The role of transparency in recommender systems

By R. Sinha, Kirsten Swearingen. 2002

582 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “…2009; Papadimitiou, Symeonidis and Manolopoulos, 2012; Pearl, 1988; Suermondt, 1992; Shafto and Goodman, 2008; Shafto, Goodman, and Griffiths, 2014; Sinha and Swearingen, 2002; Sørmo et al., 2005; Theis, Oord, and Bethge, 2015; Wang, Ruin, Velez-Doshi, Liu, Klampfl, and MacNeille, 2010a,b; Yap,…”
Knowledge-aware Autoencoders for Explainable Recommender Systems (2018, background): “Different studies [15, 18] have pointed out that introducing transparency in the recommendation process may have lots of advantages because users appear to be more satisfied with the recommendation if they are aware of the reasons why certain items are suggested.”
Explainable Recommendation: A Survey and New Perspectives (2018, background): “Research pioneers in very early stages also noticed the importance of the problem (Herlocker and Konstan, 2000; Herlocker et al., 2000; Sinha and Swearingen, 2002).”
Explaining Recommendations (2007, unknown): “In a literature survey (see [7] for details) we have identified seven different criteria by which explanations for single recommendations have been evaluated with users in the past: transparency [12], scrutability [13], trust [10, 14], effectiveness [1], persuasiveness [5], efficiency [15], and sati”
When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “In contrast, user-based explanations [134] leverage social relationships to make recommendations by explaining that users with similar interests also favor the recommended item .”
EventAction (2019, methodology): “In an experiment on music recommender systems, Sinha and Swearingen [68] examined the role of transparency by measuring recommenders’ ability to explain the recommendations to users.”
Tagsplanations: explaining recommendations using tags (2009, background): “Research shows that explanations help users make more accurate decisions [1], improve user acceptance of recommendations [6], and increase trust in the recommender system [13].”
Evaluating collaborative filtering recommender systems (2004, unknown): “…at measures including the degree to which the recommendations cover the entire set of items [Mobasher et al. 2001], the degree to which recommendations made are non-obvious [McNee et al. 2002], and the ability of recommenders to explain their recommendations to users [Sinha and Swearingen 2002].”
Crowd-Based Personalized Natural Language Explanations for Recommendations (2016, background): “Past research has shown several positive eﬀects of recommendation explanations, including increasing user trust in recommender systems [18] and helping users make good decisions on recommendations [20].”
How Much Information?: Effects of Transparency on Trust in an Algorithmic Interface (2016, background): “Increased transparency is also associated with fewer misconceptions [16] and higher confidence in system recommendations [29].”
E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact (2007, background): “Sinha and Swearingen (2002) suggest that one way for a user to decide whether to trust recommendations is to examine the success of prior suggestions from the RAs, as evidence of the RAs’ credibility.”
Explanations as Mechanisms for Supporting Algorithmic Transparency (2018, background): “When users believe they understand why a system makes a recommendation, they feel more comfortable and satisfied with recommendations [49], and are more willing to accept a recommendation [10].”
Designing and Evaluating Explanations for Recommender Systems (2011, background): “(Music) [55] X”
Transparency you can trust: Transparency requirements for artificial intelligence between legal norms and contextual concerns (2019, background): “In the context of recommender systems, for example, transparency of music recommendations increased participants’ satisfaction with the recommendation and their conﬁdence (Sinha and Swearingen, 2002).”
Evaluating the effectiveness of explanations for recommender systems (2012, background): “Music (Sinha and Swearingen 2002) X Movies (Tintarev and Masthoff 2008b) X X X Adaptive Place Advisor: restaurants (Thompson et al 2004) X X”
Music recommendation and discovery in the long tail (2008, background): “A recommender should be able to explain to the user why the system recommends the list of top–K items (Sinha and Swearingen, 2002).”