Explaining Recommendations

By Nava Tintarev. 2007

Subfields: 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 Recommender Systems

In Human-Computer Interaction

Citations in the corpus

Explaining Predictions from Tree-based Boosting Ensembles (2019, background): “Understanding how “black-box” models arrive at their predictions has sparked significant interest from both within and outside the IR community. can be in the context of rankings [11], recommendations [12], or digital assistants that engage in interactive question answering [8].”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “…and Benbasat, 2003; Polson and Richardson, 1988; Psotka, Massey, and Mutter, 1988; Ritter and Feurzeig, 1988; Silverman, 1992; Sleeman and Brown, 1982; Southwick, 1991; Swartout, Paris, and Moore, 1991; Tanner and Keuneke, 1991; Tintarev, 2007; Woolf, 2007; Woolf, Beck, Eliot, and Stern, 2001)”
The Effectiveness of Personalized Movie Explanations: An Experiment Using Commercial Meta-data (2008, methodology): “uk/∼ ereiter/simplenlg 3 The used meta-data considers the finding of focus groups and analysis of online movie reviews [5,11,6] as well as which features are readily available via Amazon’s”
The effects of recommendations’ presentation on persuasion and satisfaction in a movie recommender system (2010, background): “Tintarev and Masthoff [34, 36] researched the factors that subconsciously affect users when describing or evaluating a movie.”
Visualization of Explanations in Recommender Systems (2014, background): “In [20], the authors conducted a study consisting of seven focus groups totaling sixty seven participants to see whether users prefer the textual or the graphical presentation style.”
Explaining Recommendations: Design and Evaluation (2015, background): “much more extensively than in previous advisory systems, and in a much wider range of domains (varying from movies [73] to financial advice [26] to cultural heritage artifacts [20]).”