Search results

For ranking aggregation in crowdsourcing task, the key issue is how to select the optimal working group with a given number of workers to optimize the performance of their aggregation. Performance prediction for ranking aggregation can solve this issue effectively. However, the performance prediction effect for ranking aggregation varies greatly due to the different influencing factors selected. Although questions on why and how data fusion methods perform well have been thoroughly discussed in the past, there is a lack of insight about how to select influencing factors to predict the performance and how much can be improved of.

In this paper, performance prediction of multivariable linear regression based on the optimal influencing factors for ranking aggregation in crowdsourcing task is studied. An influencing factor optimization selection method based on stepwise regression (IFOS-SR) is proposed to screen the optimal influencing factors. A working group selection model based on the optimal influencing factors is built to select the optimal working group with a given number of workers.

The proposed approach can identify the optimal influencing factors of ranking aggregation, predict the aggregation performance more accurately than the state-of-the-art methods and select the optimal working group with a given number of workers.

To find out under which condition data fusion method may lead to performance improvement for ranking aggregation in crowdsourcing task, the optimal influencing factors are identified by the IFOS-SR method. This paper presents an analysis of the behavior of the linear combination method and the CombSUM method based on the optimal influencing factors, and optimizes the task assignment with a given number of workers by the optimal working group selection method.

Culture is considered a critical aspect of social media usage. The purpose of this paper is to explore how cultures and languages influence multilingual users' cross-cultural information sharing patterns.

This study used a crowdsourcing survey with Amazon Mechanical Turk to collect qualitative and quantitative data from 355 multilingual users who utilize two or more languages daily. A mixed-method approach combined statistical, and cluster analysis with thematic analysis was employed to analyze information sharing patterns among multilingual users in the Chinese cultural context.

It was found that most multilingual users surveyed preferred to share in their first and second language mainly because that is what others around them speak or use. Multilingual users have more diverse sharing characteristics and are more actively engaged in social media. The results also provide insights into what incentives make multilingual users engage in social media to share information related to Chinese culture with the MOA model. Finally, the ten motivation factors include learning, entertainment, empathy, personal gain, social engagement, altruism, self-expression, information, trust and sharing culture. One opportunity factor is identified, which is convenience. Three ability factors are recognized consist of self-efficacy, habit and personality.

The findings are conducive to promoting the active participation of multilingual users in online communities, increasing global resource sharing and information flow and promoting the consumption of digital cultural content.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

This study examines three significant collaborative journalism projects in the Americas: The Panama Papers, from the United States-based International Consortium of Investigative Journalists (ICIJ); “América Latina, Región de Carteles,” by Colombian-based Connectas; and the first phase of the Brazilian-based project, Comprova, supported by Brazilian Association of Investigative Journalists (Abraji) and First Draft. The work investigates what encompasses collaborative journalism; and explores whether it is a recent phenomenon of the news ecosystem, a consequence of the institutional crisis of journalism, and if it is influenced by a network-based and platformed society. A mixed-method approach is applied in a three-stage analysis: (1) desk research; (2) quantitative content analysis; and (3) qualitative semi-structured in-depth interviews. To gain a broader picture of the organizations and their respective projects, documental and bibliographical research was carried out with a focus on data from press releases, corporate reports, and articles published on the websites of the organizations coordinating the projects. Furthermore, a quantitative content analysis of 10 news articles published by each of these collaboration partnerships was completed. Finally, qualitative semi-structured in-depth interviews were conducted with the directors, managers, and professional journalists’ part of the organizations and project. This study emphasizes the importance of collaborative practices, demonstrates how collaborative practices contribute to a new modus operandi of the news ecosystem; and considers why journalists and media organizations have turned to collaborative journalism as a model of production, circulation, and distribution of journalistic investigations.

The COVID-19 pandemic has generated unprecedented public fear, impeding both individuals’ social life and the travel industry as a whole. China was one of the first major countries to experience the COVID-19 outbreaks and recovery from the pandemic. The demand for outings is increasing in the post-COVID-19 world, leading to the recovery of the ride-sharing industry. Integrating protection motivation theory and the theory of reasoned action, this study aims to investigate ride-sharing customers’ self-protection motivation to provide anti-pandemic measures and promote the resilience of ride-sharing industry.

This study followed a two-phase mixed-methods design. In the first phase, the authors executed a qualitative study with 30 interviews. In the second phase, the authors used the results of the interviews to inform the design of a survey, with which 272 responses were collected. Both studies were conducted in China.

The present results indicate that customers’ perceived vulnerability of COVID-19 and perceived COVID protection efficacy (self-efficacy and response efficacy) are positively correlated with their attitude toward self-protection, thus leading to their self-protection motivation during the rides. Moreover, subjective norms and customers’ distrust appear to also impact their self-protection motivation during the ride-sharing service.

The present research provides one of the first in-depth studies, to the best of the authors’ knowledge, on customers’ protection motivation in ride-sharing services in the new normal. The empirical evidence provides important insights for ride-sharing service providers and managers in the post-pandemic world and promote the resilience of ride-sharing industry.

The purpose of this research is to propose and empirically validate a theoretical framework to investigate the willingness of the elderly to disclose personal health information (PHI) to improve the operational efficiency of AI-integrated caregiver robots.

Drawing upon Privacy Calculus Theory (PCT) and the Technology Acceptance Model (TAM), 274 usable responses were collected through an online survey.

