Modeling Content Creator Incentives on Algorithm-Curated Platforms
This addresses the problem of algorithmic misalignment for platform developers and creators, offering a pre-deployment audit tool, though it is incremental in applying game theory to existing recommendation systems.
The paper tackles the problem of how algorithmic choices on content platforms affect creator incentives, formalizing this as an exposure game and proving that choices like non-negative factorization impact Nash equilibria, with audits on MovieLens and LastFM showing dependencies between algorithmic exploration and content diversity, and model expressivity and gender-based bias.
Content creators compete for user attention. Their reach crucially depends on algorithmic choices made by developers on online platforms. To maximize exposure, many creators adapt strategically, as evidenced by examples like the sprawling search engine optimization industry. This begets competition for the finite user attention pool. We formalize these dynamics in what we call an exposure game, a model of incentives induced by algorithms, including modern factorization and (deep) two-tower architectures. We prove that seemingly innocuous algorithmic choices, e.g., non-negative vs. unconstrained factorization, significantly affect the existence and character of (Nash) equilibria in exposure games. We proffer use of creator behavior models, like exposure games, for an (ex-ante) pre-deployment audit. Such an audit can identify misalignment between desirable and incentivized content, and thus complement post-hoc measures like content filtering and moderation. To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets. Among else, we find that the strategically produced content exhibits strong dependence between algorithmic exploration and content diversity, and between model expressivity and bias towards gender-based user and creator groups.