Search results

This paper aims to perform an exhaustive revision of relevant and recent related studies, which reveals that both extraction methods are currently used to analyze credibility on Twitter. Thus, there is clear evidence of the need of having different options to extract different data for this purpose. Nevertheless, none of these studies perform a comparative evaluation of both extraction techniques. Moreover, the authors extend a previous comparison, which uses a recent developed framework that offers both alternates of data extraction and implements a previously proposed credibility model, by adding a qualitative evaluation and a Twitter-Application Programming Interface (API) performance analysis from different locations.

As one of the most popular social platforms, Twitter has been the focus of recent research aimed at analyzing the credibility of the shared information. To do so, several proposals use either Twitter API or Web scraping to extract the data to perform the analysis. Qualitative and quantitative evaluations are performed to discover the advantages and disadvantages of both extraction methods.

The study demonstrates the differences in terms of accuracy and efficiency of both extraction methods and gives relevance to much more problems related to this area to pursue true transparency and legitimacy of information on the Web.

Results report that some Twitter attributes cannot be retrieved by Web scraping. Both methods produce identical credibility values when a robust normalization process is applied to the text (i.e. tweet). Moreover, concerning the time performance, Web scraping is faster than Twitter API and it is more flexible in terms of obtaining data; however, Web scraping is very sensitive to website changes. Additionally, the response time of the Twitter API is proportional to the distance from the central server at San Francisco.

The purpose of this paper is to discuss web scraping as a method for extracting large amounts of data from online sources. The author wants to raise awareness of the method’s potential in the field of food price research, hoping to enable fellow researchers to apply this method.

The author explains the technical procedure of web scraping, reviews the existing literature, and identifies areas of application and limitations for food price research.

The author finds that web scraping is a promising method to collect customised, high-frequency data in real time, overcoming several limitations of currently used food price data sources. With today’s applications mostly focussing on (online) consumer prices, the scope of applications for web scraping broadens as more and more price data are published online.

To better deal with the technical and legal challenges of web scraping and to exploit its scalability, joint data collection projects in the field of agricultural and food economics should be considered.

In agricultural and food economics, web scraping as a data collection technique has received little attention. This is one of the first articles to address this topic with particular focus on food price analysis.

Timely detection of emergency events and effective tracking of corresponding public opinions are critical in emergency management. As media are immediate sources of information on emergencies, the purpose of this paper is to propose cross-media analytics to detect and track emergency events and provide decision support for government and emergency management departments.

In this paper, a novel emergency event detection and opinion mining method is proposed for emergency management using cross-media analytics. In the proposed approach, an event detection module is constructed to discover emergency events based on cross-media analytics, and after the detected event is confirmed as an emergency event, an opinion mining module is used to analyze public sentiments and then generate public sentiment time series for early warning via a semantic expansion technique.

Empirical results indicate that a specific emergency can be detected and that public opinion can be tracked effectively and efficiently using cross-media analytics. In addition, the proposed system can be used for decision support and real-time response for government and emergency management departments.

This paper takes full advantage of cross-media information and proposes novel emergency event detection and opinion mining methods for emergency management using cross-media analytics. The empirical analysis results illustrate the efficiency of the proposed method.

The proposed method can be applied for detection of emergency events and tracking of public opinions for emergency decision support and governmental real-time response.

This research work contributes to the design of a decision support system for emergency event detection and opinion mining. In the proposed approaches, emergency events are detected by leveraging cross-media analytics, and public sentiments are measured using an auto-expansion of the domain dictionary in the field of emergency management to eliminate the misclassification of the general dictionary and to make the quantization more accurate.

This article aims to know the direction of current research based on the previous research in the last ten years (2012–2021).

Text mining was integrated with a network and content analysis as part of the mix methodological approach. The scientific articles, on the other hand, were assembled on Litmaps through web scraping. This process selected 86 articles about medical tourism published between 2012 and 2021. This study employed AntConc, RStudio and Gephi tools for data analysis and visualization.

