A Survey of Explanations in Recommender Systems

By Nava Tintarev, Judith Masthoff. 2007

604 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Safety, Robustness & Interpretability, Recommender Systems

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Systems

In Safety, Robustness & Interpretability

In Recommender Systems

Citations in the corpus

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “nts of the loss Lwith respect to model parameters Θ, and update all parameters by back-propagation based on the sampled minibatch. 3.5 Discussion 3.5.1 Explainability. Explainable recommender systems [24] aim to reveal why a user might like a particular item, which helps improve their acceptance or ”
Knowledge-aware Autoencoders for Explainable Recommender Systems (2018, background): “The main advantages users may get from the explanation are described in [17] and they include: transparency, scrutability, trust, effectiveness, persuasiveness, efficiency and satisfaction.”
Explainable Recommendation: A Survey and New Perspectives (2018, background): “cial to read other related surveys such as explanations in recommender systems from a user study perspective (Tintarev and Masthoff, 2007a), interpretable machine learning (Lipton, 2018; Molnar, 2019), as well as explainable AI in general (Gunning, 2017; Samek et al.”
A user-centric evaluation framework for recommender systems (2011, background): “In addition, Tintarev and Masthoff [23] defined in detail possible aims of explanation facilities: transparency, scrutability, trust, effectiveness, persuasiveness, efficiency, and satisfaction.”
Explore, exploit, and explain: personalizing explainable recommendations with bandits (2018, background): “Adding an associated explanation for a recommendation (abbreviated as recsplanation [16]), is known to increase user satisfaction and the persuasiveness of recommendations [6, 13, 24] Explanations in recommender systems have the goals of both providing information about recommended items and encoura”
Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering (2016, methodology): “Generic methodologies for communicating explanations to the user have been studied in [42], [11], [12].”
Tagsplanations: explaining recommendations using tags (2009, background): “Future research might also address a broader set of goals, including scrutability, transparency, and trust [16].”
Ontology Matching: State of the Art and Future Challenges (2013, background): “the abstraction techniques extensively and build on top of the work on explanations in recommender systems [145].”
Visually Explainable Recommendation (2018, background): “Researchers have pointed out long ago that providing appropriate explanations is beneficial to recommender systems in terms of recommendation persuasiveness, satisfaction, effectiveness, and scrutability, etc [12, 28].”
Who Also Likes It? Generating the Most Persuasive Social Explanations in Recommender Systems (2014, methodology): “Persuasiveness, defined as the power of convincing users to try(Tintarev and Masthoff 2007), is evaluated by real user’s rating on the persuasiveness of various explanations, which will be explained in details in section 4 and 5.”
Factorization meets the neighborhood: a multifaceted collaborative filtering model (2008, background): “In fact, the importance of explaining automated recommendations is widely recognized [11, 23].”
Inspectability and control in social recommenders (2012, background): “[44] also introduces the concept of scrutability with the (more interactive) aim to “allow users to tell the system it is wrong”, while Czarkowski and Kay [9] examine scrutability and control as separate mechanisms, in the context of a student model application.”
Aspects of Intelligent Systems Explanation (2013, background): “[55] has examined content based explanations and lists transparency, trustworthiness, user performance (i.”
Explaining Recommendations (2007, neutral): “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”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “Transparency [222,33] Explain how the system works Effectiveness [222] Help users make good decisions Trust [222,33] Increase users’ confidence in the system Persuasiveness [222,33] Convince users to try or buy Satisfaction [222] Increase the ease of use or enjoyment Education [33] Allow users to le”
A Hybrid Explanations Framework for Collaborative Filtering Recommender Systems (2014, background): “Several algorithms have been presented in the past and extensive surveys can be found in [3, 6].”