Explaining collaborative filtering recommendations

By Jonathan L. Herlocker, J. Konstan, John Riedl. 2000

1,918 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

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, background): “improved, providing guiding posts for further developments [10]–[12].”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…Grecu, Modgil, South, and Patkar, 2007; Freuder, Likitvivatanavong, and Wallace, 2001; Haddawy, et al., 1997; Henrion and Druzdzel, 1990a, 1990b; Herlocker, Konstan, and Riedl, 2000; Khan, Poupart, and Black, 2009; Kisa, Van den Broeck, Choi, and Darwiche, 2014; Kofod-Petersen, Cassens, and…”
Knowledge-aware Autoencoders for Explainable Recommender Systems (2018, background): “Making a Recommender System (RS) transparent to users is getting more and more relevance since it may lead to users retain [8].”
Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “However, although the idea of collaborative filtering has achieved significant improvement on recommendation accuracy, CF is less intuitive to explain compared with many content-based algorithms, and research pioneers in very early stages also noticed the importance of the problem (Herlocker et al. ”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “In some cases, explanation increases trust and reliance [33, 85, 1, 30, 60], but in others an explanation may have the opposite effect if the level of detail it contains is deemed insufficient [7].”
Generating Predictive Movie Recommendations from Trust in Social Networks (2006, methodology): “MovieLens [5], Recommendz [6], and Film-Conseil [7] are just a few of the websites that implement recommender systems in the context of films.”
The effects of transparency on trust in and acceptance of a content-based art recommender (2008, background): “Herlocker et al. (2000) found that poorly designed explanations can actually hinder the acceptance of individual recommendations.”
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions (2005, background): “Other important research issues that have been explored in the recommender systems literature include explainability [12], [42], trustworthiness [28], scalability [4], [39], [91], [93], and privacy [82], [93] issues of recommender systems.”
Explaining the user experience of recommender systems (2012, background): “Herlocker et al. (2000) found that users like explanations in collaborative filtering recommender systems.”
Recommendation to Groups (2007, background): “Recommender systems for individuals often accompany each recommendation with some sort of analysis of its predicted acceptability; the analysis may range from a simple index of the system’s confidence to a complex visualization of the pros and cons of the recommended solution (see, e.g., Herlocker e”
Inspectability and control in social recommenders (2012, background): “Herlocker [19] argues that explanation provides transparency, “exposing the reasoning behind a recommendation”.”
Toward harnessing user feedback for machine learning (2007, background): “It has been shown that explanations that answer why certain outcomes happened, based on user actions, can contribute positively to system use [11, 18].”
Explicit factor models for explainable recommendation based on phrase-level sentiment analysis (2014, background): “Researchers have shown that providing appropriate explanations could improve user acceptance of the recommended items [10, 37], as well as benefit user experience in various other aspects, including system transparency, user trust, effectiveness, efficiency, satisfaction and scrutability [38, 3, 2].”
Make it personal: A social explanation system applied to group recommendations (2017, background): “Research in explanations started with the premise that users would more likely trust a recommendation when they know the rationale behind it (Herlocker et al., 2000; Zanker and Ninaus, 2010; Lamche et al., 2014; Symeonidis et al., 2009).”
A Survey on Conversational Recommender Systems (2020, background): “y represented recommendation were considered in a bandit approach to balance exploration and exploitation. 5.1.3 Explain. The value of explanations in general recommender systems is widely recognized [50, 101, 136]. Explanations can increase the system’s perceived transparency, user trust and satisf”
Great Explanations: Opinionated Explanations for Recommendations (2015, methodology): “Early work explored the utility of explanations in collaborative filtering systems with [1] reviewing different models and techniques for explanation based on MovieLens data.”