A total of 138 articles were identified through Litmaps using web scraping and 86 studies met the criteria. The trend of medical tourism research is a positive sign for tourism and health industries; this is the beginning to recognize the importance of elaborating on these two topics. Several researchers have frequently studied issues of destination, hospital, development, quality, stakeholders, surgery, service, economics and policy. Policymakers must establish a medical tourism ecosystem to accommodate all stakeholders in this industry. This study also recommends focusing on supply and institution for medical tourism future research.

This literature review presents research trends on medical tourism in 2012–2021 based solely on articles available on the Litmaps search engine. If the time span is extended and the sources of articles are expanded there will be more literature available for analysis. The articles obtained are also only articles published in English due to the language limitations of the author.

Policymakers must establish a medical tourism ecosystem to accommodate all stakeholders in this industry. Stakeholders must work together to provide medical tourism package therefore people can get their health services while visiting available tourist areas.

The literary study of medical tourism over 10 years is considered the most recent systematic literature review.

The purpose of this paper is to investigate if online reviews (e.g. valence and volume), online promotional strategies (e.g. free delivery and discounts) and sentiments from user reviews can help predict product sales.

The authors designed a big data architecture and deployed Node.js agents for scraping the Amazon.com pages using asynchronous input/output calls. The completed web crawling and scraping data sets were then preprocessed for sentimental and neural network analysis. The neural network was employed to examine which variables in the study are important predictors of product sales.

This study found that although online reviews, online promotional strategies and online sentiments can all predict product sales, some variables are more important predictors than others. The authors found that the interplay effects of these variables become more important variables than the individual variables themselves. For example, online volume interactions with sentiments and discounts are more important than the individual predictors of discounts, sentiments or online volume.

This study designed big data architecture, in combination with sentimental and neural network analysis that can facilitate future business research for predicting product sales in an online environment. This study also employed a predictive analytic approach (e.g. neural network) to examine the variables, and this approach is useful for future data analysis in a big data environment where prediction can have more practical implications than significance testing. This study also examined the interplay between online reviews, sentiments and promotional strategies, which up to now have mostly been examined individually in previous studies.

The aim of this paper is to present an initiative to apply the principles of Linked Data to enhance the search and discovery of OpenCourseWare (OCW) contents created and shared by the universities.

This paper is a case study of how linked data technologies can be applied for the enhancement of open learning contents.

Results presented under the umbrella of OCW-Universia consortium, as the integration and access to content from different repositories OCW and the development of a query method to access these data, reveal that linked data would offer a solution to filter and select semantically those open educational contents, and automatically are linked to the linked open data cloud.

The new OCW-Universia integration with linked data adds new features to the initial framework including improved query mechanisms and interoperability.

Starting from a critical analysis of the main criteria currently used to identify marginal areas, this paper aims to propose a new classification model of such territories by leveraging knowledge discovery approaches and knowledge visualization techniques, which represent a fundamental pillar in the knowledge-based urban development process.

The methodology adopted in this study relies on the design science research, which includes five steps: problem identification, objective definition, solution design and development, demonstration and evaluation.

Results demonstrate how to exploit knowledge discovery and visualization to obtain multiple mappings of inner areas, in the aim to identify good practices and optimize resources to set up more effective territorial development strategies and plans. The proposed approach overcomes the traditional way adopted to map inner areas that uses a single indicator (i.e. the distance between a municipality and the nearest pole where it is possible to access to education, health and transportation services) and leverages seven groups of indicators that represent the distinguishing features of territories (territorial capital, social costs, citizenship, geo-demography, economy, innovation and sustainable development).

The proposed model could be enriched by new variables, whose value can be collected by official sources and stakeholders engaged to provide both structured and unstructured data. Also, another enhancement could be the development of a cross-algorithms comparison that may reveal useful to suggest which algorithm can better suit the needs of policy makers or practitioners.

