The Importance of Cognitive Biases in the Recommendation Ecosystem

TL;DR

Addressing the overlooked role of cognitive biases in recommendation systems, the paper argues that certain biases can improve models if accounted for. It surveys and formalizes biases such as the feature-positive effect, Ikea effect, and cultural homophily, and examines their manifestations across data, algorithms, and user interactions. The authors present three small experiments in recruitment and music domains showing FPE influences relevance predictions, Ikea-driven ownership effects, and cultural homophily in consumption and recommendations. The work advocates bias-aware, prejudice-free design to enhance user and item models and calls for broader, cross-platform research.

Abstract

Cognitive biases have been studied in psychology, sociology, and behavioral economics for decades. Traditionally, they have been considered a negative human trait that leads to inferior decision-making, reinforcement of stereotypes, or can be exploited to manipulate consumers, respectively. We argue that cognitive biases also manifest in different parts of the recommendation ecosystem and at different stages of the recommendation process. More importantly, we contest this traditional detrimental perspective on cognitive biases and claim that certain cognitive biases can be beneficial when accounted for by recommender systems. Concretely, we provide empirical evidence that biases such as feature-positive effect, Ikea effect, and cultural homophily can be observed in various components of the recommendation pipeline, including input data (such as ratings or side information), recommendation algorithm or model (and consequently recommended items), and user interactions with the system. In three small experiments covering recruitment and entertainment domains, we study the pervasiveness of the aforementioned biases. We ultimately advocate for a prejudice-free consideration of cognitive biases to improve user and item models as well as recommendation algorithms.

Figures (2)

• Figure 1: The effect of removing adjectives from job ads on the relevance predictions of candidate-job pairs.
• Figure 2: Distribution of the consumption frequency difference between own and other playlists. Positive values show preference towards own playlists.