Quantifying the Effects of Recommendation Systems
This addresses the issue of algorithmic bias affecting consumer behavior and perceptions, but it appears incremental as it focuses on quantifying known effects rather than proposing new solutions.
The paper tackles the problem of biases in recommendation systems, analyzing how collaborative filtering creates feedback loops that magnify popular items and alter user preferences, and quantifies the resulting inequalities.
Recommendation systems today exert a strong influence on consumer behavior and individual perceptions of the world. By using collaborative filtering (CF) methods to create recommendations, it generates a continuous feedback loop in which user behavior becomes magnified in the algorithmic system. Popular items get recommended more frequently, creating the bias that affects and alters user preferences. In order to visualize and compare the different biases, we will analyze the effects of recommendation systems and quantify the inequalities resulting from them.