Rabbit Holes and Taste Distortion: Distribution-Aware Recommendation with Evolving Interests
Authors:
Open Access
- 19 April 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 888-899
Abstract
To mitigate the rabbit hole effect in recommendations, conventional distribution-aware recommendation systems aim to ensure that a user’s prior interest areas are reflected in the recommendations that the system makes. For example, a user who historically prefers comedies to dramas by 2:1 should see a similar ratio in recommended movies. Such approaches have proven to be an important building block for recommendation tasks. However, existing distribution-aware approaches enforce that the target taste distribution should exactly match a user’s prior interests (typically revealed through training data), based on the assumption that users’ taste distribution is fundamentally static. This assumption can lead to large estimation errors. We empirically identify this taste distortion problem through a data-driven study over multiple datasets. We show how taste preferences dynamically shift and how the design of a calibration mechanism should be designed with these shifts in mind. We further demonstrate how to incorporate these shifts into a taste enhanced calibrated recommender system, which results in simultaneously mitigated both the rabbit hole effect and taste distortion problem.Keywords
This publication has 32 references indexed in Scilit:
- Intent-Aware Diversification Using a Constrained PLSA2016
- Query-based Music Recommendations via Preference Embedding2016
- Bayesian Low-Rank Determinantal Point Processes2016
- Down the (White) Rabbit Hole: The Extreme Right and Online Recommender SystemsSocial Science Computer Review, 2014
- A submodular optimization approach to sentence set selection2014
- Novelty and Diversity in Top-N Recommendation -- Analysis and EvaluationACM Transactions on Internet Technology, 2011
- Quantitative and empirical demonstration of the Matthew effect in a study of career longevityProceedings of the National Academy of Sciences, 2010
- Improving recommendation lists through topic diversification2005
- LSTM recurrent networks learn simple context-free and context-sensitive languagesIEEE Transactions on Neural Networks, 2001
- Asymptotic calibrationBiometrika, 1998