Trust building with explanation interfaces

By Pearl Huan Z. Pu, Li Chen. International Conference on Intelligent User Interfaces, 2006

336 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Systems and Management

View Paper: https://www.semanticscholar.org/paper/019b7f71d524c31d8ee8c96ae8866014099cc270

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 Information Systems and Management

Citations in the corpus

Interactive and interpretable machine learning models for human machine collaboration (2015, background): “Communication with the user is essential to a successful interactive system — it improves transparency, which has been identified as a major factor in establishing user trust in adaptive agents [111, 58] and improving system acceptance [68, 127].”
Evaluating Recommendation Systems (2011, background): “whether the system recommendations are reasonable in a user study [22, 12, 11, 47].”
How should I explain? A comparison of different explanation types for recommender systems (2014, background): “In the existing literature on recommender system explanations, authors often limit their analysis to some specific explanation goals [Herlocker et al., 2000; Bilgic and Mooney, 2005; Pu and Chen, 2006, 2007; Symeonidis et al., 2009] or explanation types [Vig et al., 2009; Gedikli et al., 2011].”
Toward harnessing user feedback for machine learning (2007, background): “For example, showing contrasting features in recommendations can play a role in user trust [11, 23].”
iBCM: Interactive Bayesian Case Model Empowering Humans via Intuitive Interaction (2015, background): “Communication with the user is essential to a successful interactive system — it improves transparency, which has been identified as a major factor in establishing user trust in adaptive agents [28, 13] and improving system acceptance [17, 30].”
Evaluating the effectiveness of explanations for recommender systems (2012, background): “Effective explanations could also serve the purpose of introducing a new domain, or the range of products, to a novice user, thereby helping them to understand the full range of options (Felfernig et al. 2007; Pu and Chen 2006).”
Explaining Recommendations: Design and Evaluation (2015, background): “(Digital cameras, notebooks computers) [59] X”
A Survey on Conversational Recommender Systems (2020, background): “In the context of critiquing-based systems, [105] examined the trust-building nature of explanations.”
Recommendation Systems in Software Engineering (2014, methodology): “[34], Walker and Holmes [36], and Avazpour et al.”
Recommendation Diversification Using Explanations (2009, background): “To address these two issues, we propose to formalize a notion of diversity based on recommendation explanations [2], [8].”
Explainable Entity-based Recommendations with Knowledge Graphs (2017, background): “ke a purchase (persuasiveness) or whether they help the user make decision more rapidly (e˝ciency). In general, providing an explanation has been shown to build user’s trust in the recommender system [9]. The focus of this paper is a system to generate explanations for Knowledge Graph (KG) -based re”
A Survey of Explanations in Recommender Systems (2007, background): “Effective explanations could also serve the purpose of introducing a new domain, or the range of products, to a novice user, thereby helping them to understand the full range of options [14, 28].”
A user-centric evaluation framework for recommender systems (2011, background): “A recommender system can convey its inner logic to the user via an explanation interface [3, 8, 22, 23].”
Visualization of Explanations in Recommender Systems (2014, methodology): “When using text as a means to represent explanations, users would prefer short sentences for low-risk products while for high-risk products, users would prefer the use of more detailed sentences [5].”