional news values, examining the possible consequences of one set of values supplanting the other. The study finds a set of nine News Feed values that drive story selection: friend relationships, explicitly expressed user interests, prior user engagement, implicitly expressed user preferences, post age, platform priorities, page relationships, negatively expressed preferences, and content quality. It also finds evidence that friend relationships act as an overall influence on all other story selection values.