Explaining Recommendations: Satisfaction vs. Promotion

By Mustafa Bilgic, Raymond J. Mooney. 2005

324 citations recorded by the source corpus.

How researchers see this paper

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

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, methodology): “…to any classifier, or have been used on traditional classifiers such as support vector machines or decision trees (Akata, 2013; Akata, et al., 2015; Bilgic and Mooney, 2005; Biran and McKeown, 2014, 2017; Craven and Shavlik, 1996; Lakkaraju, Kamar, Caruana, and Leskovec, 2017; Lou, Caruana, and…”
Explainable Recommendation: A Survey and New Perspectives (2018, background): “[2009]), satisfaction (Bilgic and Mooney [2005]), and scrutability of the system (Knijnenburg et al.”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, background): “For example, Tintarev and Masthoff [2015] provides a survey in the context of recommendation systems, noting differences between the kind of explanations that manipulate trust [Cosley et al., 2003] and the kind that increase the odds of a good decision [Bilgic and Mooney, 2005].”
How to Design AI for Social Good: Seven Essential Factors (2020, background): “Explainability breeds trust in, and fosters adoption of, AI4SG solutions (Herlocker et al. 2000; Swearingen and Sinha 2002; Bilgic and Mooney 2005).”
Explainable Product Search with a Dynamic Relation Embedding Model (2019, background): “significantly improves user acceptance for recommended items [26, 55]. It benefits recommendation systems in multiple ways including user satisfaction, system transparency, debugging complexity, etc. [11, 15, 56, 74]. It is reasonable to assume that providing explanations for retrieval results will ”
ExpLOD: A Framework for Explaining Recommendations based on the Linked Open Data Cloud (2016, background): “This is an evaluation protocol which is very common in literature [1], whose insight is that an eﬀective explanation may help the user to evaluate to what extent she would like the recommendation, even before enjoying it.”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “lf-explanations. 7.2 M2: Explanation Usefulness and Satisfaction End-user satisfaction and usefulness of machine explanation are also of importance when evaluating explanations in intelligent systems [19]. Researchers use different subjective and objective measures for understandability, usefulness,”
Explanation-based Ranking in Opinionated Recommender Systems (2018, background): “Bilgic and Mooney [1] used keywords to justify items, ﬁnding that users tended to overestimate item quality when presented with this style of explanation.”
An Evaluation of the Human-Interpretability of Explanation (2019, background): “, 2003] and the kind that increase the odds of a good decision [Bilgic and Mooney, 2005].”
ReEL: Review Aware Explanation of Location Recommendation (2018, background): “The similarity-based approaches [4, 23] have proposed user-based neighbor style (e.g., "users with similar interest have purchased the following items..." ) explanations.”
Effective explanations of recommendations: user-centered design (2007, methodology): “Similarly, Bilgic and Mooney [2] failed to show a significant effect on Effectiveness for an explanation interface which used information about previously rated items, but where the explicit relations between these previously rated items and the current recommendation are not clear.”
No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML (2020, unknown): “Although, successful commercial projects, such Common Voice, 9 exemplify that users might be willing to spend time improving models.”
The FacT: Taming Latent Factor Models for Explainability with Factorization Trees (2019, background): “y calls for transparency, i.e., explaining how/why the customized result is presented to a user [20, 34, 38, 39]. Previous research has shown that explanations help users make more accurate decisions [2], improve their acceptance of recommendations [9], and also increase their trust in the system Pe”
Collaborative Filtering Recommender Systems (2011, background): “Bilgic andMooney [17] argue that for many domains, user satisfaction with the item is more important than whether they act on the recommendation: satisfaction and effectiveness are more critical to evaluate than persuasiveness.”
A historical perspective of explainable Artificial Intelligence (2020, background): “” This is called User style (Bilgic & Mooney, 2005) as it is based on users performing similar actions like buying or rating items (see also Figure 6).”
User Preferences for Hybrid Explanations (2017, background): “Existing work has explored user preferences for these single-style explanations [2, 8].”
The effects of recommendations’ presentation on persuasion and satisfaction in a movie recommender system (2010, background): “Thus, text is combined with image [18, 35] or sound [16 ]( http:// www.musicovery.com) in the recommendation lists, while graphs are utilized mainly in recommendations’ explanations [ 3 , 12].”
Faithful Multimodal Explanation for Visual Question Answering (2018, background): “…explanations should more faithfully reflect the actual processing of the underlying system in order to provide users with a deeper understanding of the system that increases trust for the right reasons, rather than simply trying to convince them of the system’s reliability (Bilgic and Mooney 2005).”