Trust building with explanation interfaces
Open accessThe DOI matches its Crossref record; 23 of the 24 references it cites were found in a registry or an index.
Abstract
Based on our recent work on the development of a trust model for recommender agents and a qualitative survey, we explore the potential of building users' trust with explanation interfaces. We present the major results from the survey, which provided a roadmap identifying the most promising areas for investigating design issues for trust-inducing interfaces. We then describe a set of general principles derived from an in-depth examination of various design dimensions for constructing explanation interfaces, which most contribute to trust formation. We present results of a significant-scale user study, which indicate that the organization-based explanation is highly effective in building users' trust in the recommendation interface, with the benefit of increasing users' intention to return to the agent and save cognitive effort.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Mining association rules between sets of items in large databases
Agrawal, R., Imieliński, T., & Swami, A. (1993) · Proceedings of the 1993 ACM SIGMOD international conference on Management of data · doi:10.1145/170035.170072 · Cited by 14,907 · cited 1×
“The top level of the algorithm can be described in four steps: generate all possible category titles by the Apriori algorithm [ 1 ]; exclude dominated categories; select a few prominent categories not only with longer tradeoff distance with the top candidate but also with higher diversity degree between each other; ra…”
What trust means in e-commerce customer relationships: an interdisciplinary conceptual typology
McKnight, D. H., & Chervany, N. L. (2001) · International Journal of Electronic Commerce · doi:10.1080/10864415.2001.11044235 · Cited by 2,282
Improving recommendation lists through topic diversification
Ziegler, C.-N., McNee, S. M., Konstan, J. A., & Lausen, G. (2005) · Proceedings of the 14th international conference on World Wide Web - WWW '05 · doi:10.1145/1060745.1060754 · Cited by 1,892 · cited 1×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundExplaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731 · cited 1×
“Herlocker et al addressed explanation interfaces for ACF (automated collaborative filtering) systems, and demonstrated that the histogram with grouping of neighbor ratings was the most compelling explanation component among the users that they studied [8].”
BackgroundO'Donovan, J., & Smyth, B. (2005) · Proceedings of the 10th international conference on Intelligent user interfaces · doi:10.1145/1040830.1040870 · Cited by 865 · cited 1×
“They also showed that providing explanations can improve the acceptance of ACF systems and potentially improve users filtering performance.”
BackgroundEmpirical research in on-line trust: a review and critical assessment
Grabner-Kräuter, S., & Kaluscha, E. A. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00043-0 · Cited by 827 · cited 2×
“Studies show that customer trust is positively associated with customers’ intention to transact, purchase a product, and return to the website [7].”
BackgroundThe role of transparency in recommender systems
Sinha, R., & Swearingen, K. (2002) · CHI '02 Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/506443.506619 · Cited by 477 · cited 1×
“Sinha and Swearingen [22] found that users like and feel more confident about recommendations that they perceive as transparent.”
BackgroundThe FindMe approach to assisted browsing
Burke, R. D., Hammond, K. J., & Yound, B. C. (1997) · IEEE Expert · doi:10.1109/64.608186 · Cited by 343 · cited 1×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundExplanation in Recommender Systems
Mcsherry, D. (2005) · Artificial Intelligence Review · doi:10.1007/s10462-005-4612-x · Cited by 182 · cited 1×
“Case-based reasoning recommender systems that can explain their recommendations include ExpertClerk [21], Dynamic critiquing systems [10], FirstCase and TopCase [14, 15].”
BackgroundOn the Role of Diversity in Conversational Recommender Systems
McGinty, L., & Smyth, B. (2007) · Springer eBooks · doi:10.1007/3-540-45006-8_23 · Cited by 158 · cited 1×
“McGinty and Smyth [12] maintain that showing diverse items can reduce the recommendation cycles.”
BackgroundShimazu, H. (2002) · Artificial Intelligence Review · doi:10.1023/a:1020757023711 · Cited by 107 · cited 1×
“Case-based reasoning recommender systems that can explain their recommendations include ExpertClerk [21], Dynamic critiquing systems [10], FirstCase and TopCase [14, 15].”
BackgroundMcSherry, D. (2007) · Springer eBooks · doi:10.1007/3-540-45006-8_24 · Cited by 101 · cited 3×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundExperiments in dynamic critiquing
McCarthy, K., Reilly, J., McGinty, L., & Smyth, B. (2005) · Proceedings of the 10th international conference on Intelligent user interfaces · doi:10.1145/1040830.1040871 · Cited by 86 · cited 3×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundMethodEvaluating example-based search tools
Pu, P. H. Z., & Kumar, P. (2004) · Proceedings of the 5th ACM conference on Electronic commerce · doi:10.1145/988772.988804 · Cited by 70 · cited 2×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundSelf-citationIntegrating tradeoff support in product search tools for e-commerce sites
Pu, P., & Chen, L. (2005) · ACM Conference on Electronic Commerce (EC) · doi:10.1145/1064009.1064038 · Cited by 70 · cited 1×
“According to [18, 20], integrating tradeoff support in a product search tool can improve users’ decision accuracy by up to 57%.”
