Search results

There is a need to predict whether the consumers liked the stay in the hotel rooms or not, and to remove the aspects the customers did not like. Many customers leave a review after staying in the hotel. These reviews are mostly given on the website used to book the hotel. These reviews can be considered as a valuable data, which can be analyzed to provide better services in the hotels. The purpose of this study is to use machine learning techniques for analyzing the given data to determine different sentiment polarities of the consumers.

Reviews given by hotel customers on the Tripadvisor website, which were made available publicly by Kaggle. Out of 10,000 reviews in the data, a sample of 3,000 negative polarity reviews (customers with bad experiences) in the hotel and 3,000 positive polarity reviews (customers with good experiences) in the hotel is taken to prepare data set. The two-stage feature selection was applied, which first involved greedy selection method and then wrapper method to generate 37 most relevant features. An improved stacked decision tree (ISD) classifier) is built, which is further compared with state-of-the-art machine learning algorithms. All the tests are done using R-Studio.

The results showed that the new model was satisfactory overall with 80.77% accuracy after doing in-depth study with 50–50 split, 80.74% accuracy for 66–34 split and 80.25% accuracy for 80–20 split, when predicting the nature of the customers’ experience in the hotel, i.e. whether they are positive or negative.

The implication of this research is to provide a showcase of how we can predict the polarity of potentially popular reviews. This helps the authors’ perspective to help the hotel industries to take corrective measures for the betterment of business and to promote useful positive reviews. This study also has some limitations like only English reviews are considered. This study was restricted to the data from trip-adviser website; however, a new data may be generated to test the credibility of the model. Only aspect-based sentiment classification is considered in this study.

Stacking machine learning techniques have been proposed. At first, state-of-the-art classifiers are tested on the given data, and then, three best performing classifiers (decision tree C5.0, random forest and support vector machine) are taken to build stack and to create ISD classifier.

The primary aim of this paper is to concurrently use the data types to enhance econometric analysis in the housing market in developing countries, particularly Namibia.

Scholarly discussions on econometric analysis in the housing market in sub-Saharan Africa suggest that the inadequacy of time series data has impeded studies of such nature in the region. Hence, this paper aims to comparatively analyse the impact of economic fundamentals on house prices in Namibia using real and interpolated data from 1990 to 2021 supported by the ARDL model.

It was discovered that in all the three types of data house prices were affected by fundamentals except real GDP in the long term. It was also noted that there were not much significant variations between the real data and the interpolated data frequencies. However, the results of the annual data and the semi-annual interpolated data were more analogously comparable to the quarterly interpolated data

It is suggested that the adoption of interpolated data frequency type should be based on the statistical significance of the result. In addition, the need to monitor the nexus of the housing market and fundamentals is necessary for stable and sustainable housing market for enhanced policy direction and prudent property investment decision.

The study pioneer to concurrently use the data types to enhance econometric analysis in the housing market in developing countries.

With the advent of the second wave of COVID-19 pandemic, there is a need to analyse the scenario of panic buying (PB) behaviour of the customers which was evident in the first wave. This paper aims to examine the PB scenario as well as the moderating effect of past buying experience (PBE) on PB in the second wave of the COVID-19 pandemic.

This study is based on the theories of stimulus–organism–response model and the competitive arousal model. Based on these theories, this paper investigates how panic situation created by external stimuli such as perceived scarcity (PS), perceived risk (PR), news in media (NM) and social learning affect the perceived arousal (PA) among people which in turn influence the PB behaviour of customers. Data were collected from 253 customers from different parts of India. Structural equation modelling is used to analyse the moderating effect of PBE on the PB in the second wave of COVID-19 pandemic.

The results indicate that the PS, PR and NM continue to be strong predictors of a buyer for PA. However, the PB is not reinforced by the moderation effect of PBE.

