46,244 Hits in 6.2 sec

International Workshop on Algorithmic Bias in Search and Recommendation (Bias 2020) [chapter]

Ludovico Boratto, Mirko Marras, Stefano Faralli, Giovanni Stilo
2020 Lecture Notes in Computer Science  
In order to do so, such a relevance is usually computed by models trained on historical data, which is biased in most cases.  ...  Both search and recommendation algorithms provide results based on their relevance for the current user.  ...  websites. • Healthcare systems. • Social networks.  ... 
doi:10.1007/978-3-030-45442-5_84 fatcat:d3qzkywr5zhsfpfrfy24vcrwru

Bias and Debias in Recommender System: A Survey and Future Directions [article]

Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, Xiangnan He
2021 arXiv   pre-print
While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data.  ...  This makes various biases widely exist in the data, including but not limited to selection bias, position bias, exposure bias, and popularity bias.  ...  [30] develop a social network-based function by modeling item information propagation along the social network; Chen et al.  ... 
arXiv:2010.03240v2 fatcat:6fticc3otndsra2whs5e4nrdpi

Evolution of Ego-networks in Social Media with Link Recommendations

Luca Maria Aiello, Nicola Barbieri
2017 Proceedings of the Tenth ACM International Conference on Web Search and Data Mining - WSDM '17  
Last, with two link prediction experiments, we show how insights from our analysis can be used to improve the effectiveness of social recommender systems.  ...  In an online context, a key question is how link recommender systems may skew the growth of these networks, possibly restraining diversity.  ...  They find that most edges are added in short bursts separated by long inactivity intervals. Effect of social recommender systems.  ... 
doi:10.1145/3018661.3018733 dblp:conf/wsdm/AielloB17 fatcat:p5rml756fzg45no5ew2na7vayy

How algorithmic confounding in recommendation systems increases homogeneity and decreases utility

Allison J. B. Chaney, Brandon M. Stewart, Barbara E. Engelhardt
2018 Proceedings of the 12th ACM Conference on Recommender Systems - RecSys '18  
These systems are often evaluated or trained with data from users already exposed to algorithmic recommendations; this creates a pernicious feedback loop.  ...  Recommendation systems are ubiquitous and impact many domains; they have the potential to influence product consumption, individuals' perceptions of the world, and life-altering decisions.  ...  For our simulations (section 4), we use binary item attributes and learn real-valued user preferences. 7 A.3 Social Filtering Social filtering recommendation systems rely on a user's social network to  ... 
doi:10.1145/3240323.3240370 dblp:conf/recsys/ChaneySE18 fatcat:et4mqnixdncvlc3ydhmgbhfbci

Enhancing web activities with information visualization

Eduardo Graells-Garrido
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
Sometimes these biases are inherent in social behavior (like homophily), and sometimes they are external as they affect the system (like media bias).  ...  We select a Web activity, identify the biases that affect it, and evaluate how the biases affect a population from online social networks using web mining techniques, and then, we design a visualization  ...  Then, we will design a playful visualization to explore content generated on the social network using a geographical facet.  ... 
doi:10.1145/2567948.2567958 dblp:conf/www/Graells-Garrido14 fatcat:3scldqkfv5dcpmm5zgad3lxrri

Exposure Inequality in People Recommender Systems: The Long-Term Effects [article]

Francesco Fabbri, Maria Luisa Croci, Francesco Bonchi, Carlos Castillo
2021 arXiv   pre-print
People recommender systems may affect the exposure that users receive in social networking platforms, influencing attention dynamics and potentially strengthening pre-existing inequalities that disproportionately  ...  In this paper we introduce a model to simulate the feedback loop created by multiple rounds of interactions between users and a link recommender in a social network.  ...  The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  ... 
arXiv:2112.08237v1 fatcat:6zo37ujzafeulplmxd4zlfmvju

Beautiful and Damned. Combined Effect of Content Quality and Social Ties on User Engagement

Luca Maria Aiello, Rossano Schifanella, Miriam Redi, Stacey Svetlichnaya, Frank Liu, Simon Osindero
2017 IEEE Transactions on Knowledge and Data Engineering  
Beautiful images are evenly distributed in the network, although only a small core of people get social recognition for them.  ...  Our analysis has practical implications for improving link recommender systems.  ...  In this work we explore the impact of visual aesthetic quality in online social networks.  ... 
doi:10.1109/tkde.2017.2747552 fatcat:hnyc2psnnza6vhsp3til6khczm

Cross-Cutting Political Awareness through Diverse News Recommendations [article]

Bibek Paudel, Abraham Bernstein
2019 arXiv   pre-print
The suggestions generated by most existing recommender systems are known to suffer from a lack of diversity, and other issues like popularity bias.  ...  To promote the diversity of views, we developed a novel computational framework that can identify the political leanings of users and the news items they share on online social networks.  ...  A research paper based on this work is currently under submission.  ... 
arXiv:1909.01495v1 fatcat:m5nkz3tdpncslgibl4bcgvlica

