Search results

This paper aims to classify tourist accommodation using data from Booking.com and TripAdvisor and analyse the extent to which the different segments identified differ in terms of being adults-only.

In total, 1,535 properties located in nine Spanish sun and beach destinations were examined using a latent class cluster analysis (LCCA). The bias-adjusted three-step approach was used to investigate the differences between belonging to adults-only accommodation or not among the identified clusters.

Results show that adults-only accommodation tends to belong to the cluster with higher online ratings. In small Spanish islands, adults-only hotels account for a large share (more than 25%) of hotels.

It was not possible to analyse whether the higher rating was due to the accommodation being better or due to the tourists being more satisfied with their stay.

In urban destinations, the model is not widely used. However, in coastal destinations, it is becoming more than a novelty or a new trend.

In small Spanish islands, people traveling with children are becoming a minority. Families may feel discriminated against and express dissatisfaction with this situation in the future.

This study covers the gap in the academic literature on this growing hotel segment.

This study aimed to identify subgroups of esports players based on their gaming behavior patterns across game genres and compare self-efficacy, social efficacy, loneliness and three dimensions of quality of life between these subgroups.

324 participants were recruited from prolific academic to complete an online survey. We employed latent profile analysis (LPA) to identify subgroups of esports players based on their behavioral patterns across genres. Additionally, a one-way multivariate analysis of covariance (MANCOVA) was conducted to test the association between cluster memberships and development and well-being outcomes, controlling for age and gender as covariates.

LPA analysis identified five clusters (two single-genre gamer groups, two multigenre gamer groups and one all-genre gamer group). Univariate analyses indicated the significant effect of the clusters on social efficacy, psychological health and social health. Pairwise comparisons highlighted the salience of the physical enactment-plus-sport simulation genre group in these outcomes.

This study contributes to the understanding of the development and well-being benefits experienced by various esports consumers, as well as the role of specific gameplay in facilitating targeted outcomes among these consumer groups.

Although risk culture is a key determinant for an effective risk management, identifying the risk culture of a firm can be challenging due to the abstract concept of culture. This paper proposes a novel approach that uses unsupervised machine learning techniques to identify significant features needed to assess and differentiate between different forms of risk culture.

To convert the unstructured text in our sample of banks' 10K reports into structured data, a two-dimensional dictionary for text mining is built to capture risk culture characteristics and the bank's attitude towards the risk culture characteristics. A principal component analysis (PCA) reduction technique is applied to extract the significant features that define risk culture, before using a K-means unsupervised learning to cluster the reports into distinct risk culture groups.

The PCA identifies uncertainty, litigious and constraining sentiments among risk culture features to be significant in defining the risk culture of banks. Cluster analysis on the PCA factors proposes three distinct risk culture clusters: good, fair and poor. Consistent with regulatory expectations, a good or fair risk culture in banks is characterized by high profitability ratios, bank stability, lower default risk and good governance.

The relationship between culture and risk management can be difficult to study given that it is hard to measure culture from traditional data sources that are messy and diverse. This study offers a better understanding of risk culture using an unsupervised machine learning approach.

This study aims to progress scholarly understanding of the staycation phenomenon by examining customer segments and documenting local customers’ attribute preferences.

A stated choice experiment is used to examine customer preferences for staycation package attributes. Latent class discrete choice modeling is deployed to classify customers into market segments based on their preferences. The profile of each segment is enhanced by documenting customer characteristics and consumption styles.

Six prominent market segments are identified using a combination of sociodemographics, consumption styles and staycation attribute preferences. The findings draw on consumer experiences during the COVID-19 pandemic to generate theoretical insights into preferred staycation packages. Empirically, the estimation results from the research framework and choice experimental method demonstrate that staycation market segments exhibit distinct preference structures.

Practitioners and policymakers can incorporate the findings of this study in designing and/or assessing staycation packages. This can ensure differentiated products for defined segments that resonate within local communities through positive word of mouth, thus offering prospective spillovers to visiting friends and relatives.

This is a pioneering study on preference heterogeneity from the customer perspective, with a focus on staycation markets. The findings can encourage and assist hotel sector leaders to capitalize on local market developments to achieve a more resilient hospitality business model.

Communities representing groups of agents with similar interests or functions are one of the essential features of complex networks. Finding communities in real-world networks is critical for analyzing complex systems in various areas ranging from collaborative information to political systems. Given the different characteristics of networks and the capability of community detection in handling a plethora of societal problems, community detection methods represent an emerging area of research. Contributing to this field, the authors propose a new community detection algorithm based on the hybridization of node and link granulation.

The proposed algorithm utilizes a rough set-theoretic concept called closure on networks. Initial sets are constructed by using neighborhood topology around the nodes as well as links and represented as two different categories of granules. Subsequently, the authors iteratively obtain the constrained closure of these sets. The authors use node mutuality and link mutuality as merging criteria for node and link granules, respectively, during the iterations. Finally, the constrained closure subsets of nodes and links are combined and refined using the Jaccard similarity coefficient and a local density function to obtain communities in a binary network.

