Serendipity in Recommender Systems: A Systematic Literature Review

Ziarani, Reza Jafari; Ravanmehr, Reza

doi:10.1007/s11390-020-0135-9

Cited by 69 publications

(29 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the idea of serendipity has been proposed to solve the filter-bubble problem by offering novel, diverse and high-satisfaction recommendations. (Ziarani and Ravanmehr 2021) gave general explanations about why serendipity items could work for tackling the filter-bubble situations. (Yang et al 2018) proposed a matrix factorization-based model for enhancing serendipity for superior recommendations.…”

Section: Related Workmentioning

confidence: 99%

“…To address the filter-bubble problem, most researchers so far have focused on exploiting auxiliary information such as users' attributes (Bi et al 2020), user's social relations (Fu et al 2021), and item's description text (Chae et al 2020) or reviews (Wang, Ounis, and Macdonald 2021). Along with this line, serendipity-oriented recommender system are proposed to make unexpected but valuable items to users (Yang et al 2018;Ziarani and Ravanmehr 2021). However, their models are effective and useful only when these auxiliary information are available.…”

Section: Introductionmentioning

confidence: 99%

“…Our research focuses on original rating-based RS, a Top-K recommendation task with only one user-item rating matrix, without requiring any auxiliary information or changing the existing recommendation models. In this context, data completion has been the most popular algorithm to tackle the CS problem (Chae et al 2020;Kim and Suh 2019;Ziarani and Ravanmehr 2021). These models fill the sparse user-item rating matrix by inferring the data distribution from existing ratings to relieve the cold-start problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems

Xu¹,

Yue²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

Classical accuracy-oriented Recommender Systems (RSs) typically face the cold-start problem and the filter-bubble problem when users suffer the familiar, repeated, and even predictable recommendations, making them boring and unsatisfied. To address the above issues, serendipity-oriented RSs are proposed to recommend appealing and valuable items significantly deviating from users' historical interactions and thus satisfying them by introducing unexplored but relevant candidate items to them. In this paper, we devise a novel serendipity-oriented recommender system (Generative Self-Serendipity Recommender System, GS 2 -RS) that generates users' self-serendipity preferences to enhance the recommendation performance. Specifically, this model extracts users' interest and satisfaction preferences, generates virtual but convincible neighbors' preferences from themselves, and achieves their self-serendipity preference. Then these preferences are injected into the rating matrix as additional information for RS models. Note that GS 2 -RS can not only tackle the cold-start problem but also provides diverse but relevant recommendations to relieve the filter-bubble problem. Extensive experiments on benchmark datasets illustrate that the proposed GS 2 -RS model can significantly outperform the state-of-the-art baseline approaches in serendipity measures with a stable accuracy performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems

Xu¹,

Yue²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Hence, SLR is more comprehensive, has lower risk of bias, has more formal and systematic protocols, but is relatively slower compared to narrative and traditional literature reviews. Recently, several studies used this type of review in the field of recommender systems [15][16][17].…”

Section: Survey Strategymentioning

confidence: 99%

Recommender Systems in the Real Estate Market—A Survey

2021

View full text Add to dashboard Cite

The shift to e-commerce has changed many business areas. Real estate is one of the applications that has been affected by this modern technological wave. Recommender systems are intelligent models that assist users of real estate platforms in finding the best possible properties that fulfill their needs. However, the recommendation task is substantially more challenging in the real estate domain due to the many domain-specific limitations that impair typical recommender systems. For instance, real estate recommender systems usually face the clod-start problem where there are no historical logs for new users or new items, and the recommender system should provide recommendations for these new entities. Therefore, the recommender systems in the real estate market are different and substantially less studied than in other domains. In this article, we aim at providing a comprehensive and systematic literature review on applications of recommender systems in the real estate market. We evaluate a set of research articles (13 journal and 13 conference papers) which represent the majority of research and commercial solutions proposed in the field of real estate recommender systems. These papers have been reviewed and categorized based on their methodological approaches, the main challenges that they addressed, and their evaluation procedures. Based on these categorizations, we outlined some possible directions for future research.

show abstract

“…The feedback loop effect is studied in real and model systems as an undesirable phenomenon related to reliable and ethical AI. Some of the consequences of the effect are induced shift in users interests [6], loss of novelty and diversity in recommendations [14], presence of "echo chambers" and "filter bubbles" [4,5], induced concept drift in housing prices prediction [8]. Nevertheless, a full description of the feedback loop effect and its existence conditions is still lacking for many cases [10,1].…”

Section: Introductionmentioning

confidence: 99%

Existence conditions for hidden feedback loops in online recommender systems

Khritankov,

Pilkevich

2021

Preprint

View full text Add to dashboard Cite

We explore a hidden feedback loops effect in online recommender systems. Feedback loops result in degradation of online multi-armed bandit (MAB) recommendations to a small subset and loss of coverage and novelty. We study how uncertainty and noise in user interests influence the existence of feedback loops. First, we show that an unbiased additive random noise in user interests does not prevent a feedback loop. Second, we demonstrate that a non-zero probability of resetting user interests is sufficient to limit the feedback loop and estimate the size of the effect. Our experiments confirm the theoretical findings in a simulated environment for four bandit algorithms.

show abstract

Serendipity in Recommender Systems: A Systematic Literature Review

Cited by 69 publications

References 97 publications

Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems

Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems

Recommender Systems in the Real Estate Market—A Survey

Existence conditions for hidden feedback loops in online recommender systems

Contact Info

Product

Resources

About