Search results

This study aims to provide a method for classifying travellers’ requirements to help hoteliers understand travellers’ requirements and improve hotel services. Specifically, this study develops a strength-frequency Kano (SF-Kano) model to classify the requirements expressed by travellers in online reviews.

The strength and frequency of travellers’ requirements are determined through sentiment and statistical analyses of the 13,217 crawled online reviews. The proposed method considering the interaction between strength and frequency is proposed to classify the different travellers’ requirements.

This study identifies 13 travellers’ requirements by mining online reviews. According to the results of the improved Kano model, the six travellers’ requirements belong to one-dimensional requirements; two travellers’ requirements belong to must-be requirements; three travellers’ requirements belong to attractive requirements; two travellers’ requirements belong to indifferent requirements.

Results of this research can guide hoteliers to address hotel service improvement strategies according to the types of travellers’ requirements. This study can also expand the analysis scope of hotel online reviews and provide a reference for hoteliers to understand travellers’ requirements.

By mining online reviews, this study proposes an SF-Kano model to classify travellers’ requirements by considering both the strength and frequency of requirements. This study uses the optimisation model to determine the classification thresholds. This process maximises travellers’ satisfaction at the lowest cost. The classification results of travellers’ requirements can help hoteliers gain a deeper understanding of travellers’ requirements and prioritise service improvements.

Online medical repositories provide a platform for users to share information and dynamically access abundant electronic health data. It is important to determine whether case report information can assist the general public in appropriately managing their diseases. Therefore, this paper aims to introduce a novel deep learning-based method that allows non-professionals to make inquiries using ordinary vocabulary, retrieving the most relevant case reports for accurate and effective health information.

The dataset of case reports was collected from both the patient-generated research network and the digital medical journal repository. To enhance the accuracy of obtaining relevant case reports, the authors propose a retrieval approach that combines BERT and BiLSTM methods. The authors identified representative health-related case reports and analyzed the retrieval performance, as well as user judgments.

This study aims to provide the necessary functionalities to deliver relevant health case reports based on input from ordinary terms. The proposed framework includes features for health management, user feedback acquisition and ranking by weights to obtain the most pertinent case reports.

This study contributes to health information systems by analyzing patients' experiences and treatments with the case report retrieval model. The results of this study can provide immense benefit to the general public who intend to find treatment decisions and experiences from relevant case reports.

Extant research shows mixed results on the impact of expressed negative emotions on donations in online charitable crowdfunding. This study solves the puzzle by examining how different types of negative emotions (i.e. sadness, anxiety and fear) expressed in crowdfunding project descriptions affect donations.

Data on 15,653 projects across four categories (medical assistance, education assistance, disaster assistance and poverty assistance) from September 2013 to May 2019 come from a leading online crowdfunding platform in China. Text analysis and regression models serve to test the hypotheses.

In the medical assistance category, the expression of sadness has an inverted U-shaped effect on donations, while the expression of anxiety has a negative effect. An appropriate number of sadness words is helpful but should not exceed five times. In the education assistance and disaster assistance categories, the expression of sadness has a positive effect on donations, but disclosure of anxiety and fear has no influence on donations. Expressions of sadness, anxiety and fear have no impact on donations in the poverty assistance category.

This work has important implications for fundraisers on how to regulate the fundraisers' expressions of negative emotions in a project's description to attract donations. These insights are also relevant for online crowdfunding platforms.

Online crowdfunding research often studies negative emotions as a whole and does not differentiate project types. The current work contributes by empirically testing the impact of three types of negative emotions on donations across four major online crowdfunding categories.