skip to main content

Title: Calibration in Collaborative Filtering Recommender Systems: a User-Centered Analysis
Recommender systems learn from past user preferences in order to predict future user interests and provide users with personalized suggestions. Previous research has demonstrated that biases in user profiles in the aggregate can influence the recommendations to users who do not share the majority preference. One consequence of this bias propagation effect is miscalibration, a mismatch between the types or categories of items that a user prefers and the items provided in recommendations. In this paper, we conduct a systematic analysis aimed at identifying key characteristics in user profiles that might lead to miscalibrated recommendations. We consider several categories of profile characteristics, including similarity to the average user, propensity towards popularity, profile diversity, and preference intensity. We develop predictive models of miscalibration and use these models to identify the most important features correlated with miscalibration, given different algorithms and dataset characteristics. Our analysis is intended to help system designers predict miscalibration effects and to develop recommendation algorithms with improved calibration properties.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
HT '20: Proceedings of the 31st ACM Conference on Hypertext and Social Media
Page Range / eLocation ID:
197 to 206
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Recently there has been a growing interest in fairness-aware recommender systems including fairness in providing consistent performance across different users or groups of users. A recommender system could be considered unfair if the recommendations do not fairly represent the tastes of a certain group of users while other groups receive recommendations that are consistent with their preferences. In this paper, we use a metric called miscalibration for measuring how a recommendation algorithm is responsive to users’ true preferences and we consider how various algorithms may result in different degrees of miscalibration for different users. In particular, we conjecture that popularity bias which is a well-known phenomenon in recommendation is one important factor leading to miscalibration in recommendation. Our experimental results using two real-world datasets show that there is a connection between how different user groups are affected by algorithmic popularity bias and their level of interest in popular items. Moreover, we show that the more a group is affected by the algorithmic popularity bias, the more their recommendations are miscalibrated. 
    more » « less
  2. Latent factor models have achieved great success in personalized recommendations, but they are also notoriously difficult to explain. In this work, we integrate regression trees to guide the learning of latent factor models for recommendation, and use the learnt tree structure to explain the resulting latent factors. Specifically, we build regression trees on users and items respectively with user-generated reviews, and associate a latent profile to each node on the trees to represent users and items. With the growth of regression tree, the latent factors are gradually refined under the regularization imposed by the tree structure. As a result, we are able to track the creation of latent profiles by looking into the path of each factor on regression trees, which thus serves as an explanation for the resulting recommendations. Extensive experiments on two large collections of Amazon and Yelp reviews demonstrate the advantage of our model over several competitive baseline algorithms. Besides, our extensive user study also confirms the practical value of explainable recommendations generated by our model. 
    more » « less
  3. Explaining automatically generated recommendations allows users to make more informed and accurate decisions about which results to utilize, and therefore improves their satisfaction. In this work, we develop a multi-task learning solution for explainable recommendation. Two companion learning tasks of user preference modeling for recommendation and opinionated content modeling for explanation are integrated via a joint tensor factorization. As a result, the algorithm predicts not only a user's preference over a list of items, i.e., recommendation, but also how the user would appreciate a particular item at the feature level, i.e., opinionated textual explanation. Extensive experiments on two large collections of Amazon and Yelp reviews confirmed the effectiveness of our solution in both recommendation and explanation tasks, compared with several existing recommendation algorithms. And our extensive user study clearly demonstrates the practical value of the explainable recommendations generated by our algorithm. 
    more » « less
  4. Fitness trackers are undoubtedly gaining in popularity. As fitness-related data are persistently captured, stored, and processed by these devices, the need to ensure users’ privacy is becoming increasingly urgent. In this paper, we apply a data-driven approach to the development of privacy-setting recommendations for fitness devices. We first present a fitness data privacy model that we defined to represent users’ privacy preferences in a way that is unambiguous, compliant with the European Union’s General Data Protection Regulation (GDPR), and able to represent both the user and the third party preferences. Our crowdsourced dataset is collected using current scenarios in the fitness domain and used to identify privacy profiles by applying machine learning techniques. We then examine different personal tracking data and user traits which can potentially drive the recommendation of privacy profiles to the users. Finally, a set of privacy-setting recommendation strategies with different guidance styles are designed based on the resulting profiles. Interestingly, our results show several semantic relationships among users’ traits, characteristics, and attitudes that are useful in providing privacy recommendations. Even though several works exist on privacy preference modeling, this paper makes a contribution in modeling privacy preferences for data sharing and processing in the IoT and fitness domain, with specific attention to GDPR compliance. Moreover, the identification of well-identified clusters of preferences and predictors of such clusters is a relevant contribution for user profiling and for the design of interactive recommendation strategies that aim to balance users’ control over their privacy permissions and the simplicity of setting these permissions. 
    more » « less
  5. null (Ed.)
    Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of these patterns reflect important real-world phenomena driving interactions between the various users and items; other patterns may be irrelevant or reflect undesired discrimination, such as discrimination in publishing or purchasing against authors who are women or ethnic minorities. In this work, we examine the response of collaborative filtering recommender algorithms to the distribution of their input data with respect to one dimension of social concern, namely content creator gender. Using publicly available book ratings data, we measure the distribution of the genders of the authors of books in user rating profiles and recommendation lists produced from this data. We find that common collaborative filtering algorithms tend to propagate at least some of each user’s tendency to rate or read male or female authors into their resulting recommendations, although they differ in both the strength of this propagation and the variance in the gender balance of the recommendation lists they produce. The data, experimental design, and statistical methods are designed to be reusable for studying potentially discriminatory social dimensions of recommendations in other domains and settings as well. 
    more » « less