Understanding Longitudinal Dynamics of Recommender Systems with Agent-Based Modeling and Simulation [article]

Gediminas Adomavicius and Dietmar Jannach and Stephan Leitner and Jingjing Zhang
2021 arXiv   pre-print
Today's research in recommender systems is largely based on experimental designs that are static in a sense that they do not consider potential longitudinal effects of providing recommendations to users  ...  In reality, however, various important and interesting phenomena only emerge or become visible over time, e.g., when a recommender system continuously reinforces the popularity of already successful artists  ...  The work presented in [33] further builds on the same ABM approach, but focuses on the longitudinal effects of preference biases.  ... 
arXiv:2108.11068v1 fatcat:pbi6oxnwp5amhnhxsi6omrs6ny

Network-based ranking in social systems: three challenges

Manuel S Mariani, Linyuan Lü
2020 Journal of Physics: Complexity  
Ranking algorithms are pervasive in our increasingly digitized societies, with important real-world applications including recommender systems, search engines, and influencer marketing practices.  ...  by various factors; (2) their effectiveness might be limited to specific problems; and (3) agents' decisions driven by rankings might result in potentially vicious feedback mechanisms and unhealthy systemic  ...  to this article as no new data were created or analysed in this study.  ... 
doi:10.1088/2632-072x/ab8a61 fatcat:zdrzhwohofbjzeovn43jfm7z5i

Systematic Evaluation of Social Recommendation Systems: Challenges and Future

Priyanka Rastogi, Dr. Vijendra
2016 International Journal of Advanced Computer Science and Applications  
Social Recommender System (SRS) exploits social contextual information in the form of social links of users, social tags, user-generated data that contain huge supplemental information about items or services  ...  But the key challenge lies in what all information can be collected and assimilated to make effective recommendations.  ...  CONCLUSION From the literature review, it can be concluded that Social information aided Recommender System have outperformed most traditional systems in making effective recommendations.  ... 
doi:10.14569/ijacsa.2016.070420 fatcat:wwvyumdr5ffohiphirbb3ycuoa

Adversarial Learning for Debiasing Knowledge Graph Embeddings [article]

Mario Arduini, Lorenzo Noci, Federico Pirovano, Ce Zhang, Yash Raj Shrestha, Bibek Paudel
2021 arXiv   pre-print
Such biases can have detrimental consequences on different population and minority groups as applications of KG begin to intersect and interact with social spheres.  ...  We also suggest the applicability of FAN for debiasing other network embeddings which could be explored in future work.  ...  Previous work in recommendation systems have reported the presence of popularity bias in popular ranking algorithms and ways to mitigate them.  ... 
arXiv:2006.16309v2 fatcat:ifplybaiqnekxlfjxz26ags7da

Data Portraits and Intermediary Topics

Eduardo Graells-Garrido, Mounia Lalmas, Ricardo Baeza-Yates
2016 Proceedings of the 21st International Conference on Intelligent User Interfaces - IUI '16  
We performed an "in the wild" evaluation of this platform, and found that people explored more recommendations when using a biased algorithm instead of ours.  ...  In line with our hypothesis, we also found that the mixture of our recommender algorithm and our user interface, allowed politically interested users to exhibit an unbiased exploration of the recommended  ...  This work was partially funded by Grant TIN2012-38741 (Understanding Social Media: An Integrated Data Mining Approach) of the Ministry of Economy and Competitiveness of Spain.  ... 
doi:10.1145/2856767.2856776 dblp:conf/iui/Graells-Garrido16a fatcat:oq43y3ud6va3virgjius66x2nq

Analysing the Effect of Recommendation Algorithms on the Amplification of Misinformation [article]

Miriam Fernández and Alejandro Bellogín and Iván Cantador
2021 arXiv   pre-print
Motivated by this fact, in this paper we present an analysis of the effect of some of the most popular recommendation algorithms on the spread of misinformation in Twitter.  ...  Recommendation algorithms have been pointed out as one of the major culprits of misinformation spreading in the digital sphere.  ...  In addition to the potential effect of item popularity, the information that users consume in social networking sites is also influenced by two other types of biases: (i) social biases and (ii) cognitive  ... 
arXiv:2103.14748v1 fatcat:x3xbvwajdjbojpyzfd34gngq2m

Combating Fake News with Interpretable News Feed Algorithms [article]

Sina Mohseni, Eric Ragan
2018 arXiv   pre-print
We discuss how improved user awareness and system transparency could mitigate unwanted outcomes of echo chambers and bubble filters in social media.  ...  Further, as demonstrated in recent political events in the US and EU, malicious bots and social media users can create and propagate targeted 'fake news' content in different forms for political gains.  ...  In another work, Hou et al. (2018) demonstrated methods to balance popularity bias in network-based recommendation systems and to significantly improve the system's diversity and accuracy.  ... 
arXiv:1811.12349v2 fatcat:ud4wixjxangsllbwtoxqawij4q
« Previous Showing results 1 — 15 out of 46,244 results