Explaining Recommendations: Design and Evaluation

By Nava Tintarev, Judith Masthoff. 2015

357 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Recommender Systems, Human-Computer Interaction

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 Information Systems

In Recommender Systems

In Human-Computer Interaction

Citations in the corpus

Explainable Recommendation: A Survey and New Perspectives (2018, background): “Recommendation explanations can be generated from different information sources and be presented in different display styles (Tintarev and Masthoff, 2015), e.”
A Survey of Methods for Explaining Black Box Models (2018, background): “For a survey of such approaches, we refer the reader to Reference [120].”
Manipulating and Measuring Model Interpretability (2018, background): “This problem is exacerbated by the fact that machine learning models have many different types of stakeholders and these stakeholders may have different needs in different scenarios [44, 99, 100].”
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].”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “Tintarev and Mastho identify seven purposes for recommender system explanations, namely: transparency, scrutability, trust, effectiveness, persuasiveness, efficiency and satisfaction [74].”
A historical perspective of explainable Artificial Intelligence (2020, background): “…(Guidotti et al., 2018), for both autonomous (Nunes & Jannach, 2017) and human-in-the-loop systems (Holzinger, 2016; Holzinger, Plass, et al., 2019), with applications in recommender systems (Tintarev & Masthof, 2015), and approaches of neural-symbolic learning and reasoning (Garcez et al., 2015).”
Explaining Social Recommendations to Casual Users: Design Principles and Opportunities (2018, methodology): “We did an online survey to collect necessary demographic information and self-reﬂection about how to design an explanation function in seven explanatory goals [2].”
Schema-summarization in linked-data-based feature selection for recommender systems (2017, background): “It is interesting to point out that having a higher number of features is also a plus if we consider other facilities that can be exposed by a recommendation engine such as explanation [23].”
Human Evaluation of Models Built for Interpretability (2019, background): “For example, Tintarev and Masthoff (2015) provide a survey in the context of recommendation systems, noting differences between the kind of system explanations that manipulate trust and the kind that increase the odds of a good decision.”
Transparent, Scrutable and Explainable User Models for Personalized Recommendation (2019, background): “Recommender systems represent an important branch of AI research and the explainability of recommendations has at-tracted considerable attention [49, 54].”
Designing Explanation Interfaces for Transparency and Beyond (2019, methodology): “We followed the seven explanatory goals that proposed by Tintarev and Masthoff [17]: Transparency, Scrutability, Trust, Persuasiveness, Effectiveness, Efficiency, and Satisfaction.”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “on the healthcare domain [169], the evaluation of local explanations [90], contrastive and counterfactual explanations [250] or explanations and their evaluation for recommender systems [189, 261].”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “Effectiveness The capacity of a method for explainability to support good user decision-making [71, 72, 73]”