Problem
Research questions and friction points this paper is trying to address.
video recommendation
online experiments
user behavior
recommendation policy
playback behavior
WatchLens: A Configurable Platform for Online Video Recommendation Experiments
🤖 AI Summary
Existing user research infrastructures struggle to link recommendation strategies with user behaviors within a unified experimental pipeline, hindering causal analysis in video recommender systems. This work proposes a modular and configurable online video recommendation experimentation platform that, for the first time, enables direct event-level alignment between recommendation policies and user interactions through a standardized logging layer and a plug-and-play policy architecture. The platform supports independent configuration of interface layouts, content sources, and recommendation strategies, operates on a single server, and has been validated through short-video case studies. It successfully facilitates session-level comparative evaluation of recommendation effectiveness, offering an open-source infrastructure for reproducible and fine-grained online recommendation research.
📝 Abstract
Studying how video recommender systems shape user behavior requires online experiments that link playback behavior with the recommendation conditions that produced it. Existing user-study infrastructure provides one or the other, but not both within a single experimentation workflow. We present WatchLens, an open-source platform that fills this gap. WatchLens adopts a modular architecture in which user interfaces, content sources, and recommendation policies are independently configurable, with policies assignable separately to the feed and the watch page, while a standardized logging layer attaches the recommendation policy and ranking position to every event at recording time. This design enables researchers to analyze how recommendation policies and ranking positions shape downstream playback behavior, session continuation, and navigation between the feed and the watch page, with the linkage between policy and outcome available in each event rather than reconstructed afterwards. We demonstrate WatchLens with a short-form video case study that holds the interface, feed policy, and content pool constant while varying only the watch-page policy, showing how the platform supports session-level comparison of recommendation effects on real viewing behavior. WatchLens is released as a publicly available, single-server deployable system for reproducible online video recommendation research.
Innovation
Methods, ideas, or system contributions that make the work stand out.
modular architecture
online video recommendation
configurable recommendation policies
standardized logging
session-level analysis
🔎 Similar Papers