Extensive experiments conducted on twelve real-world networks followed by a comparison with state-of-the-art methods demonstrate the viability and effectiveness of the proposed algorithm.

The study also contributes to the ongoing effort related to the application of soft computing techniques to model complex systems. The extant literature has integrated a rough set-theoretic approach with a fuzzy granular model (Kundu and Pal, 2015) and spectral clustering (Huang and Xiao, 2012) for node-centric community detection in complex networks. In contributing to this stream of work, the proposed algorithm leverages the unexplored synergy between rough set theory, node granulation and link granulation in the context of complex networks. Combined with experiments of network datasets from various domains, the results indicate that the proposed algorithm can effectively reveal co-occurring disjoint, overlapping and nested communities without necessarily assigning each node to a community.

This study carries important practical implications for complex adaptive systems in business and management sciences, in which entities are increasingly getting organized into communities (Jacucci et al., 2006). The proposed community detection method can be used for network-based fraud detection by enabling experts to understand the formation and development of fraudulent setups with an active exchange of information and resources between the firms (Van Vlasselaer et al., 2017). Products and services are getting connected and mapped in every walk of life due to the emergence of a variety of interconnected devices, social networks and software applications.

The proposed algorithm could be extended for community detection on customer trajectory patterns and design recommendation systems for online products and services (Ghose et al., 2019; Liu and Wang, 2017). In line with prior research, the proposed algorithm can aid companies in investigating the characteristics of implicit communities of bloggers or social media users for their services and products so as to identify peer influencers and conduct targeted marketing (Chau and Xu, 2012; De Matos et al., 2014; Zhang et al., 2016). The proposed algorithm can be used to understand the behavior of each group and the appropriate communication strategy for that group. For instance, a group using a specific language or following a specific account might benefit more from a particular piece of content than another group. The proposed algorithm can thus help in exploring the factors defining communities and confronting many real-life challenges.

This work is based on a theoretical argument that communities in networks are not only based on compatibility among nodes but also on the compatibility among links. Building up on the aforementioned argument, the authors propose a community detection method that considers the relationship among both the entities in a network (nodes and links) as opposed to traditional methods, which are predominantly based on relationships among nodes only.

The purpose of this paper is to provide a guiding framework for studying the travel patterns of PT users. The combination of public transit (PT) users’ travel data and user profiling (UP) technology to draw a portrait of PT users can effectively understand users’ travel patterns, which is important to help optimize the scheduling of PT operations and planning of the network.

To achieve the purpose, the paper presents a three-level classification method to construct the labeling framework. A station area attribute mining method based on the term frequency-inverse document frequency weighting algorithm is proposed to determine the point of interest attributes of user travel stations, and the spatial correlation patterns of user travel stations are calculated by Moran’s Index. User travel feature labels are extracted from travel data containing Beijing PT data for one consecutive week.

In this paper, a universal PT user labeling system is obtained and some related methods are conducted including four categories of user-preferred travel area patterns mining and a station area attribute mining method. In the application of the Beijing case, a precise exploration of the spatiotemporal characteristics of PT users is conducted, resulting in the final Beijing PTUP system.

This paper combines UP technology with big data analysis techniques to study the travel patterns of PT users. A user profile label framework is constructed, and data visualization, statistical analysis and K-means clustering are applied to extract specific labels instructed by this system framework. Through these analytical processes, the user labeling system is improved, and its applicability is validated through the analysis of a Beijing PT case.

This research paper aims to analyze the scientific and grey literature on Quality 4.0 and zero-defect manufacturing (ZDM) frameworks to develop an integrated quality 4.0 framework (IQ4.0F) for quality improvement (QI) based on Six Sigma and machine learning (ML) techniques towards ZDM. The IQ4.0F aims to contribute to the advancement of defect prediction approaches in diverse manufacturing processes. Furthermore, the work enables a comprehensive analysis of process variables influencing product quality with emphasis on the use of supervised and unsupervised ML techniques in Six Sigma’s DMAIC (Define, Measure, Analyze, Improve and Control) cycle stage of “Analyze.”

The research methodology employed a systematic literature review (SLR) based on PRISMA guidelines to develop the integrated framework, followed by a real industrial case study set in the automotive industry to fulfill the objectives of verifying and validating the proposed IQ4.0F with primary data.

This research work demonstrates the value of a “stepwise framework” to facilitate a shift from conventional quality management systems (QMSs) to QMSs 4.0. It uses the IDEF0 modeling methodology and Six Sigma’s DMAIC cycle to structure the steps to be followed to adopt the Quality 4.0 paradigm for QI. It also proves the worth of integrating Six Sigma and ML techniques into the “Analyze” stage of the DMAIC cycle for improving defect prediction in manufacturing processes and supporting problem-solving activities for quality managers.

