User acceptance of knowledge-based system recommendations: Explanations, arguments, and fit

Giboney, Justin Scott; Brown, Susan A.; Lowry, Paul Benjamin; Nunamaker, Jay F.

doi:10.1016/j.dss.2015.02.005

Cited by 48 publications

(18 citation statements)

References 127 publications

(153 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although explanation and argumentation have long been identified as distinct processes [10], it is also recognized that the distinction is a matter of context, hence they both play a role [4] when it comes to eliciting an answer to a "why" question. This is exactly what is attempted in this paper, as we are providing "possible" explanations, that thus can be turned into arguments.…”

Section: Resultsmentioning

confidence: 99%

Arguments Using Ontological and Causal Knowledge

Besnard

Cordier

Moinard

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

RésuméNous décrivons l'utilisation d'un système logique de raisonnement à partir de données causales et ontologiques dans un cadre argumentatif. Les données consistent en liens causaux ({A1, · · · , An} cause B) et ontologiques (o1 est_un o2). Le système en déduit des liens explicatifs possibles ({A1, · · · , An} explique {B1, · · · , Bm}). Ces liens explicatifs servent ensuite de base à un système argumentatif qui fournit des explications possibles. Un exemple inspiré de la tempête Xynthia, laquelle a provoqué un trop grand nombre de victimes par rapport aux conditions purement météo-rologiques, illustre une utilisation de notre système. AbstractWe investigate an approach to reasoning about causes through argumentation. We consider a causal model for a physical system, and look for arguments about facts. Some arguments are meant to provide explanations of facts whereas some challenge these explanations and so on. At the root of argumentation here, are causal links ({A1, · · · , An} causes B) and ontological links (o1 is_a o2). We present a system that provides a candidate explanation ({A1, · · · , An} explains {B1, · · · , Bm}) by resorting to an underlying causal link substantiated with appropriate ontological links. Argumentation is then at work from these various explaining links. A case study is developed : a severe storm Xynthia that devastated part of France in 2010, with an unaccountably high number of casualties.

show abstract

Section: Resultsmentioning

confidence: 99%

Arguments Using Ontological and Causal Knowledge

Besnard

Cordier

Moinard

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Apart from the solution to a model, this also requires insight in the model and model outcome. Giboney (2015) shows that the representation of a knowledge systems is crucial for user acceptance. In relation to container logistics, existing literature mostly focuses on modelling and finding solutions.…”

Section: Optimisation Models For Decision Problemsmentioning

confidence: 98%

Real-time container transport planning with decision trees based on offline obtained optimal solutions

Riessen

Negenborn

Dekker

2016

Decision Support Systems

View full text Add to dashboard Cite

Hinterland networks for container transportation require planning methods in order to increase efficiency and reliability of the inland road, rail and waterway connections. In this paper we aim to derive real-time decision rules for suitable allocations of containers to inland services by analysing the solution structure of a centralised optimisation method used offline on historic data. The decision tree can be used in a decision support system (DSS) for instantaneously allocating incoming orders to suitable services, without the need for continuous planning updates. Such a DSS is beneficial, as it is easy to implement in the current practice of container transportation. Earlier proposed centralised methods can find the optimal solution for the intermodal inland transportation problem in retrospect, but are not suitable when information becomes gradually available. The main contributions are threefold: firstly, a structured method for creating decision trees from optimal solutions is proposed. Secondly, an innovative method is used for obtaining multiple equivalent optimal solutions to prevent overfitting of the decision tree. And finally, a structured analysis of three error types is presented for assessing the quality of an obtained tree. A case study illustrates the method's purpose by comparing the quality of the resulting plan with alternative methods.

show abstract

“…Past opinion agreement between the consumer and the RA has been found to be an important cue in alleviating the reactance behavior (Gershoff, Mukherjee, & Mukhopadhyay, 2003). Cognitive fit has been shown to influence the degree of recommendation acceptance (Giboney et al, 2015). Consumers have been shown to exhibit less reactance behavior as information overload increases (Aljukhadar, Senecal, & Daoust, 2012).…”

Section: The Reactance Behavior Toward the Ra Advicementioning

confidence: 99%

Consumer self‐construal and trust as determinants of the reactance to a recommender advice

Aljukhadar

Trifts

Sénécal

2017

Psychology and Marketing

View full text Add to dashboard Cite

Commercial recommendation agents (RAs) represent an important type of the decision support systems (DSSs) that are widely used by online retailers and firms. To date, little is known about the factors that shape the user's decision making and reactance toward the recommendations of these agents. Building on theories from psychology and information systems domains, this research proposes that a user's self‐construal and trust are two relevant factors that interact to shape the behavior toward the RA advice. Two studies, the first conducted using potential online customers and the second conducted at a behavioral laboratory, provided support to this proposition. The first study considered RA trust and showed that activating the interdependent self leads users with low (high) trust to exhibit high reactance behavior toward the RA advice. The second study variated trust using trust cues and corroborated the latter finding, while showing no important impact for the psychological reactance trait. As expected, in both studies the reactance behavior of independent users was not affected by trust. These results contribute by underscoring that social interdependence extends to RAs because the role of trust becomes salient when the interdependent self is activated for a user.

show abstract

User acceptance of knowledge-based system recommendations: Explanations, arguments, and fit

Cited by 48 publications

References 127 publications

Arguments Using Ontological and Causal Knowledge

Arguments Using Ontological and Causal Knowledge

Real-time container transport planning with decision trees based on offline obtained optimal solutions

Consumer self‐construal and trust as determinants of the reactance to a recommender advice

Contact Info

Product

Resources

About