Evaluating the effectiveness of explanations for recommender systems

By Nava Tintarev, Judith Masthoff. 2012

337 citations recorded by the source corpus.

Subfields: Information Systems, Management Science and Operations Research, Marketing

How researchers see this paper

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

In Information Systems

In Management Science and Operations Research

In Marketing

Citations in the corpus

Knowledge-aware Autoencoders for Explainable Recommender Systems (2018, methodology): “In [19], the authors show how they can be exploited as evaluation metrics for explanatory services.”
Transparent, Scrutable and Explainable User Models for Personalized Recommendation (2019, background): “For the ease of presentation, all our examples are from the domain of our evaluation dataset, movies, as this has been a fertile area of recommendation systems research both from an algorithmic and from an explainability perspective [6, 8, 17, 22, 48, 51].”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “(Non-)personalised decisive features (popularity): movies I (Tintarev and Masthoff 2012)”
Designing Theory-Driven User-Centric Explainable AI (2019, background): “, [65, 69, 81, 98]), however, Lim and Dey have also found that users should not trust systems when they are poorly performing;”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “Increased transparency has been associated with many beneﬁts, including increased user acceptance of (or satisfaction with) recommendations and predictions [4, 8, 42], improved training of intelligent agents [41], and increased trust in the system’s predictions [10].”
Visualization of Explanations in Recommender Systems (2014, background): “Their study was followed by a number of works such as [3]-[8].”
ReEL: Review Aware Explanation of Location Recommendation (2018, result): “Contrary to that, some of the studies [17, 18, 35, 36, 40, 41, 43, 57] have already claimed the user persuasiveness due to explainability in real-world systems.”
Style in the long tail: discovering unique interests with latent variable models in large scale social E-commerce (2014, background): “[20]) that users appreciate explanations of why certain content is being recommended to them.”
Evaluating Recommender Systems with User Experiments (2015, background): “We reiterate the conclusion by [72, 111] that future work should explore how explanations can help to reduce choice overload and otherwise improve users’ decision-making.”
Designing Explanation Interfaces for Transparency and Beyond (2019, background): “, enhancing the system explainability) can achieve different explanatory goals which help users to make a better decision or persuading them to accept the suggestions from a system [14, 16].”
User Trust in Intelligent Systems: A Journey Over Time (2016, methodology): “The effect of explanations on user trust has been examined using existing methods [1, 12, 16].”
Automatic Generation of Natural Language Explanations (2017, background): “Explanations showed to increase the effectiveness of the recommendation and the user’s satisfaction [26] in various evaluations methods.”
Make it personal: A social explanation system applied to group recommendations (2017, background): “…based on how to present them (Herlocker et al., 2000): 1) showing an explicative text giving a reason or justification for (Zanker and Ninaus, 2010; Tintarev and Masthoff, 2012) or 2) using images to enhance the credibility of information (Sharma and Cosley, 2013; Fogg et al., 2001; Nguyen and…”
ExpLOD: A Framework for Explaining Recommendations based on the Linked Open Data Cloud (2016, methodology): “Those baselines were already adopted in literature [8] for similar experimental protocols.”
Explanations as Mechanisms for Supporting Algorithmic Transparency (2018, background): “Explanations present information about how the system produced the recommendation and the reasons behind it [3, 24, 52], and are in service to the system’s purpose and goals [20].”
Crowd-Based Personalized Natural Language Explanations for Recommendations (2016, methodology): “[20] also experimented with filling a template with movie meta data.”
SAsSy - Making Decisions Transparent with Argumentation and Natural Language Generation (2014, background): “However, there are other reasons why explanations may be introduced to an IS including transparency and scrutability [8] – helping users understand how decisions were made (transparency), as well as allowing users to tell the system that it is wrong (scrutability).”