BackgroundSelf-citationTrust Building in Recommender Agents
(2005) · Proceedings of the 1st International Workshop on Web Personalisation, Recommender Systems and Intelligent User Interfaces · doi:10.5220/0001422901350145 · Cited by 64
Self-citationDesigning example-critiquing interaction
Faltings, B., Pu, P., Torrens, M., & Viappiani, P. (2004) · Proceedings of the 9th international conference on Intelligent user interfaces · doi:10.1145/964442.964449 · Cited by 63 · cited 2×
“Methods have been developed to address users’ potentially unstated preferences [6,17], to cover topic diversity [24], to propose possible tradeoffs a user may be prepared to accept [14], and to allow faster navigation to the target choice by critiquing the proposed items [3,11,20].”
BackgroundSelf-citationOptimal recommendation sets: covering uncertainty over user preferences
Price, B., & Messinger, P. R. (2005) · Cited by 48
Individual Prognosis of Diabetes Long-term Risks: A CBR Approach
Palaudàries, A., Plaza, E., & Armengol, E. (2001) · Methods of Information in Medicine · doi:10.1055/s-0038-1634463 · Cited by 45 · cited 1×
“The importance of explanation interfaces in providing system transparency and thus increasing user acceptance has been well recognized in a number of fields: expert systems [9], medical decision support systems [2], intelligent tutoring systems [23], and data exploration systems [4].”
BackgroundA framework for explaining decision-theoretic advice
Klein, D. A., & Shortliffe, E. H. (1994) · Artificial Intelligence · doi:10.1016/0004-3702(94)90053-1 · Cited by 33 · cited 1×
“The importance of explanation interfaces in providing system transparency and thus increasing user acceptance has been well recognized in a number of fields: expert systems [9], medical decision support systems [2], intelligent tutoring systems [23], and data exploration systems [4].”
BackgroundEffective Interaction Principles for Online Product Search Environments
Pu, P., Faltings, B. V., & Torrens, M. (2004) · doi:10.1109/wi.2004.59 · Cited by 22 · cited 1×
“This is similar to the goal of resolving users’ preference conflict by providing them with partially satisfied solutions [19].”
BackgroundSelf-citationKnowledge communication and CBR.
Sørmo, F., & Aamodt, A. (2002) · Cited by 16
Carenini, G., & Moore, J. C. (1998) · Cited by 11
Research works printed but not linked: 4
- 10.5555/1760422.1760447 · doi:10.5555/1760422.1760447
- 10.5555/1760422.1760448 · doi:10.5555/1760422.1760448
- McSherry , D. Explanation in recommender systems . In Workshop Proceedings of the 7th European Conference on Case-Based Reasoning , 2004 , 125--134. McSherry, D. Explanation in recommender systems. In Workshop Proceedings of the 7th European Conference on Case-Based Reasoning, 2004, 125--134.
- 10.5555/1025132.1026421 · doi:10.5555/1025132.1026421
Cited by
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Evaluating Recommendation Systems
Shani, G., & Gunawardana, A. (2011) · Recommender Systems Handbook · doi:10.1007/978-0-387-85820-3_8 · Cited by 1,325
“whether the system recommendations are reasonable in a user study [22, 12, 11, 47].”
BackgroundA user-centric evaluation framework for recommender systems
Pu, P., Chen, L., & Hu, R. (2011) · Proceedings of the fifth ACM conference on Recommender systems · doi:10.1145/2043932.2043962 · Cited by 850
“A recommender system can convey its inner logic to the user via an explanation interface [3, 8, 22, 23].”
BackgroundInfluentialSelf-citationExplaining the user experience of recommender systems
Knijnenburg, B. P., Willemsen, M. C., Gantner, Z., Soncu, H., & Newell, C. (2012) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9118-4 · Cited by 799
“The results of these studies show that subjective system aspects and experience variables are invaluable in explaining why and how the user experience of recommender systems comes about.”
BackgroundA Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2018) · arXiv · doi:10.48550/arxiv.1811.11839 · Cited by 783
“For instance, Pu and Chen [97] proposed an organizational framework for generating explanations.”
Background
Metadata
- Authors
- Pu, P., & Chen, L.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Venue
- Proceedings of the 11th international conference on Intelligent user interfaces
- Publisher
- ACM
- Published
- 2006-01-29
- Pages
- 93-100
- OpenAlex
- W1995445252
- Semantic Scholar
- 019b7f71d524c31d8ee8c96ae8866014099cc270
- Cited by
- 300
- References
- 24
- Citations by year
- 2026: 6 · 2025: 14 · 2024: 10 · 2023: 13 · 2022: 23 · 2021: 31 · 2020: 24 · 2019: 21 · 2018: 20 · 2017: 7 · 2016: 10 · 2015: 9 · 2014: 7 · 2013: 11 · 2012: 19
- FWCI
- 11.51
- Type
- conference paper
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Locations
- ACM International Conference on Intelligent User Interfaces (IUI) (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- trust building, recommendation agents, trust model, interface design principles, cognitive effort, recommender systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.