Exploring author gender in book rating and recommendation

@article{Ekstrand2018ExploringAG,
  title={Exploring author gender in book rating and recommendation},
  author={Michael D. Ekstrand and Mucun Tian and Mohammed R. Imran Kazi and Hoda Mehrpouyan and Daniel Kluver},
  journal={Proceedings of the 12th ACM Conference on Recommender Systems},
  year={2018}
}
Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of the patterns in rating datasets reflect important real-world differences between the various users and items in the data; other patterns may be irrelevant or possibly undesirable for social or ethical reasons, particularly if they reflect undesired discrimination, such as gender or ethnic discrimination in publishing. In this work, we examine… 

Figures and Tables from this paper

Revisiting Popularity and Demographic Biases in Recommender Evaluation and Effectiveness
TLDR
It is found that total usage and the popularity of consumed content are strong predictors of recommender performance and also vary significantly across demographic groups, and that the utility is higher for users from countries with more representation in the dataset.
The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses
TLDR
This paper compares existing algorithms and their recommended lists against biases related to course popularity, catalog coverage, and course category popularity, and remarks even more the need of better understanding how recommenders react against bias in diverse contexts.
Calibration in Collaborative Filtering Recommender Systems: a User-Centered Analysis
TLDR
A systematic analysis aimed at identifying key characteristics in user profiles that might lead to miscalibrated recommendations and develops predictive models of miscalibration, which are intended to help system designers predict miscalIBration effects and to develop recommendation algorithms with improved calibration properties.
Exploring and Mitigating Gender Bias in Recommender Systems with Explicit Feedback
TLDR
This paper proposes a model to quantify the gender bias present in book rating datasets and in the recommendations produced by the recommender systems, and theoretically shows that the proposed approach provides unbiased recommendations despite biased data.
Break the Loop: Gender Imbalance in Music Recommenders
TLDR
This work analyzes a widely-used collaborative filtering approach with two public datasets-enriched with gender information-to understand how this approach performs with respect to the artists' gender and proposes a progressive re-ranking method based on the insights from the interviews.
Exploring Artist Gender Bias in Music Recommendation
TLDR
This work presents an exploratory study, analyzing the extent to which commonly deployed state of the art Collaborative Filtering algorithms may act to further increase or decrease artist gender bias, and deploys a recently proposed metric of bias disparity on two listening event datasets.
Popularity Bias in Recommendation: A Multi-stakeholder Perspective
TLDR
This dissertation, which studies the impact of popularity bias in recommender systems from a multi-stakeholder perspective, proposes several algorithms each approaching the popularity bias mitigation from a different angle and compares their performances using several metrics with some other state-of-the-art approaches in the literature.
Addressing Marketing Bias in Product Recommendations
TLDR
This paper investigates the correlation between users' interaction feedback and products' marketing images on two real-world e-commerce datasets and develops a framework to address this potential marketing bias, and demonstrates that the proposed approach significantly improves the recommendation fairness across different market segments, with a negligible loss of recommendation accuracy.
...
...

References

SHOWING 1-10 OF 81 REFERENCES
Recommender Response to Diversity and Popularity Bias in User Profiles
TLDR
It is found that the diversity and popularity of movies in users’ profiles has little impact on the recommendations they receive, and the conditions under which common algorithms produce more or less diverse or popular recommendations are probed.
Temporal diversity in recommender systems
TLDR
It is shown that temporal diversity is an important facet of recommender systems, by showing how CF data changes over time and performing a user survey, and proposed and evaluated set methods that maximise temporal recommendation diversity without extensively penalising accuracy.
What recommenders recommend: an analysis of recommendation biases and possible countermeasures
TLDR
It is shown that popular recommendation techniques—despite often being similar when compared with the help of accuracy measures—can be quite different with respect to which items they recommend.
Improving recommendation lists through topic diversification
TLDR
This work presents topic diversification, a novel method designed to balance and diversify personalized recommendation lists in order to reflect the user's complete spectrum of interests, and introduces the intra-list similarity metric to assess the topical diversity of recommendation lists.
All The Cool Kids, How Do They Fit In?: Popularity and Demographic Biases in Recommender Evaluation and Effectiveness
TLDR
System evaluation protocols that explicitly quantify the degree to which the system is meeting the information needs of all its users are proposed, as well as the need for researchers and operators to move beyond evaluations that favor the needs of larger subsets of the user population while ignoring smaller subsets.
Novelty and Diversity in Top-N Recommendation -- Analysis and Evaluation
TLDR
It is argued that the motivation of diversity research is to increase the probability of retrieving unusual or novel items which are relevant to the user and a methodology to evaluate their performance in terms of novel item retrieval is introduced.
Music Recommendation and Discovery in the Long Tail
TLDR
The Long Tail curve of artist popularity is model to predict —potentially— interesting and unknown music, hidden in the tail of the popularity curve, which has significant implications for recommender systems that assist users to explore the Long Tail, digging for content they might like.
Item-based top-N recommendation algorithms
TLDR
This article presents one class of model-based recommendation algorithms that first determines the similarities between the various items and then uses them to identify the set of items to be recommended, and shows that these item-based algorithms are up to two orders of magnitude faster than the traditional user-neighborhood based recommender systems and provide recommendations with comparable or better quality.
Collaborative Filtering Recommender Systems
TLDR
A wide variety of the choices available and their implications are discussed, aiming to provide both practicioners and researchers with an introduction to the important issues underlying recommenders and current best practices for addressing these issues.
Will the Global Village Fracture Into Tribes? Recommender Systems and Their Effects on Consumer Fragmentation
TLDR
Whether personalization is in fact fragmenting the online population does not appear to do so in this study, and appears to be a tool that helps users widen their interests, which in turn creates commonality with others.
...
...