Empirical results reveal that trust, privacy concerns, and social isolation have a direct impact on the willingness to disclose PHI. Perceived ease of use (PEOU), perceived usefulness (PU), social isolation, and recognized benefits significantly influence user trust. Conversely, elderly individuals with pronounced privacy concerns are less inclined to disclose PHI when using AI-enabled caregiver robots.

Given the pressing need for AI-enabled caregiver robots due to the aging population and a decrease in professional human caregivers, understanding factors that influence the elderly's disclosure of PHI can guide design considerations and policymaking.

Considering the increased demand for accurate and comprehensive elder services, this is the first time that information disclosure and AI-enabled caregiver robot technologies have been combined in the field of healthcare management. This study bridges the gap between the necessity for technological improvement in caregiver robots and the importance of transparent operational information by disclosing the elderly's willingness to share PHI.

Users often struggle to select choosing among similar online services. To help them make informed decisions, it is important to establish a service reputation measurement mechanism. User-provided feedback ratings serve as a primary source of information for this mechanism, and ensuring the credibility of user feedback is crucial for a reliable reputation measurement. Most of the previous studies use passive detection to identify false feedback without creating incentives for honest reporting. Therefore, this study aims to develop a reputation measure for online services that can provide incentives for users to report honestly.

In this paper, the authors present a method that uses a peer prediction mechanism to evaluate user credibility, which evaluates users’ credibility with their reports by applying the strictly proper scoring rule. Considering the heterogeneity among users, the authors measure user similarity, identify similar users as peers to assess credibility and calculate service reputation using an improved expectation-maximization algorithm based on user credibility.

Theoretical analysis and experimental results verify that the proposed method motivates truthful reporting, effectively identifies malicious users and achieves high service rating accuracy.

The proposed method has significant practical value in evaluating the authenticity of user feedback and promoting honest reporting.

This study, a conceptual paper, analyses the growth of curation in tourism and hospitality and the curator role in selecting and framing products and experiences. It considers the growth of expert, algorithmic, social and co-creative curation modes and their effects.

Narrative and integrative reviews of literature on curation and tourism and hospitality are used to develop a typology of curation and identify different curation modes.

Curational techniques are increasingly used to organise experience supply and distribution in mainstream fields, including media, retailing and fashion. In tourism and hospitality, curated tourism, curated hospitality brands and food offerings and place curation by destination marketing organisations are growing. Curation is undertaken by experts, algorithms and social groups and involves many of destination-related actors, producing a trend towards “hybrid curation” of places.

Research is needed on different forms of curation, their differential effects and the power roles of different curational modes.

Curation is a widespread intermediary function in tourism and hospitality, supporting better consumer choice. New curators influence experience supply and the distribution of consumer attention, shaping markets and co-creative activities. Increased curatorial activity should stimulate aesthetic and stylistic innovation and provide the basis for storytelling and narrative in tourism and hospitality.

This is the first study of curational strategies in tourism and hospitality, providing a definition and typology of curation, and linking micro and macro levels of analysis. It suggests the growth of choice-based logic alongside service-dominant logic in tourism and hospitality.

Recently emerged Packaging-as-a-Service (PaaS) systems adopt aspects of access-based services and triadic frameworks, which have typically been treated as conceptually separate. The purpose of this paper is to investigate the implications of blending the two in what we call “access-based triadic systems,” by empirically evaluating intentions to adopt PaaS systems for takeaway food among restaurants and consumers.

We derived relevant attributes of PaaS systems from a qualitative pre-study with restaurants and consumers. Next, we conducted two factorial survey experiments with restaurants (N = 176) and consumers (N = 245) in Germany to quantitatively test the effects of those system attributes on their adoption intentions.

This paper highlights that the role of access-based triadic system providers as both the owners of shared assets and the operators of a triadic system is associated with a novel set of challenges and opportunities: System providers need to attract a critical mass of business and end customers while balancing asset protection and system complexity. At the same time, asset ownership introduces opportunities for improved quality control and differentiation from competition.

Conceptually, this paper extends research on access-based services and triadic frameworks by describing an unexplored hybrid form of non-ownership consumption we call “access-based triadic systems.” Empirically, this paper addresses the need to account for the demands of two distinct target groups in triadic systems and demonstrates how factorial survey experiments can be leveraged in this field.

Although extant studies have investigated the antecedents of negative electronic word of mouth (eWOM), they treated it as a unidimensional concept without classification. To bridge this knowledge gap, this paper distinguishes rational negative eWOM (RNW) from emotional negative eWOM (ENW) and leverages the consumer value framework to investigate their drivers in the context of peer-to-peer accommodation platforms (PPAPs).

This study collected data through an online survey of 437 PPAP users. Partial least squares (PLS) were used to validate the proposed hypotheses. Further, the path coefficients comparison method was adopted to distinguish the different impacts of consumer values on RNW and ENW.

This research showed that self-presentation exerted a positive impact on RNW, but its relationship with ENW was insignificant. Anger and regret were, respectively, positively related to ENW and RNW. Besides, altruism exerted a positive effect on RNW, whereas it had a negative effect on ENW.

First, this paper makes a fresh attempt to categorize negative eWOM into RNW and ENW. Second, this paper draws upon the consumer value framework to dissect varied motivations for posting RNW versus ENW on PPAPs. Third, this paper empirically verifies the differential influences that consumer values exert on RNW and ENW.