This study sets the ground for proposing a decision support tool that policy makers can use to classify in a new way the inner areas, thus overcoming the current approach and leveraging the distinguishing features of territories.

This study shows how the availability of distributed knowledge sources, the modern knowledge management techniques and the emerging digital technologies can provide new opportunities for the governance of a city or territory, thus revitalizing the domain of knowledge-based urban development.

The purpose of this paper is to highlight the intelligence and investigatory challenges experienced by law enforcement agencies in discovering the identity of illicit Bitcoin users and the transactions that they perform. This paper proposes solutions to assist law enforcement agencies in piecing together the disparate and complex technical, behavioural and criminological elements that make up cybercriminal offending.

A literature review was conducted to highlight the main law enforcement challenges and discussions and examine current discourse in the areas of anonymity and attribution. The paper also looked at other research and projects that aim to identify illicit transactions involving cryptocurrencies and the darknet.

An optimal solution would be one which has a predictive capability and a machine learning architecture which automatically collects and analyses data from the Bitcoin blockchain and other external data sources and applies search criteria matching, indexing and clustering to identify suspicious behaviours. The implementation of a machine learning architecture would help improve results over time and would be less manpower intensive. Cyber investigators would also receive intelligence in a format and language that they understand and it would allow for intelligence-led and predictive policing rather than reactive policing. The optimal solution would be one which allows for intelligence-led, predictive policing and enables and encourages information sharing between multiple stakeholders from the law enforcement, financial intelligence units, cyber security organisations and fintech industry. This would enable the creation of red flags and behaviour models and the provision of up-to-date intelligence on the threat landscape to form a viable intelligence product for law enforcement agencies so that they can more easily get to the who, what, when and where.

The development of a functional software architecture that, in theory, could be used to detected suspicious illicit transactions on the Bitcoin network.

Companies are currently facing the challenge of understanding how their business is affected by the large volume of opinions continually generated by their stakeholders in social media regarding their intangible assets (experiences, emotions and attitudes). With this in mind, the purpose of this paper is to present an innovative management model, named E2AB, to measure and analyse reputational intangibles from digital ecosystems and their impacts on tangible assets.

The methodology applied was big data and business intelligence techniques. These methods were used in the computing process to obtain daily data from every asset guarantees that the model is validated with robust data. This model has been corroborated using data from the banking sector, specifically 402,383 net data inputs from the digital ecosystems.

This study illustrates the existence of a holistic influence of intangible assets over tangible assets. The findings demonstrate complex relationships between tangible and intangible assets, determined not only by the type of variable but also by its valence and intensity.

These findings may help chief communication officers and general managers a better understanding of how intangible assets extracted from online users’ opinions are related to their organisation’s tangible assets plus a chance to find out about their impact and how to manage them for a practical and agile decision making in real time.

It is a pioneering work in establishing a model, which demonstrates transversal and holistic relationships between relational intangible and tangible assets of firms from digital ecosystems, using business intelligence techniques.

This study aimed to examine the similarities and differences between the ability to analyze the environment and exploit new knowledge (absorptive capacity) and the skills to generate value from innovation (appropriation). These fields have similar origins and are sometimes confused by practitioners and academics.

A review was conducted based on a full-text analysis of 681 and 431 papers on appropriation and absorptive capacity, respectively, from Scopus, Science Direct and Lens, using methodologies such as text mining, backward citation analysis, modularity clustering and latent Dirichlet allocation analysis.

In business disciplines, the fields are considered different; however, in other disciplines, it was found that some authors defined them quite similarly. The citation analysis results showed that appropriation was more relevant to absorptive capacity, or vice versa. From the dimension perspective, it was found that although appropriation was considered a relevant element for absorptive capacity, the last models did not include it. Finally, it was found that studies on both topics identified the importance of appropriation and absorptive capacity for innovation performance, knowledge management and technology transfer.

This is one of the first studies to examine in-depth the relationship between appropriation and absorptive capacity, bridging a gap in both fields.