Decision Support Systems

• MERLIN: A tool to compute global model contrast explanations of any classifier.
• Explanations are provided through Natural Language.
• Evaluation on benchmark datasets.
• Implementation of the method as a pip-python tool publicly ...

Explaining how two machine learning classification models differ in their behaviour is gaining significance in eXplainable AI, given the increasing diffusion of learning-based decision support systems. Human decision-makers deal with more than ...

This study proposes a novel research framework to examine the effect of digital CSR communications on financial performance while incorporating deep learning techniques to identify firms' CSR communications on social media. Particularly, this ...

• Novel research framework to examine the effect of digital CSR communications on financial performance.
• Using deep learning techniques to identify firms’ CSR communications on social media.
• Use of financial and secondary data of ...

Although online health communities (OHCs) serve as a convenient and important platform for patients to access professional services, limited knowledge is available on patients' adoption behavior of physician services in OHCs across different ...

• A model was proposed to explore patients' adoption behavior of physician services in OHCs.
• Patients' adoption behavior of physician services was divided into first adoption and post-adoption.
• eWOM works positively in both the first ...

The development of the Internet has significantly reduced the threshold of entrepreneurship, and the number of new companies is increasing. Following the rise of crowdfunding platforms, many startup companies have begun to use such platforms to ...

• Many startup companies have begun to use crowdfunding platforms to raise funds.
• We propose an endorsing investor discovery mechanism that could be applied to equity crowdfunding for startup support.
• We use the investor's community ...

Health advice from doctors on the Internet may help patients make preliminary medical decisions. Patients may not adopt doctors' advice because of the problems with how the advice is structured rather than the advice quality. We apply the ...

• Our study highlights the importance of structuring the sequence of advice components based on the specific context.
• Our study highlights the distinctive roles played by problem analysis and suggested actions in affecting advice ...

This paper develops an explainable artificial intelligence (AI) approach to measuring service quality in voice-based service encounters. Drawing from the psychology and computer science literature, we construct features of a customer's emotion ...

• This study develops a new customer-emotion-based method to measure service quality in call centers, which is superior to two benchmarks for assessing service quality.
• The paper uses explainable AI approach unveils what dynamic ...

Estimating the effect of mixed treatments is a crucial problem in causal inference. While previous studies have focused on econometric analysis, few have positioned the mixed treatment problem within the realm of causal machine learning, ...

• A novel uplift modeling approach is proposed to estimate the effects of mixed treatments.
• The approach performs treatment attribution to untangle treatment confoundedness through Shapley value.
• The approach provides robust ...

Express delivery, enabled by automated warehouse systems, offers a competitive advantage to e-commerce retailers by shortening order shipping time. It is a common strategy used to attract customers to maintain customer loyalty and improve ...

• Express delivery promises heighten customer expectations, subsequently impacting their post-purchase satisfaction and rating behavior.
• Orders with express delivery promises tend to receive fewer and lower ratings, compared to non-...

Online reviews play a crucial role in comprehending user rating behavior and improving personalized recommendations in e-commerce. However, existing review-based recommendation systems ignore the influence of theory-driven and context ...

• A cognitive process-driven DL recommendation model is proposed by integrating textual review and context information.
• The framework of the proposed model mimics the human brain's cognitive process for predicting user rating behavior.

Of the many factors affecting supply chain resiliency, visibility can have a profound effect on critical decisions for improving the readiness, response, and recovery from supply chain disruptions. The visibility of tier-1 ...

• This is a clean version of the final paper and thus, Word's track changes tool was not used to highlight the changes.
• We confirm that this version was prepared following the “Guide for Authors” guideline of DSS.
• It includes all the ...

• We rationalize firms' (downward) service line extension via congestion effect.
• We derive firms' intermediate-disclosure strategy under low-end encroachment.
• For policymakers, inter- rather than intra-firm service competition is ...

Firms frequently introduce a new quality differentiated service to extend or encroach on the original market, such as expert consultations, airlines, and catering, thereby ameliorating the congestion effect incurred by noisy environments and ...

The rapid rise of many e-commerce platforms for individual consumers has generated a large amount of text-based data, and thus researchers have begun to experiment with text mining techniques to extract information from the large amount of ...

• AI framework to explain the impact of product descriptions on sales forecasting.
• Data from nearly 200,000 sales records obtained from a cross-border e-commerce firm.
• Product description influences sales forecasting, and 44% of the ...

Investor sentiment based on social media Word-of-Mouth (WoM) has been shown to be predictive of stock returns under normal market conditions. However, the COVID-19 pandemic has brought unprecedented impact and uncertainty to the stock market. In ...

• Examine the stock market using social media word of mouth (WoM) before, during, and after a major socio-economic disruption.
• Aggregate social media (SM) WoM predicts financial markets under normal conditions, but not during/after the ...

Social identification theory (SIT) posits that social identification predicts individuals' commitment and loyalty. However, SIT has not clarified the mechanism underlying the impact of social identification on engagement, particularly in terms of ...

• We proposed external articulation and internal stabilization as novel components of social identification theory.
• The two components explain how social identification affects gamers' further engagement.
• External articulation has ...