Search results

1 – 10 of 524
To view the access options for this content please click here
Article
Publication date: 3 August 2021

Irvin Dongo, Yudith Cardinale, Ana Aguilera, Fabiola Martinez, Yuni Quintero, German Robayo and David Cabeza

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…

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Originality/value

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.

Details

International Journal of Web Information Systems, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1744-0084

Keywords

To view the access options for this content please click here
Article
Publication date: 12 November 2019

Judith Hillen

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…

Abstract

Purpose

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.

Design/methodology/approach

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

Findings

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.

Research limitations/implications

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.

Originality/value

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.

Details

British Food Journal, vol. 121 no. 12
Type: Research Article
ISSN: 0007-070X

Keywords

To view the access options for this content please click here
Book part
Publication date: 15 March 2021

Reto Hofstetter

Every second, vast amounts of data are generated and stored on the Internet. Data scraping makes these data accessible and usable for business and scientific purposes. Web

Abstract

Every second, vast amounts of data are generated and stored on the Internet. Data scraping makes these data accessible and usable for business and scientific purposes. Web-scraped data are of high value to businesses as they can be used to inform many strategic decisions such as pricing or market positioning. Although it is not difficult to scrape data, particularly when they come from public websites, there are six key steps that analysts should ideally consider and follow. Following these steps can help to better harness the business value of online data.

To view the access options for this content please click here
Article
Publication date: 14 August 2017

Wei Xu, Lingyu Liu and Wei Shang

Timely detection of emergency events and effective tracking of corresponding public opinions are critical in emergency management. As media are immediate sources of…

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Research limitations/implications

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.

Practical implications

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.

Originality/value

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.

Details

Online Information Review, vol. 41 no. 4
Type: Research Article
ISSN: 1468-4527

Keywords

To view the access options for this content please click here
Article
Publication date: 4 April 2016

Alain Yee Loong Chong, Boying Li, Eric W.T. Ngai, Eugene Ch'ng and Filbert Lee

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…

Downloads
7932

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Originality/value

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.

Details

International Journal of Operations & Production Management, vol. 36 no. 4
Type: Research Article
ISSN: 0144-3577

Keywords

To view the access options for this content please click here
Article
Publication date: 28 January 2014

Nelson Piedra, Edmundo Tovar, Ricardo Colomo-Palacios, Jorge Lopez-Vargas and Janneth Alexandra Chicaiza

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…

Downloads
1192

Abstract

Purpose

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.

Design/methodology/approach

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

Findings

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.

Originality/value

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

Details

Program, vol. 48 no. 1
Type: Research Article
ISSN: 0033-0337

Keywords

To view the access options for this content please click here
Article
Publication date: 2 July 2018

Angela S.M. Irwin and Adam B. Turner

The purpose of this paper is to highlight the intelligence and investigatory challenges experienced by law enforcement agencies in discovering the identity of illicit…

Downloads
1623

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Originality/value

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

Details

Journal of Money Laundering Control, vol. 21 no. 3
Type: Research Article
ISSN: 1368-5201

Keywords

To view the access options for this content please click here
Article
Publication date: 12 November 2019

Ana-María Casado-Molina, Celia M.Q. Ramos, María-Mercedes Rojas-de-Gracia and José Ignacio Peláez Sánchez

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…

Abstract

Purpose

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.

Design/methodology/approach

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.

Findings

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.

Practical implications

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.

Originality/value

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.

Details

Industrial Management & Data Systems, vol. 120 no. 1
Type: Research Article
ISSN: 0263-5577

Keywords

To view the access options for this content please click here
Article
Publication date: 22 March 2019

Karen L. Xie and Yong Chen

Despite the importance of hosts who contribute to the success of accommodation sharing through sharing underutilized space with guests, current literature sheds little…

Abstract

Purpose

Despite the importance of hosts who contribute to the success of accommodation sharing through sharing underutilized space with guests, current literature sheds little light on what exactly incentivizes hosts to grow their properties. The purpose of this study is to investigate the effects of multifaceted motivations including financial benefits, online social interaction and membership seniority and their interplay on hosts’ multiple listing behavior.

Design/methodology/approach

The study is instantiated on real-world business data collected from an accommodation-sharing platform in China. The data set includes 3,199 observations of 252 multi-listing hosts in Beijing who managed 815 properties from September 2012 to October 2016.

Findings

The study discloses that financial benefits, online social interaction and membership seniority significantly incentivize hosts to list multiple properties on the accommodation-sharing platform. In particular, the social incentive is the most important driver among the three. With a 1 per cent increase in online social interactions, the number of properties operated by a host would increase by 13.5 per cent. While the financial benefits and online social interaction motivate hosts to engage in the multi-listing behavior, such effects are significantly mitigated as the membership seniority increases.

Research limitations/implications

This study adds to the extant literature a unique yet less researched perspective of supply expansion driven by hosts. It also provides important practical implications for managing multiple properties for a healthy and viable accommodation-sharing community.

Originality/value

While a majority of the extant research on the sharing economy primarily takes a consumer-related perspective, this study addresses a different and original topic about hosts’ multiple-listing behavior that drives the supply of accommodation sharing. It is a first empirical investigation of the increase of accommodation sharing supply with host motivations explained.

Details

International Journal of Contemporary Hospitality Management, vol. 31 no. 4
Type: Research Article
ISSN: 0959-6119

Keywords

To view the access options for this content please click here
Article
Publication date: 4 May 2012

Evi Werkers and Peggy Valcke

Audiovisual works – especially cinematographic works – are at the heart of the changes resulting from the development of the information society. Media convergence

Downloads
1867

Abstract

Purpose

Audiovisual works – especially cinematographic works – are at the heart of the changes resulting from the development of the information society. Media convergence radically changed the way traditional audiovisual content is produced, distributed, consumed and eventually archived. Film producers slowly started to experiment with new ways of digital production such as the shortening of release windows to favor new on demand services. How does this translate to European film policy? Due to the unique double nature of cinematographic works which are both economic and cultural goods at the same time, the European film policy is at the crossing point of media, culture, competition and heritage. This paper seeks to address these issues.

Design/methodology/approach

In this research paper the authors assessed to what extent the adoption of digital technologies is stimulated throughout the value chain of film making and more precisely to what degree the distribution of a European culturally diverse catalogue of films is encouraged.

Findings

For the first time in history, European producers have the tools at their disposal to collaborate, promote and distribute internationally, at lower transaction costs and at a higher speed, and to look beyond their national market. The fast‐evolving technological developments provided the European legislator with the opportunity to strengthen and support the promotion of the European cultural identity in all its diversity. But is this also reflected in the current legislative framework? It is clear that different hurdles still need to be tackled.

Originality/value

In this research paper an overview is given of the regulatory steps that have been taken so far in the field of European film policy to stimulate the digital production and distribution of European film productions. In the context of new unfolding alliances between stakeholders and experiments with premium video‐on‐demand or shorter cinema release windows, the relevance of digital production and distribution schemes can no longer be neglected. The emergence of web‐based services including cloud computing is likely to accelerate this trend.

1 – 10 of 524