This paper investigates the consumers’ PB behaviours in the wake of third wave of COVID-19 pandemic which add to the existing literature of COVID-19 pandemic. Moreover, this study also examines how previous buying experience can moderate the PB behaviour of the customers in subsequent phases of COVID-19 pandemic. This supports the potential effectiveness of self-regulation as an intervention strategy for reducing PB behaviours during the COVID-19 pandemic.

This study emphasises the impact of external stimuli like PS, PR and media coverage on PB behaviour, marketers and policymakers should manage to avoid triggers. Although PBE may not moderate PB during a pandemic, it can play a significant role in future buying behaviour. Anticipating potential triggers and designing effective marketing strategies that cater to customers' needs can help manage PB behaviour during disasters or pandemics. In addition, promoting conscious consumption awareness and self-regulation practices among customers can help manage PB behaviour, benefit the environment and society and make customers more responsible buyers.

To the best of the authors’ knowledge, this study examines the PB behaviour of customers during the second wave of COVID-19 pandemic for the first time. This study also investigates the moderating effect of PBE on the PB behaviour of customers during a pandemic which is new and significant that extends the literature on PB behaviour during a pandemic.

Nowadays, a prominent research area is the development of competitive advantages in companies, due to their environmental commitment and orientation. Based on resource-based view (RBV) and institutional theory (InT), this paper aims to investigate the influence of internal and external orientation on businesses' sustainable performance while considering the effect of sustainable supply chain management (SSCM) practices.

Data from 351 manufacturing companies in the Kingdom of Saudi Arabia have been collected and analysed through structural equation modelling (SEM) using the partial least squares (PLS) method.

The results indicated that both internal and external environmental orientation have important effects on SSCM practices, which in turn have a considerable beneficial effect on environmental, social and economic performance.

Although SSCM is constantly gaining ground in the literature, most SSCM research and models examine its effects, antecedents or motivation, mainly adopting a qualitative approach. Research on the topic adopting a large-scale empirical approach is still limited. In this context, this study contributes to the SSCM management literature by exploring the role of environmental orientation in facilitating the adoption of SSCM practices and improving companies' performance.

Agile principles have been widely used in software development team practice since the creation of the Agile Manifesto. Studies have examined variables related to agile principles without systematically considering the relationships among key team, agile methodology, and process variables underlying the agile principles and how these variables jointly influence the achievement of software development agility. In this study, the authors tested a team/methodology–process–agility model that links team variables (team autonomy and team competence) and methodological variable (iterative development) to process variables (communication and collaborative decision-making), which are in turn linked to software development agility (ability to sense, respond and learn).

Survey data from one hundred and sixty software development professionals were analyzed using structural equation modeling methods.

The results support the team/methodology–process–agility model. Process variables (communication and collaborative decision-making) mediated the effects of team (autonomy and competence) and methodological (iterative development) variables on software development agility. In addition, team, methodology and process variables had different effects on the three dimensions of software development agility.

The results contribute to the literature on organizational IT management by establishing a team/methodology–process–agility model that can serve as a basis for developing a core theoretical foundation underlying agile principles and practices. The results also have practical implications for organizations in understanding and managing holistically the different roles that agile methodological, team and process factors play in achieving software development agility.

This paper aims to discuss innovations in the training and development practices of companies and delineate a new approach to training and development in the context of the hybrid workplace using the ADDIE and Kirkpatrick training models.

This paper discusses innovations in training and development in modern times and builds on the instructional training design approach or the ADDIE Model and the Kirkpatrick Model of training evaluation.

The paper presents new approaches to training and development in the context of the hybrid work model applying the ADDIE Model and the Kirkpatrick Model. These new approaches are both necessitated and also made possible due to the technological advancements of modern times.

With the rapid transition of companies to the hybrid model of work in recent times, several human resource management practices need to be transformed to suit the requirements of the new work model. Training and development is one function that needs to change in the hybrid work model to ensure its effectiveness. This paper analyses innovations in the training and development practices of companies and discusses new approaches while applying existing training models, the ADDIE and Kirkpatrick Models, to adapt to the changes associated with the hybrid work model.