Counteracting the filter bubble in recommender systems: Novelty-aware matrix factorization

Symeonidis, Panagiotis; Çoba, Ludovik; Zanker, Markus

doi:10.3233/ia-190017

Cited by 10 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Symeonidis et al [156] propose a popularity-based and a distance-based novelty-aware matrix factorization technique to address the problem of filter bubbles created by recommender systems. Novelty-aware matrix factorization introduces in the classic regularized matrix factorization model a soft constraint that controls how new items are being recommended.…”

Section: Fairness Of Recommendationsmentioning

confidence: 99%

A survey on knowledge-aware news recommender systems

Iana

Alam

Paulheim

2024

View full text Add to dashboard Cite

News consumption has shifted over time from traditional media to online platforms, which use recommendation algorithms to help users navigate through the large incoming streams of daily news by suggesting relevant articles based on their preferences and reading behavior. In comparison to domains such as movies or e-commerce, where recommender systems have proved highly successful, the characteristics of the news domain (e.g., high frequency of articles appearing and becoming outdated, greater dynamics of user interest, less explicit relations between articles, and lack of explicit user feedback) pose additional challenges for the recommendation models. While some of these can be overcome by conventional recommendation techniques, injecting external knowledge into news recommender systems has been proposed in order to enhance recommendations by capturing information and patterns not contained in the text and metadata of articles, and hence, tackle shortcomings of traditional models. This survey provides a comprehensive review of knowledge-aware news recommender systems. We propose a taxonomy that divides the models into three categories: neural methods, non-neural entity-centric methods, and non-neural path-based methods. Moreover, the underlying recommendation algorithms, as well as their evaluations are analyzed. Lastly, open issues in the domain of knowledge-aware news recommendations are identified and potential research directions are proposed.

show abstract

Section: Fairness Of Recommendationsmentioning

confidence: 99%

A survey on knowledge-aware news recommender systems

Iana

Alam

Paulheim

2024

View full text Add to dashboard Cite

show abstract

“…Studies focused on the popularity bias and calibration phenomena often aim to minimize some form of disproportionality between the proposed recommendations and user profiles (Abdollahpouri et al 2020;Steck 2018). Also, methods dealing with the filter bubbles phenomenon mostly focus on some form of similarity relaxation among recommended items (Lunardi et al 2020), or introduce additional optimization axis less correlated with the estimated relevance of items (Symeonidis et al 2019). As a result, they indirectly manipulate with the proportionality of exploitation-and exploration-oriented recommendations.…”

Section: Motivationmentioning

confidence: 99%

“…Mansoury 2021; Elahi et al 2021). The other direction considers the long-term effects of RS exposure (Nguyen et al 2014;Symeonidis et al 2019;Ge et al 2020;Lunardi et al 2020;Sinha et al 2016), which is more relevant for our work.…”

Section: Introductionmentioning

confidence: 99%

Rank-sensitive proportional aggregations in dynamic recommendation scenarios

Balcar

Škrhák

Peška

2022

User Model User-Adap Inter

View full text Add to dashboard Cite

In this paper, we focus on the problem of rank-sensitive proportionality preservation when aggregating outputs of multiple recommender systems in dynamic recommendation scenarios. We believe that individual recommenders may provide complementary views on the user’s preferences or needs, and therefore, their proportional (i.e. unbiased) aggregation may be beneficial for the long-term user satisfaction. We propose an aggregation framework (FuzzDA) based on a modified D’Hondt’s algorithm (DA) for proportional mandates allocation. Specifically, we adjusted DA to register fuzzy membership of items and modified the selection procedure to balance both relevance and proportionality criteria. Furthermore, we propose several iterative votes assignment strategies and negative implicit feedback incorporation strategies to make FuzzDA framework applicable in dynamic recommendation scenarios. Overall, the framework should provide benefits w.r.t. long-term novelty of recommendations, diversity of recommended items as well as overall relevance. We evaluated FuzzDA framework thoroughly both in offline simulations and in online A/B testing. Framework variants outperformed baselines w.r.t. click-through rate (CTR) in most of the evaluated scenarios. Some variants of FuzzDA also provided the best or close-to-best iterative novelty (while maintaining very high CTR). While the impact of the framework variants on user-wise diversity was not so extensive, the trade-off between CTR and diversity seems reasonable.

show abstract

“…However, these solutions are difficult to deploy in practice because they rely on the will of the users to change their viewpoints. In Symeonidis et al (2019), the authors propose a popularity-based matrix-factorization computation for recommending new items. This approach offers a trade-off for the matrix-factorization performance with respect to the criteria of novelty while only minimally compromising on accuracy.…”

Section: Related Workmentioning

confidence: 99%

Reducing the filter bubble effect on Twitter by considering communities for recommendations

Grossetti

Mouza

Travers

et al. 2021

IJWIS

View full text Add to dashboard Cite

Purpose Social network platforms are considered today as a major communication mean. Their success leads to an unprecedented growth of user-generated content; therefore, finding interesting content for a given user has become a major issue. Recommender systems allow these platforms to personalize individual experience and increase user engagement by filtering messages according to user interest and/or neighborhood. Recent research results show, however, that this content personalization might increase the echo chamber effect and create filter bubbles that restrain the diversity of opinions regarding the recommended content. Design/methodology/approach The purpose of this paper is to present a thorough study of communities on a large Twitter data set that quantifies the effect of recommender systems on users’ behavior by creating filter bubbles. The authors further propose their community-aware model (CAM) that counters the impact of different recommender systems on information consumption. Findings The authors propose their CAM that counters the impact of different recommender systems on information consumption. The study results show that filter bubbles effects concern up to 10% of users and the proposed model based on the similarities between communities enhance recommendations. Originality/value The authors proposed the CAM approach, which relies on similarities between communities to re-rank lists of recommendations to weaken the filter bubble effect for these users.

show abstract

Counteracting the filter bubble in recommender systems: Novelty-aware matrix factorization

Cited by 10 publications

References 11 publications

A survey on knowledge-aware news recommender systems

A survey on knowledge-aware news recommender systems

Rank-sensitive proportional aggregations in dynamic recommendation scenarios

Reducing the filter bubble effect on Twitter by considering communities for recommendations

Contact Info

Product

Resources

About