English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We consider a novel application of inverse reinforcement learning withbehavioral economics constraints to model, learn and predict the commentingbehavior of YouTube viewers. Each group of users is modeled as a rationallyinattentive Bayesian agent which solves a contextual bandit problem. Ourmethodology integrates three key components. First, to identify distinctcommenting patterns, we use deep embedded clustering to estimate framinginformation (essential extrinsic features) that clusters users into distinctgroups.Second, we present an inverse reinforcement learning algorithm that usesBayesian revealed preferences to test for rationality: does there exist autility function that rationalizes the given data, and if yes, can it be usedto predict commenting behavior? Finally, we impose behavioral economicsconstraints stemming from rational inattention to characterize the attentionspan of groups of users. The test imposes a R{\'e}nyi mutual information costconstraint which impacts how the agent can select attention strategies tomaximize their expected utility. After a careful analysis of a massive YouTubedataset, our surprising result is that in most YouTube user groups, thecommenting behavior is consistent with optimizing a Bayesian utility withrationally inattentive constraints. The paper also highlights how the rationalinattention model can accurately predict commenting behavior. The massiveYouTube dataset and analysis used in this paper are available on GitHub andcompletely reproducible.

Rationally Inattentive Inverse Reinforcement Learning Explains YouTube Commenting Behavior