Rationally inattentive inverse reinforcement learning explains youtube commenting behavior

被引：0

作者：

Hoiles, William ^{[1
]}

Krishnamurthy, Vikram ^{[2
]}

Pattanayak, Kunal ^{[2
]}

机构：

[1] KATERRA, Menlo Park,CA,94025, United States

[2] Electrical and Computer Engineering, Cornell University, Ithaca,NY,14853, United States

来源：

Journal of Machine Learning Research | 2020年 / 21卷

关键词：

We consider a novel application of inverse reinforcement learning with behavioral economics constraints to model; learn and predict the commenting behavior of YouTube viewers. Each group of users is modeled as a rationally inattentive Bayesian agent which solves a contextual bandit problem. Our methodology integrates three key components. First; to identify distinct commenting patterns; we use deep embedded clustering to estimate framing information (essential extrinsic features) that clusters users into distinct groups. Second; we present an inverse reinforcement learning algorithm that uses Bayesian revealed preferences to test for rationality: does there exist a utility function that rationalizes the given data; and if yes; can it be used to predict commenting behavior? Finally; we impose behavioral economics constraints stemming from rational inattention to characterize the attention span of groups of users. The test imposes a Rényi mutual information cost constraint which impacts how the agent can select attention strategies to maximize their expected utility. After a careful analysis of a massive YouTube dataset; our surprising result is that in most YouTube user groups; the commenting behavior is consistent with optimizing a Bayesian utility with rationally inattentive constraints. The paper also highlights how the rational inattention model can accurately predict commenting behavior. The massive YouTube dataset and analysis used in this paper are available on GitHub and completely reproducible. © 2020 Wiliam Hoiles; Vikram Krishnamurthy and Kunal Pattanayak;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

引用

共 50 条

[1] Rationally Inattentive Inverse Reinforcement Learning Explains YouTube Commenting Behavior
Hoiles, William
Krishnamurthy, Vikram
Pattanayak, Kunal
JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
[2] Commenting on learning Korean on TikTok and YouTube
Vazquez-Calvo, Boris
Duarte-Marti, Sergio
Zhang, Leticia-Tian
INTERACTIVE LEARNING ENVIRONMENTS, 2024, 32 (10) : 6063 - 6080
[3] Rationally Inattentive Behavior: Characterizing and Generalizing Shannon Entropy
Caplin, Andrew
Dean, Mark
Leahy, John
JOURNAL OF POLITICAL ECONOMY, 2022, 130 (06) : 1676 - 1715
[4] Learning Behavior Styles with Inverse Reinforcement Learning
Lee, Seong Jae
popovic, Zoran
ACM TRANSACTIONS ON GRAPHICS, 2010, 29 (04):
[5] Hierarchical Reinforcement Learning Explains Task Interleaving Behavior
Gebhardt C.
Oulasvirta A.
Hilliges O.
Computational Brain & Behavior, 2021, 4 (3) : 284 - 304
[6] Testing the behavior of rationally inattentive consumers in a residential water market
Wang, Xiangrui
Lee, Jukwan
Yan, Jia
Thompson, Gary D.
JOURNAL OF ENVIRONMENTAL ECONOMICS AND MANAGEMENT, 2018, 92 : 344 - 359
[7] Modular inverse reinforcement learning for visuomotor behavior
Rothkopf, Constantin A.
Ballard, Dana H.
BIOLOGICAL CYBERNETICS, 2013, 107 (04) : 477 - 490
[8] Modular inverse reinforcement learning for visuomotor behavior
Constantin A. Rothkopf
Dana H. Ballard
Biological Cybernetics, 2013, 107 : 477 - 490
[9] Commenting behavior as a mirror of parasocial relationships and emotional attachment on YouTube
Pelttari, Sanna
PRAGMATICS AND SOCIETY, 2025,
[10] Inverse Reinforcement Learning Based Stochastic Driver Behavior Learning
Ozkan, Mehmet F.
Rocque, Abishek J.
Ma, Yao
IFAC PAPERSONLINE, 2021, 54 (20): : 882 - 888

← 1 2 3 4 5 →