Search results

Traditional classification algorithms always have an incorrect prediction. As the misclassification rate increases, the usefulness of the learning model decreases. This paper presents the development of a wisdom framework that reduces the error rate to less than 3% without human intervention.

The proposed WisdomModel consists of four stages: build a classifier, isolate the misclassified instances, construct an automated knowledge base for the misclassified instances and rectify incorrect prediction. This approach will identify misclassified instances by comparing them against the knowledge base. If an instance is close to a rule in the knowledge base by a certain threshold, then this instance is considered misclassified.

The authors have evaluated the WisdomModel using different measures such as accuracy, recall, precision, f-measure, receiver operating characteristics (ROC) curve, area under the curve (AUC) and error rate with various data sets to prove its ability to generalize without human involvement. The results of the proposed model minimize the number of misclassified instances by at least 70% and increase the accuracy of the model minimally by 7%.

This research focuses on defining wisdom in practical applications. Despite of the development in information system, there is still no framework or algorithm that can be used to extract wisdom from data. This research will build a general wisdom framework that can be used in any domain to reach wisdom.

The purpose of the paper is to predict mapping of areas vulnerable to flooding in the Ourika watershed in the High Atlas of Morocco with the aim of providing a useful tool capable of helping in the mitigation and management of floods in the associated region, as well as Morocco as a whole.

Four machine learning (ML) algorithms including k-nearest neighbors (KNN), artificial neural network, random forest (RF) and x-gradient boost (XGB) are adopted for modeling. Additionally, 16 predictors divided into categorical and numerical variables are used as inputs for modeling.

The results showed that RF and XGB were the best performing algorithms, with AUC scores of 99.1 and 99.2%, respectively. Conversely, KNN had the lowest predictive power, scoring 94.4%. Overall, the algorithms predicted that over 60% of the watershed was in the very low flood risk class, while the high flood risk class accounted for less than 15% of the area.

There are limited, if not non-existent studies on modeling using AI tools including ML in the region in predictive modeling of flooding, making this study intriguing.

Due to the unknown location, size and timing of disasters, the rapid response required by humanitarian operations (HO) faces high uncertainty and limited time to raise funds. These harsh realities make HO challenging. This study aims to systematically capture the complex dynamic relationships between operations in humanitarian settings.

To achieve this goal, the authors undertook a systematic review of the extant academic literature linking HO to system dynamics (SD) simulation.

The research reviews 88 papers to propose a taxonomy of different topics covered in the literature; a framework represented through a causal loop diagram (CLD) to summarise the taxonomy, offering a view of operational activities and their linkages before and after disasters; and a research agenda for future research avenues.

As the authors provide an adequate representation of reality, the findings can help decision makers understand the problems faced in HO and make more effective decisions.

While other reviews on the application of SD in HO have focused on specific subjects, the current research presents a broad view, summarising the main results of a comprehensive CLD.

The COVID-19 pandemic, which appeared in China in late 2019, has affected the world psychologically, socially and economically in 2020. Tourism is one of the areas where the effects of COVID-19 have been felt most clearly. The study aims to determine the effect of negative problem orientation (NPO) and perceived risk related to the COVID-19 pandemic on travel and destination visit intention.

This study employed a convenience and probabilistic sampling method for collecting data from 531 respondents using an online questionnaire. Partial least square structural equation modeling (PLS-SEM) was used for testing research model.

According to the findings, NPO and perceived risk related to the pandemic were found to have direct and indirect effects on the travel behavior of tourists. The results of this research provide theoretical and practical implications for hospitality and travel businesses on topics such as the psychological effects of the pandemic and the travel behaviors of tourists.

It is estimated that the pandemic will also affect tourist behavior due to its effects on human psychology. For this reason, a study conducted in the context of tourist behavior theories is expected to contribute to the literature, managers and future of the tourism.

Data represents a critical resource that enables construction companies’ success; thus, its management is very important. The purpose of this study is to assess the benefits of construction data risks management (DRM) in the construction industry (CI).

This study adopted a quantitative method and collected data from various South African construction professionals with the aid of an e-questionnaire. These professionals involve electrical engineers, quantity surveyors, architects and mechanical, as well as civil engineers involved under a firm, or organisation within the province of Gauteng, South Africa. Standard deviation, mean item score, non-parametric Kruskal–Wallis H test and exploratory factor analysis were used to analyse the retrieved data.

