Logical rules characterization of online consumer trust

Abstract

In this study, we address the discriminant factors of website trust. We specifically build sets of propositional rules that can be used to predict the level of trustworthiness of a site. Focusing on initial trust, a survey was designed to assess site characteristics observed by the respondent and his/her perceptions around appearance, reputation, fulfillment, and security. By exploring data, we look for the most favorable rules classifiers among decision trees as well as classical and dominance-based rough sets. A heuristic aiming to derive simpler classifiers is also proposed. The experimental setup considers diverse groups of attributes (predictors) for the extraction of rules. Results obtained are compared by taking into account predictive ability and parsimony of rules' sets. Finally, the selected sets help bring light on how consumers process site information and suggest specific recommendations for e-commerce vendors.

A cognitive approach to the decision to trust or distrust phishing emails

“…They showed that negative‐valent perceptions were more useful in predicting low levels of trust than positive‐valent perceptions in predicting high trust. In their empirical study, characteristics usually considered important, such as errors, design, and support, did not seem to influence the decision to trust, even if “they may contribute to create a certain context” (Andrade et al., 2021, p. 21).…”

“…Andrade et al. (2021) recently proposed using rough sets and decision trees to predict levels of trust in websites. They showed that negative‐valent perceptions were more useful in predicting low levels of trust than positive‐valent perceptions in predicting high trust.…”

“…For Internet or website trust, some authors have proposed theoretical models or empirical assessments that aim at identifying the factors contributing most to trust (Shankar et al, 2002;Das and Teng, 2004). Andrade et al (2021) recently proposed using rough sets and decision trees to predict levels of trust in websites. They showed that negative-valent perceptions were more useful in predicting low levels of trust than positive-valent perceptions in predicting high trust.…”

“…The decision to trust may be viewed as a decision-making problem influenced by mind and cognition (Jiao et al, 2020). Some authors, such as Hurley (2006) have discussed "practical ways of managing trust," while others, such as Andrade et al (2021) have taken the view that during the decision-making processes, trust is largely influenced by information found on the Internet. Such information may be "limited and distorted" leading to biases (Peláez et al, 2020), and such biases may be exploited by attackers giving legitimate users "disruptive cues" (Yeow and Chua, 2020) to win their trust.…”