REVIEW 5 cited by
What We Know About Using Non-Engagement Signals in Content Ranking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Many online platforms predominantly rank items by predicted user engagement. We believe that there is much unrealized potential in including non-engagement signals, which can improve outcomes both for platforms and for society as a whole. Based on a daylong workshop with experts from industry and academia, we formulate a series of propositions and document each as best we can from public evidence, including quantitative results where possible. There is strong evidence that ranking by predicted engagement is effective in increasing user retention. However retention can be further increased by incorporating other signals, including item "quality" proxies and asking users what they want to see with "item-level" surveys. There is also evidence that "diverse engagement" is an effective quality signal. Ranking changes can alter the prevalence of self-reported experiences of various kinds (e.g. harassment) but seldom have large enough effects on attitude measures like user satisfaction, well-being, polarization etc. to be measured in typical experiments. User controls over ranking often have low usage rates, but when used they do correlate well with quality and item-level surveys. There was no strong evidence on the impact of transparency/explainability on retention. There is reason to believe that generative AI could be used to create better quality signals and enable new kinds of user controls.
Forward citations
Cited by 5 Pith papers
-
Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections
A browser extension that embeds reflection prompts into short-form video feeds and automatically re-aligns recommendations led to more preference adjustments and better feed alignment than a manual baseline in a 10-da...
-
Recommendation and Temptation
A recommender that models temptation and outside options and myopically recommends the item with the highest expected enrichment is proven optimal, but only under the paper's own behavioral assumptions.
-
YouTube Recommendations Reinforce Negative Emotions: Auditing Algorithmic Bias with Emotionally-Agentic Sock Puppets
Sock-puppet audits show YouTube's recommendations become more aligned with a user's revealed emotional preference, especially for negative emotions, but contextual (non-personalized) recommendations reinforce this ali...
-
Shaping the Future of Social Media with Middleware
Open third-party middleware could decentralize platform power over curation and moderation, but its success depends on platform access, business models, and targeted policy changes.
-
AI and the Future of Digital Public Squares
A multi-stakeholder agenda argues that LLM-enabled collective dialogue, bridging, moderation, and proof-of-humanity tools can strengthen digital public squares if paired with research and safeguards.
Discussion (0). Continue with ORCID to comment.