Preference Dynamics Under Personalized Recommendations

Preference Dynamics Under Personalized Recommendations
复制标题

个性化推荐下的偏好动态

DOI:
10.1145/3490486.3538346
复制
发表时间:
2022
期刊:
Economics and Computation
影响因子:
--
通讯作者:
Morgenstern, Jamie
Morgenstern, Jamie
中科院分区:
--
文献类型:
--
作者:
Dean, Sarah;Morgenstern, Jamie

文献摘要

参考文献

被引文献

相似文献

内容推荐系统的设计支撑着许多在线平台:社交媒体提要、在线新闻聚合器和音频/视频托管网站都选择如何最好地组织大量内容供用户消费。许多项目(包括实践和学术)都设计了算法来匹配用户与他们喜欢的内容,假设用户的偏好和意见不会随着他们看到的内容而改变。然而,越来越多的证据表明,个人的偏好直接受到他们看到的内容的影响-激进,兔子洞,两极分化和无聊都是受内容影响的偏好现象。两极分化尤其可能发生在具有“大众媒体”的生态系统中,在那里没有个性化发生,正如[14]和[13]最近在偏好动态的自然模型中所探索的那样。如果所有的用户的偏好被吸引到他们已经喜欢的内容,或从他们已经不喜欢的内容排斥,统一的媒体消费导致人口的异质性偏好收敛到只有两个pole.在这项工作中,我们探讨是否会发生一些类似于极化的现象,当用户收到个性化的内容推荐。我们使用类似的偏好动态模型,其中个人的偏好朝向消费和享受的内容移动,远离他们消费和不喜欢的内容。我们表明,标准的用户奖励最大化是一个几乎微不足道的目标,在这样的环境中(一大类简单的算法将实现只有不断的遗憾)。一个更有趣的目标,然后,是了解在什么条件下推荐算法可以确保用户的偏好的平稳性。我们展示了如何设计一个内容推荐,它可以实现近似平稳,在温和的条件下的一组可用的内容,当用户的喜好是已知的,以及如何可以了解足够的用户的喜好,即使用户的喜好最初是未知的,以实现这样的策略。
The design of content recommendation systems underpins many online platforms: social media feeds, online news aggregators, and audio/video hosting websites all choose how best to organize an enormous amount of content for users to consume. Many projects (both practical and academic) have designed algorithms to match users to content they will enjoy under the assumption that user's preferences and opinions do not change with the content they see.However, increasing amounts of evidence suggest that individuals' preferences are directly shaped by what content they see---radicalization, rabbit holes, polarization, and boredom are all example phenomena of preferences affected by content. Polarization in particular can occur even in ecosystems with "mass media," where no personalization takes place, as recently explored in a natural model of preference dynamics by [14] and [13]. If all users' preferences are drawn towards content they already like, or are repelled from content they already dislike, uniform consumption of media leads to a population of heterogeneous preferences converging towards only two poles.In this work, we explore whether some phenomenon akin to polarization occurs when users receive personalized content recommendations. We use a similar model of preference dynamics, where an individual's preferences move towards content the consume and enjoy, and away from content they consume and dislike. We show that standard user reward maximization is an almost trivial goal in such an environment (a large class of simple algorithms will achieve only constant regret). A more interesting objective, then, is to understand under what conditions a recommendation algorithm can ensure stationarity of user's preferences. We show how to design a content recommendations which can achieve approximate stationarity, under mild conditions on the set of available content, when a user's preferences are known, and how one can learn enough about a user's preferences to implement such a strategy even when user preferences are initially unknown.
DOI: 10.1287/moor.2023.1355
发表时间: 2019
期刊: ArXiv
影响因子: --
作者:
Jan Hązła;Yan Jin;Elchanan Mossel;Govind Ramnarayan
通讯作者: Govind Ramnarayan
DOI: --
发表时间: 2003
期刊: 36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the
影响因子: --
作者:
Jyun;Juo
通讯作者: Juo
DOI: --
发表时间: 2021-02
期刊: --
影响因子: --
作者:
De Huang;Jonathan Niles-Weed;Rachel A. Ward
通讯作者: De Huang;Jonathan Niles-Weed;Rachel A. Ward
DOI: 10.2139/ssrn.3350187
发表时间: 2020
期刊: Behavioral & Experimental Economics eJournal
影响因子: --
作者:
B. Bernheim;Luca Braghieri;Alejandro Martínez;David Zuckerman
通讯作者: David Zuckerman
强化学习推荐系统中的用户篡改
DOI: --
发表时间: 2021
期刊: AAAI/ACM Conference on AI, Ethics, and Society
影响因子: --
作者:
Atoosa Kasirzadeh;Charles Evans
通讯作者: Charles Evans