Decision Support Systems最新文献

Employees' reviews, feedback, opinions, and experiences shared on crowdsourcing platforms are now widely used by human resource management researchers to analyze a firm's performance, management effectiveness, and culture. The analysis of firm ratings posted by employees on crowdsourcing platforms can not only provide timely feedback and insights into a firm's operations but also inspire managers to make better decisions to improve organizational performance. Based on economic and psychological theories, we conduct a comprehensive and item-by-item analysis of firm ratings on Glassdoor using panel vector autoregression to explore the interactive relationship between crowdsourced firm ratings and Total Factor Productivity (TFP), examining whether this relationship differs across industries. We find a circular interaction between firms' overall ratings and TFP. Additionally, we explore employees' perspectives on compensation and work-life balance. Our results indicate that compensation ratings negatively impact TFP, whereas work-life balance ratings are solely influenced by the lagged self. Finally, we observe that the interaction between Glassdoor firm ratings and TFP varies across industries. Our study suggests that decision makers of different industries should tailor motivation strategies to suit the specific needs of their workforce, allocating resources differently between compensation and work-life balance initiatives.

This paper presents a comprehensive framework for expert-augmented supervised feature selection, addressing pre-processing, in-processing, and post-processing aspects of Explainable Artificial Intelligence (XAI). As part of pre-processing XAI, we introduce the Probabilistic Solution Generator through the Information Fusion (PSGIF) algorithm, leveraging ensemble techniques to enhance the exploration and exploitation capabilities of a Genetic Algorithm (GA). Balancing explainability and prediction accuracy, we formulate two multi-objective optimization models that empower expert(s) to specify a maximum acceptable sacrifice percentage. This approach enhances explainability by reducing the number of selected features and prioritizing those considered more relevant from the domain expert's perspective. This contribution aligns with in-processing XAI, incorporating expert opinions into the feature selection process as a multi-objective problem. Traditional feature selection techniques lack the capability to efficiently search the solution space considering our explainability-focused objective function. To overcome this, we leverage the Genetic Algorithm (GA), a powerful metaheuristic algorithm, optimizing its parameters through Bayesian optimization. For post-processing XAI, we present the Posterior Ensemble Algorithm (PEA), estimating the predictive power of features. PEA enables a nuanced comparison between objective and subjective importance, identifying features as underrated, overrated, or appropriately rated. We evaluate the performance of our proposed GAs on 16 publicly available datasets, focusing on prediction accuracy in a single objective setting. Moreover, we test our multi-objective model on a classification dataset to show the applicability and effectiveness of our framework. Overall, this paper provides a holistic and nuanced approach to explainable feature selection, offering decision-makers a comprehensive understanding of feature importance.

Patient experience surveys have become a key source of evidence for supporting decision-making and continuous quality improvement within healthcare services. To harness free-text feedback collected as part of these surveys for additional insights, text analytics methods are increasingly employed when the data collected is not amenable to traditional qualitative analysis due to volume. However, while text analytics techniques offer good predictive capabilities, they have limited explanatory features often required in formal decision-making contexts, such as programme monitoring or evaluation. To overcome these limitations, this study integrates computational text and predictive modelling as part of a Computational Grounded Theory method to determine the effect of quality gaps in care dimensions and their prioritisation from free-text feedback. The feedback was collected as part of a national survey to support decisions on continuous improvement in Maternity Services in Ireland. Our approach enables (1) operationalising the service quality lexicon in the context of maternity care to explain the effect of quality gaps in care dimensions on overall satisfaction from free-text comments; and (2) extending the service quality lexicon with two organisational and political decision-making concepts: “Salience” and “Valence”, for prioritising perceived quality gaps. These methodological affordances enable the extension of service quality theory to explicitly support the prioritisation of improvement decisions which before now required additional decision frameworks. Results show that tangibles-, process-, and reliability-related care issues have the highest importance in our study context. We also find that hospital contexts partly determine the relative importance of gaps in care dimensions.

This study proposes a real-time Decision Support System (DSS) using machine learning to enhance proactive management of Human–Machine Interaction (HMI) in safety–critical digital control rooms. The DSS provides explainable predictions and recommendations regarding near-future automation usage, customized for the railway control room management, who supervise the operations of traffic controllers (TCs). In this setting, TCs decide on the spot whether to manually or automatically open signals to regulate railway traffic, a critical aspect of ensuring punctuality and safety. This time-setting specific HMI differs across TCs and is not yet supported by a data-driven tool. The proposed DSS includes agreement levels for predictions among different modeling paradigms: linear models, tree-based models, and deep neural networks. SHAP (SHapley Additive exPlanations) values are deployed to assess the agreement level in explainability between these different modeling paradigms. The prescriptions are based on the HMI of well-performing peers. We implement the DSS as proof of concept at the Belgian railway infrastructure company and report end-user feedback on the perception, the operational impact, and the inclusion of agreement levels.