This research paper introduces a first-of-its-kind Quality 4.0 framework – the IQ4.0F. Each step of the IQ4.0F was verified and validated in an original industrial case study set in the automotive industry. It is the first Quality 4.0 framework, according to the SLR conducted, to utilize the principal component analysis technique as a substitute for “Screening Design” in the Design of Experiments phase and K-means clustering technique for multivariable analysis, identifying process parameters that significantly impact product quality. The proposed IQ4.0F not only empowers decision-makers with the knowledge to launch a Quality 4.0 initiative but also provides quality managers with a systematic problem-solving methodology for quality improvement.

In Germany, various approaches have been taken to tackle the current teacher shortage in technical and vocational education and training (TVET). One attempt to remedy the shortage in Bavaria has been the introduction of an engineering education study programme at universities of applied sciences. Ideal candidates for this programme should have an interest in both engineering and social interaction. For effective recruitment, therefore, it is necessary to know applicants’ characteristics such as their vocational interests. In this study, the vocational interest profiles of students in TVET teacher training programmes were identified and their interest profiles and further characteristics were compared with those of other VET students at universities and universities of applied sciences.

An online questionnaire based on Holland’s interest theory and adapted from the Allgemeiner-Interessen-Struktur-Test-3 (interest structure test) was administered to 85 students in TVET teacher training programmes at universities and universities of applied sciences in Bavaria. Items regarding reasons for choosing a particular study programme, university location and other personal details were added.

The vocational interest profiles of students at universities and universities of applied sciences can be described as similar but weakly differentiated. Insights are provided by the characteristics of students such as the majority being first-time academics in the family. The reasons for choosing the degree programme and university location highlight the fact that a large proportion of students in engineering education would not have chosen a teaching-related degree programme if it had not been offered at the respective university of applied sciences.

Although the sample in this study was small and, therefore, limiting, it represented a high proportion of TVET teacher training students in Bavaria and a substantial proportion of first-year students in TVET teacher training programmes at universities and universities of applied sciences in Bavaria (section 2.2 and 3.1). Thus, the findings provide valuable insights into commonalities in interest profiles between engineering education students at universities of applied sciences and other TVET students at universities. With respect to the domain of the chosen vocational specialisation, differentiated profiles emerged that, for example, showed a stronger artistic orientation among students in construction technology/wood. For further analysis, the previous variable-centred orientation of the analysis can be supplemented by person-centred analyses (e.g. cluster analysis and latent variable mixture modelling, LVMM) (cf. Leon et al., 2021).

The findings in this study reveal the potential for attracting candidates to universities of applied sciences if they prefer to study in rather rural areas close to their hometowns. With the aim to educate prospective teachers for future work not only in metropolitan regions but in rural areas too, offering bachelor degree programmes in rural areas would seem promising. A regional option can boost the recruitment of new students and attract candidates that otherwise would be unable to pursue studies or a career as a teacher in vocational education. The results of this study and those of previous studies suggest that universities of applied sciences can cooperate with universities to help solve the teacher shortage problem.

Overall, it is apparent that the students' interests reached comparatively high values in all interest orientations and thus are only weakly differentiated. If undifferentiated profiles indicate low levels of career readiness, this significantly affects the recruitment of young people for the teaching profession. Assessing career orientation and promoting vocational interests should be prioritised during secondary school education. Vocational orientation measures are essential and should provide insight into typical activities of daily work life in different professions and thus pique and foster interests.

This study provides insight into how to respond to the teacher shortage in VET by identifying important characteristics of engineering education students using vocational interest profiling.

The development of information technologies has led to a considerable transformation in human resource management from conventional or commonly known as personnel management to modern one. Data mining technology, which has been widely used in several applications, including those that function on the web, includes clustering algorithms as a key component. Web intelligence is a recent academic field that calls for sophisticated analytics and machine learning techniques to facilitate information discovery, particularly on the web. Human resource data gathered from the web are typically enormous, highly complex, dynamic, and unstructured. Traditional clustering methods need to be upgraded because they are ineffective. Standard clustering algorithms are enhanced and expanded with optimization capabilities to address this difficulty by swarm intelligence, a subset of nature-inspired computing. We collect the initial raw human resource data and preprocess the data wherein data cleaning, data normalization, and data integration takes place. The proposed K-C-means-data driven cuckoo bat optimization algorithm (KCM-DCBOA) is used for clustering of the human resource data. The feature extraction is done using principal component analysis (PCA) and the classification of human resource data is done using support vector machine (SVM). Other approaches from the literature were contrasted with the suggested approach. According to the experimental findings, the suggested technique has extremely promising features in terms of the quality of clustering and execution time.

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.