The findings revealed that DRM enhances project and company data availability, promotes confidentiality and enhances integrity, which are the primary benefits of DRM that enable the success of project delivery.

The research was carried out only in the province of Gauteng due to COVID-19 travel limitations.

The construction companies will have their data permanently in their possession and no interruption will be seen due to data unavailability, which, in turn, will allow long-term and overall pleasant project outcomes.

This study seeks to address the benefits of DRM in the CI to give additional knowledge on risk management within the built environment to promote success in every project.

This study aims to help understand individual donors’ preferences over different designs of humanitarian–business partnerships in managing humanitarian operations and to help understand if donors’ preferences align with their actual donation behavior.

Choice-based conjoint analysis was used to understand donation preferences for partnership designs, and a donation experiment was performed using real money to understand the alignment of donors’ preferences with actual donation behavior.

The results show that partnering with the business sector can be a valuable asset for humanitarian organizations in attracting individual donors if these partnerships are managed well in terms of partnership strategy, partnership history and partnership report and disclosure. In particular, the study finds that the donation of services and products from businesses corporations to humanitarian organizations are preferable to individual donors, rather than cash. Furthermore, donors’ preferences are not necessarily aligned with actual donation behavior.

The results highlight the importance of presenting objective data on projects to individual donors. The results also show that donors value the provision of services and products by business corporations to humanitarian operations.

Partnerships between humanitarian organizations and business corporations are important for the success of humanitarian operations. However, little is known about which partnership designs are most preferable to individual donors and have the biggest chance of being supported financially.

This study aims to examine how the initial ambiguity of COVID-19 contributed to tourists' intentions for visiting a once-viral outbreak site in the future.

The present study (N = 248) used partial least-squares structural equation modeling (PLS-SEM) to examine whether perceptions of ambiguity and mismanagement of COVID-19 are indirectly related to intentions to travel to Wuhan in a post-pandemic world through perceptions of risk and tourism value. Further, whether the model effects differed as a function of individual safety orientation was examined.

Perceptions of COVID-19 risk and tourism value serially mediated the effects of perceived COVID-19 ambiguity on post-pandemic travel intentions. Safety orientation did not moderate any paths. Perceived risk was a negative direct correlate of post-pandemic travel intentions.

The current study's strength is rooted in its specific targeting of post-pandemic travel intentions to Wuhan—the first city to experience a widescale outbreak of COVID-19 and subsequent international stigma—compared to general travel inclinations.

This paper aims to conduct an interdisciplinary systematic literature review (SLR) of fake news research and to advance the socio-technical understanding of digital information practices and platforms in business and management studies.

The paper applies a focused, SLR method to analyze articles on fake news in business and management journals from 2010 to 2020.

The paper analyzes the definition, theoretical frameworks, methods and research gaps of fake news in the business and management domains. It also identifies some promising research opportunities for future scholars.

The paper offers practical implications for various stakeholders who are affected by or involved in fake news dissemination, such as brands, consumers and policymakers. It provides recommendations to cope with the challenges and risks of fake news.

The paper discusses the social consequences and future threats of fake news, especially in relation to social networking and social media. It calls for more awareness and responsibility from online communities to prevent and combat fake news.

The paper contributes to the literature on information management by showing the importance and consequences of fake news sharing for societies. It is among the frontier systematic reviews in the field that covers studies from different disciplines and focuses on business and management studies.

When the probability of each model is known, a natural idea is to select the most probable model. However, in many practical situations, the exact values of these probabilities are not known; only the intervals that contain these values are known. In such situations, a natural idea is to select some probabilities from these intervals and to select a model with the largest selected probabilities. The purpose of this study is to decide how to most adequately select these probabilities.

It is desirable to have a probability-selection method that preserves independence. If, according to the probability intervals, the two events were independent, then the selection of probabilities within the intervals should preserve this independence.

The paper describes all techniques for decision making under interval uncertainty about probabilities that are consistent with independence. It is proved that these techniques form a 1-parametric family, a family that has already been successfully used in such decision problems.

This study provides a theoretical explanation of an empirically successful technique for decision-making under interval uncertainty about probabilities. This explanation is based on the natural idea that the method for selecting probabilities from the corresponding intervals should preserve independence.