Query Understanding for Surfacing Under-served Music Content

Tomasi, Federico; Mehrotra, Rishabh; Pappu, Aasish; Bütepage, Judith; Brost, Brian M.; Galvão, Hugo; Lalmas, Mounia

doi:10.1145/3340531.3412741

Cited by 5 publications

(4 citation statements)

References 26 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Improvements in system design and enhanced data collection may produce better results even if the core algorithms are unchanged. Another design strategy is to differentiate between the contexts and their associated user expectations, to identify places in the application environment where users may be more amenable to exposure to diverse content (Hansen et al 2021;Tomasi et al 2020).…”

Section: Discussionmentioning

confidence: 99%

“…Aligned with the work presented in Tomasi et al. (2020), Sonboli et al. (2020) sees users' propensities towards diversity (measured by entropy) in their recommendation lists as opportunities to increase the exposure of under‐represented loans.…”

Section: Fairness‐enhancing Interventionsmentioning

confidence: 92%

“…This work was extended in Sonboli et al (2020), which consider multiple fairness concerns and users' preferences across multiple concerns. Aligned with the work presented in Tomasi et al (2020), Sonboli et al (2020) sees users' propensities towards diversity (measured by entropy) in their recommendation lists as opportunities to increase the exposure of under-represented loans.…”

Section: Post-processingmentioning

confidence: 96%

See 2 more Smart Citations

The multisided complexity of fairness in recommender systems

et al. 2022

Self Cite

View full text Add to dashboard Cite

Recommender systems are poised at the interface between stakeholders: for example, job applicants and employers in the case of recommendations of employment listings, or artists and listeners in the case of music recommendation. In such multisided platforms, recommender systems play a key role in enabling discovery of products and information at large scales. However, as they have become more and more pervasive in society, the equitable distribution of their benefits and harms have been increasingly under scrutiny, as is the case with machine learning generally. While recommender systems can exhibit many of the biases encountered in other machine learning settings, the intersection of personalization and multisidedness makes the question of fairness in recommender systems manifest itself quite differently. In this article, we discuss recent work in the area of multisided fairness in recommendation, starting with a brief introduction to core ideas in algorithmic fairness and multistakeholder recommendation. We describe techniques for measuring fairness and algorithmic approaches for enhancing fairness in recommendation outputs. We also discuss feedback and popularity effects that can lead to unfair recommendation outcomes. Finally, we introduce several promising directions for future research in this area.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Fairness‐enhancing Interventionsmentioning

confidence: 92%

Section: Post-processingmentioning

confidence: 96%

See 1 more Smart Citation

The multisided complexity of fairness in recommender systems

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Broad intents are an opportunity to surface under-served entities that would not be discovered otherwise without affecting user satisfaction [57]. While approaches to promote the discovery of entities have been studied from the perspective of recommender systems [1,42], they do not generalize to search engines where there is an input query.…”

Section: Introductionmentioning

confidence: 99%

Improving Content Retrievability in Search with Controllable Query Generation

Penha

Palumbo²,

Aziz

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is retrievable, i.e. there are queries for which the system will surface such entity in the top results. However, machine-learned search engines have a high retrievability bias, where the majority of the queries return the same entities. This happens partly due to the predominance of narrow intent queries, where users create queries using the title of an already known entity, e.g. in book search "harry potter". The amount of broad queries where users want to discover new entities, e.g. in music search "chill lyrical electronica with an atmospheric feeling to it", and have a higher tolerance to what they might find, is small in comparison. We focus here on two factors that have a negative impact on the retrievability of the entities (I) the training data used for dense retrieval models and (II) the distribution of narrow and broad intent queries issued in the system. We propose CtrlQGen, a method that generates queries for a chosen underlying intentnarrow or broad. We can use CtrlQGen to improve factor (I) by generating training data for dense retrieval models comprised of diverse synthetic queries. CtrlQGen can also be used to deal with factor (II) by suggesting queries with broader intents to users. Our results on datasets from the domains of music, podcasts, and books reveal that we can significantly decrease the retrievability bias of a dense retrieval model when using CtrlQGen. First, by using the generated queries as training data for dense models we make 9% of the entities retrievable-go from zero to non-zero retrievability. Second, by suggesting broader queries to users, we can make 12% of the entities retrievable in the best case.

show abstract