Is seeing believing?: how recommender system interfaces affect users' opinions

By Dan Cosley, Shyong K. Lam, I. Albert, J. Konstan, John Riedl. International Conference on Human Factors in Computing Systems, 2003

561 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/ea29e57670569977f9d00968d89f74b75eb2a799

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 Management Science and Operations Research

Citations in the corpus

Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols (2013, background): “Although there is no clear explanation, variations in user interfaces (Cosley et al. 2003), data selection (Cremonesi et al.”
The Effectiveness of Personalized Movie Explanations: An Experiment Using Commercial Meta-data (2008, background): “[8] showed that manipulating a rating prediction can alter the user valuation of a movie, causing either an over- or underestimation.”
Distinguishing between Personal Preferences and Social Influence in Online Activity Feeds (2016, background): “Past studies show that people perceive actions by different friends differently based on their relationship with them [4, 18, 31, 43].”
Short-Term Satisfaction and Long-Term Coverage: Understanding How Users Tolerate Algorithmic Exploration (2018, background): “[7] conducted one of the first rating-based studies in recommendation, finding that user satisfaction decreases if a recommender shows incorrect star ratings.”
A Survey of Explanations in Recommender Systems (2007, background): “MovieLens [10, 18] Movies Top-N, Predicted ratings Collaborative-based Rating”
Explaining the user experience of recommender systems (2012, background): “In light of these hypotheses, existing research has established that users are, in several instances, able to observe objective differences in recommendation quality (in terms of the framework: OSA → SSA; for examples, see Ziegler et al. 2005; Cosley et al. 2003).”
Automatic Generation of Natural Language Explanations (2017, background): “rmation about items, since they describe personal usage experience from users. Furthermore, this source plays an important role on the user side, since he/she tend to trust the opinion of other users [5, 13, 22]. arXiv:1707.01561v1 [cs.CL] 4 Jul 2017 DLRS’17, August 2017, Como, Italy Felipe Costa, S”
Collaborative Filtering Recommender Systems (2007, background): “In MovieLens, users were frustrated that they were not able to give ratings as precise as the systems predictions of their ratings – predicted ratings were to the closest half point while user ratings were integers [13].”
Evaluating collaborative filtering recommender systems (2004, result): “We know from recent work by Cosley et al. [2003] that user satisfaction is decreased when a significant level of error is introduced into a recommender system.”
An Evaluation of the Human-Interpretability of Explanation (2019, 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].”
Introduction to Recommender Systems Handbook (2011, background): “Hence, various researchers have tried to understand the factors that lead to the acceptance of a recommendation by a given user [105, 30, 24, 97, 33].”
Evaluating recommender systems from the user’s perspective: survey of the state of the art (2012, background): “…the other hand, perceived accuracy can be enhanced by other aspects, such as the level of domain knowledge of individuals (Hu and Pu 2010; Knijnenburg et al. 2012), contexts and interface design (Xiao and Benbasat 2007; Cosley et al. 2003; Chen and Pu 2010), and interface labels (Ochi et al. 2010).”
Designing and Evaluating Explanations for Recommender Systems (2011, background): “For example, it can be measured as the difference between two ratings: the first being a previous rating, and the second a re-rating for the same item but with an explanation interface [18].”
Collaborative Filtering Recommender Systems (2011, background): “[34] found that predictions influence user rating behavior, but there is interest in using recommender systems to influence user behavior in broader contexts.”
Evaluating Recommender Systems with User Experiments (2015, background): “Users seem to prefer the 5-star and 10half-star scales [15, 23, 28, 42, 106].”
Reinforcement Learning based Recommender Systems: A Survey (2021, background): “Explanation about recommendations made could improve user experience, boost their trust in the system, and help them make better decisions [148, 149, 150].”
The Limits of Popularity-Based Recommendations, and the Role of Social Ties (2016, background): “Will unknown books become hits and vice-versa? How and how much will the habit of the typical reader change? A large body of work has investigated questions of this kind at the individual, user level [8, 25, 26, 35].”