Prick the filter bubble: A novel cross domain recommendation model with adaptive diversity regularization

Sun, Jun; Song, Jian; Jiang, Yuanchun; Liu, Yezheng; Li, Jun

doi:10.1007/s12525-021-00492-1

Cited by 11 publications

(9 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diversity of approaches and conclusions contributes to a comprehensive understanding of the filter bubble phenomenon and provides insights for future research directions. Postulated 27 (Vrijenhoek et al, 2021a;Donkers and Ziegler, 2021;Tommasel et al, 2021;Wu et al, 2018) (Makhortykh and Wijermars, 2021;Gharahighehi and Vens, 2021b;Lunardi et al, 2020;Aridor et al, 2020) (Polatidis et al, 2020;Milano et al, 2020;Gharahighehi and Vens, 2021c;Lhérisson et al, 2017) (Gharahighehi and Vens, 2020;Joris et al, 2019;Kamishima et al, 2012Kamishima et al, , 2013Nguyen et al, 2014) (Helberger et al, 2018;Symeonidis et al, 2019b;Celis et al, 2019;Abbas et al, 2021) (Lunardi, 2019;Sun et al, 2021;Zhao et al, 2020;Sun et al, 2020;Gao et al, 2022b;Dokoupil, 2022b) 0 -…”

Section: Discussion and Findingsmentioning

confidence: 99%

“…Similarly, Sun et al (2021) proposed an adaptive diversity regularization Collaborative Deep Matrix Factorization (CDMF) model. Their approach utilizes social tags as a means to connect the target and source domains, resulting in improved recommendation accuracy and enhanced recommendation diversity through adaptive diversity regularization.…”

Section: Inclusion and Exclusion Selection Criteriamentioning

confidence: 99%

“…;Sun et al, 2020Sun et al, , 2021Zhao et al, 2020) 0 recommendation lists. Similarly,Gharahighehi and Vens (2021b) introduced techniques to enhance variety and accuracy in session-based RSs using sequential rule mining and session-based k nearest neighbor algorithms.…”

mentioning

confidence: 99%

“…This system promotes diet diversification by generating dynamic criticism that guides users through different search areas and encourages them to explore alternative examples. The authors evaluate the impact of DiversityBite on diversity through user research in the recipe domain.Similarly,(Sun et al, 2021) proposed an adaptive diversity regularization CDMF (Collaborative Deep Matrix Factorization) model. Their approach utilizes social tags as a means to connect the target and source domains, resulting in improved recommendation accuracy and enhanced recommendation diversity through adaptive diversity regularization.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Filter bubbles in recommender systems: Fact or fallacy—A systematic review

Areeb

Nadeem

Sohail

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

A filter bubble refers to the phenomenon where Internet customization effectively isolates individuals from diverse opinions or materials, resulting in their exposure to only a select set of content. This can lead to the reinforcement of existing attitudes, beliefs, or conditions. In this study, our primary focus is to investigate the impact of filter bubbles in recommender systems (RSs). This pioneering research aims to uncover the reasons behind this problem, explore potential solutions, and propose an integrated tool to help users avoid filter bubbles in RSs. To achieve this objective, we conduct a systematic literature review on the topic of filter bubbles in RSs. The reviewed articles are carefully analyzed and classified, providing valuable insights that inform the development of an integrated approach. Notably, our review reveals evidence of filter bubbles in RSs, highlighting several biases that contribute to their existence. Moreover, we propose mechanisms to mitigate the impact of filter bubbles and demonstrate that incorporating diversity into recommendations can potentially help alleviate this issue. The findings of this timely review will serve as a benchmark for researchers working in interdisciplinary fields such as privacy, artificial intelligence ethics, and RSs. Furthermore, it will open new avenues for future research in related domains, prompting further exploration and advancement in this critical area.This article is categorized under: Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction Application Areas > Internet Commercial, Legal, and Ethical Issues > Ethical Considerations Commercial, Legal, and Ethical Issues > Security and Privacy

show abstract

Section: Discussion and Findingsmentioning

confidence: 99%

Section: Inclusion and Exclusion Selection Criteriamentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Filter bubbles in recommender systems: Fact or fallacy—A systematic review

Areeb

Nadeem

Sohail

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…However, recommendation algorithms, despite their benefits, can create information-related stress (Ma et al, 2021). Another study by Sun et al (2021) discussed balancing the accuracy of recommendations with diversity. While humans retain the ability to make final decisions, using AI and algorithms to achieve desired outcomes, modifying algorithms can diminish the importance of factual accuracy.…”

Section: Research Backgroundmentioning

confidence: 99%

A.M.Aminee, J.Taylor. Generative AI Results and Reality

Aminee,

Taylor

2024

ai-edu

View full text Add to dashboard Cite

The accuracy of Generative Artificial Intelligence (GAI) tools is the product of the quality of underlying data used to train models, and the models themselves. This interplay between data and models can lead to differences in the accuracy of outputs provided to common prompts across different GAI tools. This study investigates the disparities in accuracy related to representativeness between the outputs of GAI tools and demographic data from National Center for Education Statistics (NCES) and large enrollment, regional comprehensive university in the western United States (CSU). Three GAI platforms - ChatGPT, Co-pilot, and Gemini were evaluated using five samples each, with the same instruction across all platforms: “Show a class of graduate students.” The GAI outputs were analyzed based on three demographic variables: gender, race, and age group. These outputs were then compared to national averages from the NCES for gender and race and the CSU for age group. Notably, the variances in the results showed broader distributions across the demographic variables. To assess accuracy, a representation rate metric was calculated, reflecting the average absolute variance from the NCES and CSU benchmarks. The findings highlight the opportunity of higher quality data in model training, as well as the necessity for improved algorithms and methodologies in GAI systems to represent complex demographic information more accurately.

show abstract