Search Results for author: Michael D. Ekstrand

Found 23 papers, 3 papers with code

Candidate Set Sampling for Evaluating Top-N Recommendation

no code implementations21 Sep 2023 Ngozi Ihemelandu, Michael D. Ekstrand

The strategy for selecting candidate sets -- the set of items that the recommendation system is expected to rank for each user -- is an important decision in carrying out an offline top-$N$ recommender system evaluation.

Recommendation Systems

Towards Measuring Fairness in Grid Layout in Recommender Systems

no code implementations19 Sep 2023 Amifa Raj, Michael D. Ekstrand

We examine how fairness scores change with different ranking layouts to yield insights into (1) the consistency of fair ranking measurements across layouts; (2) whether rankings optimized for fairness in a linear ranking remain fair when the results are displayed in a grid; and (3) the impact of column reduction approaches to support different device geometries on fairness measurement.

Fairness Recommendation Systems

Distributionally-Informed Recommender System Evaluation

no code implementations12 Sep 2023 Michael D. Ekstrand, Ben Carterette, Fernando Diaz

Current practice for evaluating recommender systems typically focuses on point estimates of user-oriented effectiveness metrics or business metrics, sometimes combined with additional metrics for considerations such as diversity and novelty.

Recommendation Systems

Patterns of gender-specializing query reformulation

no code implementations25 Apr 2023 Amifa Raj, Bhaskar Mitra, Nick Craswell, Michael D. Ekstrand

There are many ways a query, the search results, and a demographic attribute such as gender may relate, leading us to hypothesize different causes for these reformulation patterns, such as under-representation on the original result page or based on the linguistic theory of markedness.


Overview of the TREC 2021 Fair Ranking Track

no code implementations21 Feb 2023 Michael D. Ekstrand, Graham McDonald, Amifa Raj, Isaac Johnson

The 2021 Fair Ranking track aimed to ensure that documents that are about, or somehow represent, certain protected characteristics receive a fair exposure to the Wikipedia editors, so that the documents have an fair opportunity of being improved and, therefore, be well-represented in Wikipedia.


Overview of the TREC 2022 Fair Ranking Track

no code implementations11 Feb 2023 Michael D. Ekstrand, Graham McDonald, Amifa Raj, Isaac Johnson

The 2022 Fair Ranking track aimed to ensure that documents that are about, or somehow represent, certain protected characteristics receive a fair exposure to the Wikipedia editors, so that the documents have an fair opportunity of being improved and, therefore, be well-represented in Wikipedia.


Much Ado About Gender: Current Practices and Future Recommendations for Appropriate Gender-Aware Information Access

no code implementations12 Jan 2023 Christine Pinney, Amifa Raj, Alex Hanna, Michael D. Ekstrand

Information access research (and development) sometimes makes use of gender, whether to report on the demographics of participants in a user study, as inputs to personalized results or recommendations, or to make systems gender-fair, amongst other purposes.

Fairness Information Retrieval +2

Matching Consumer Fairness Objectives & Strategies for RecSys

no code implementations6 Sep 2022 Michael D. Ekstrand, Maria Soledad Pera

The last several years have brought a growing body of work on ensuring that recommender systems are in some sense consumer-fair -- that is, they provide comparable quality of service, accuracy of representation, and other effects to their users.

Fairness Position +1

Fire Dragon and Unicorn Princess; Gender Stereotypes and Children's Products in Search Engine Responses

no code implementations28 Jun 2022 Amifa Raj, Michael D. Ekstrand

Search engines in e-commerce settings allow users to search, browse, and select items from a wide range of products available online including children's items.


Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation

no code implementations2 Oct 2021 Michael D. Ekstrand

Recommender systems research is concerned with many aspects of recommender system behavior and effects than simply its effectiveness, and simulation can be a powerful tool for uncovering these effects.

Position Recommendation Systems

Statistical Inference: The Missing Piece of RecSys Experiment Reliability Discourse

no code implementations14 Sep 2021 Ngozi Ihemelandu, Michael D. Ekstrand

In this paper, we argue that the use of statistical inference is a key component of the evaluation process that has not been given sufficient attention.

Information Retrieval Recommendation Systems +1

Pink for Princesses, Blue for Superheroes: The Need to Examine Gender Stereotypes in Kid's Products in Search and Recommendations

no code implementations13 May 2021 Amifa Raj, Ashlee Milton, Michael D. Ekstrand

In this position paper, we argue for the need to investigate if and how gender stereotypes manifest in search and recommender systems. As a starting point, we particularly focus on how these systems may propagate and reinforce gender stereotypes through their results in learning environments, a context where teachers and children in their formative stage regularly interact with these systems.


Fairness in Information Access Systems

no code implementations12 May 2021 Michael D. Ekstrand, Anubrata Das, Robin Burke, Fernando Diaz

Recommendation, information retrieval, and other information access systems pose unique challenges for investigating and applying the fairness and non-discrimination concepts that have been developed for studying other machine learning systems.

Fairness Information Retrieval +1

Comparing Fair Ranking Metrics

no code implementations2 Sep 2020 Amifa Raj, Michael D. Ekstrand

Ranked lists are frequently used by information retrieval (IR) systems to present results believed to be relevant to the users information need.

Fairness Information Retrieval +2

Evaluating Stochastic Rankings with Expected Exposure

no code implementations27 Apr 2020 Fernando Diaz, Bhaskar Mitra, Michael D. Ekstrand, Asia J. Biega, Ben Carterette

We introduce the concept of \emph{expected exposure} as the average attention ranked items receive from users over repeated samples of the same query.

Information Retrieval Retrieval

Overview of the TREC 2019 Fair Ranking Track

no code implementations25 Mar 2020 Asia J. Biega, Fernando Diaz, Michael D. Ekstrand, Sebastian Kohlmeier

The goal of the TREC Fair Ranking track was to develop a benchmark for evaluating retrieval systems in terms of fairness to different content providers in addition to classic notions of relevance.

Fairness Retrieval

Estimating Error and Bias in Offline Evaluation Results

1 code implementation26 Jan 2020 Mucun Tian, Michael D. Ekstrand

Offline evaluations of recommender systems attempt to estimate users' satisfaction with recommendations using static data from prior user interactions.

Recommendation Systems

Proceedings of FACTS-IR 2019

no code implementations12 Jul 2019 Alexandra Olteanu, Jean Garcia-Gathright, Maarten de Rijke, Michael D. Ekstrand

The proceedings list for the program of FACTS-IR 2019, the Workshop on Fairness, Accountability, Confidentiality, Transparency, and Safety in Information Retrieval held at SIGIR 2019.

Fairness Information Retrieval +1

Recommender Systems Notation: Proposed Common Notation for Teaching and Research

no code implementations4 Feb 2019 Michael D. Ekstrand, Joseph A. Konstan

In the course of years of teaching and research on recommender systems, we have seen the val-ue in adopting a consistent notation across our work.

Information Retrieval Recommendation Systems +1

LensKit for Python: Next-Generation Software for Recommender System Experiments

2 code implementations10 Sep 2018 Michael D. Ekstrand

LensKit is an open-source toolkit for building, researching, and learning about recommender systems.

Collaborative Filtering Recommendation Systems

Exploring Author Gender in Book Rating and Recommendation

2 code implementations22 Aug 2018 Michael D. Ekstrand, Daniel Kluver

Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items.

Collaborative Filtering

Cannot find the paper you are looking for? You can Submit a new open access paper.