Despite having potentially important implications, there has been little research on the relationship between the public's incidental emotion and the stock market. To that end, we construct a valence-based measure of incidental emotion using BERTweet's sentiment analysis and empirically investigate the association between collective incidental emotion toward the COVID-19 pandemic and the U.S. stock market. We employ multivariate time series autoregressive models to test the relationship between emotion polarity and stock market returns or trading volumes. The results reveal that societal sentiment toward the pandemic has a significant effect on the returns of the Dow Jones Industrial Average and S&P 500. In contrast, the macro-level emotion does not significantly affect the return for NASDAQ 100. The findings also suggest a significant association between incidental emotion and trading volumes. We conduct a battery of sensitivity tests that further support our conjecture. The study underscores the robust role of incidental emotion in investment decision-making, highlighting its significance as a distinctive feature that should be incorporated into financial decision support systems.

Sectorization problems refer to dividing a large set, area or network into smaller parts concerning one or more objectives. A decision support system (DSS) is a relevant tool for solving these problems, improving optimisation procedures, and finding feasible solutions more efficiently. This paper presents a new web-based Decision Support System for Sectorization (D3S). D3S is designed to solve sectorization problems in various areas, such as school and health districting,planning sales territories and maintenance operations zones, or political districting. Due to its generic design, D3S bridges the gap between sectorization problems and a state-of-the-art decision support tool. The paper aims to present the generic and technical attributes of D3S by providing detailed information regarding the problem-solution approach (based on Evolutionary Algorithms), objectives (most common in sectorization), constraints, structure and performance.

The emergence of enterprise social media (ESM) allows enterprises to develop employee improvisation ability for effective decision-making in various emergencies. However, it remains unclear how the use of ESM by employees affects their ability to improvise. Based on the job demands-resources model and Kahn's psychological conditions framework, this study constructs a theoretical model capturing two types of ESM usage—work-related and social-related—and examines their impact on employee improvisation ability. Through the analysis of 307 paired data collected from multi-wave and multi-source questionnaires using Smart-PLS software, the results show that both work-related and social-related ESM use can promote employees' psychological meaningfulness, availability, and safety, thus further stimulating employees' improvisation ability. ESM policies only significantly moderated the effects of work-related ESM use on the three psychological conditions of employees. Moreover, there are significant differences in the intensity of the influence of the two types of ESM uses on the psychological conditions of employees. This study not only enriches and promotes the existing research on ESM usage, psychological conditions, and employee improvisation ability but also helps enterprise management effectively guide employees to use ESM to promote their improvisation ability.

Online games represent a rapidly growing and competitive global market for technology firms. Games are viewed as places where people can temporarily escape from reality. However, it is unclear how game escapism fosters game experience and game use, thus indicating a research gap. This gap keeps decision-makers (i.e., firms and policy-makers) in the dark regarding how game escapism affects gameplay, thus hindering effective decision-making. To fill this gap, uses and gratification theory is applied to build a model for explaining the mechanism underlying the influence of game escapism and telepresence on game experience and game use. We collect 1347 online gamer responses with which to test the model. The results indicate that game escapism improves all game experiences, while only enjoyment and concentration increase game use. Moreover, telepresence strengthens the impact of game escapism on enjoyment, concentration, and fantasy. Our findings offer insights for decision-makers, enabling them to leverage game mechanisms to either provide or negate the impact of game escapism, thus changing game use.

Pretrained language models (PLMs) are frequently employed in Decision Support Systems (DSSs) due to their strong performance. However, recent studies have revealed that these PLMs can exhibit social biases, leading to unfair decisions that harm vulnerable groups. Sensitive information contained in sentences from training data is the primary source of bias. Previously proposed debiasing methods based on contrastive disentanglement have proven highly effective. In these methods, PLMs can disentangle sensitive information from non-sensitive information in sentence embedding, and then adapts non-sensitive information only for downstream tasks. Such approaches hinge on having good sentence embedding as input. However, recent research found that most non-fine-tuned PLMs such as BERT produce poor sentence embedding. Disentangling based on these embedding will lead to unsatisfactory debiasing results. Taking a finer-grained perspective, we propose PCFR (Prompt and Contrastive-based Fair Representation), a novel disentanglement method integrating prompt and contrastive learning to debias PLMs. We employ prompt learning to represent information as sensitive embedding and subsequently apply contrastive learning to contrast these information embedding rather than the sentence embedding. PCFR encourages similarity among different non-sensitive information embedding and dissimilarity between sensitive and non-sensitive information embedding. We mitigate gender and religion biases in two prominent PLMs, namely BERT and GPT-2. To comprehensively assess debiasing efficacy of PCFR, we employ multiple fairness metrics. Experimental results consistently demonstrate the superior performance of PCFR compared to representative baseline methods. Additionally, when applied to specific downstream decision tasks, PCFR not only shows strong de-biasing capability but also significantly preserves task performance.

On accommodation-sharing platform, host self-description influence consumer behavior as an important information. Based on the Perceived Value Theory and the Expectation Confirmation Theory, we developed an analytical framework to investigate the relationship between host description strategies and consumer behavior of room booking and satisfaction. We measured host description strategies (honest description and positive description) using machine learning and rule-based text analysis methods. Then we verified the different effects of two host description strategies on each of consumer behaviors based on a panel dataset from Airbnb. Positive description and honest description have a positive impact on room booking and consumer satisfaction respectively. Room price moderates the relationship between host descriptions and consumer behaviors. A highly positive description strategy can promote bookings for high-priced listings but decrease satisfaction. The honest description strategy has a positive effect on the bookings of low-priced listings. This study contributes to tourism literature and property hosts in practice.