Advances in computation and web-scraping techniques allow us to use real-time information from company websites and social media platforms, namely digital footprint indicators. Additionally to their ...real-time availability, these indicators are easily accessible, making them a potentially practical tool for monitoring a company’s level of competitiveness. Therefore, this article aims to obtain a multivariate analysis method to accurately predict the wineries’ competitiveness group, applying the methodology to a sample of Valencian wineries to explore the association between digital footprint indicators and competitiveness.
Unsupervised learning techniques were implemented to detect outliers and clusters in observations using financial variables obtained from the Sistema de Análisis de Balances Ibéricos (SABI). Thus, clustering was used to identify groups of wine companies differentiating the sample of companies according to their competitiveness characteristics. Subsequently, footprint indicators were used to create multivariate models to predict the above classification of companies. Also, this methodology permits the study of which digital indicators are essential in this prediction, specifically the presence of words on the web and others regarding online company activities on social networks associated with competitiveness. This research provides practical guidance for developing and incorporating the essential digital indicators, which could be applied in wineries and any study of companies’ competitiveness.
•Digital footprint indicators derived from web content and social media presence can predict the competitiveness of wineries.•Key digital indicators include the presence of certain keywords on websites, such as export or resources.•The number of Instagram followers and the presence on LinkedIn is also associated with improved business performance.•Random Forest and Logistic Regression with Elastic Net regularization proved most effective in predicting winery competitiveness.
Measuring digitalization has been a central topic in academic discourse. While evaluating firms' efforts in increasing digitalization is crucial, quantifying it at scale, presents considerable ...challenges. This paper uses website information as a source of data to operationalize a measure of digitalization. Drawing on a sample of 60,942 firms, our approach proposes two distinct measures of digitalization: one at the product level and the other at the general organizational level. We substantiate these measures using a blend of qualitative and quantitative methods. The study validates the content of websites as a relevant source of innovation indicator data and verifies the indicators using multiple experiments. The developed digitalization indicators offer future research an empirical measure of digitalization that can be run at scale, across industries and regions through time.
•Highlights the multifaceted nature of digitalization and the challenges in measuring it through traditional methods.•Introduces novel empirical measures for firm-level digitalization based on large sample website data.•Demonstrates the utility of website information in assessing firm digitalization and innovation performance.•Offers insights into the firm level digitalization, enhancing understanding of industry and regional dynamics.
Web scraping, a technique for extracting data from web pages, has been in use for decades, yet its utilization in the field of migration, mobility, and migrant integration studies has been limited. ...The field faces notorious limitations regarding data access and availability, particularly in low-income settings. Web scraping has the potential to provide new datasets for further qualitative and quantitative analysis. Web scraping requires no financial resources, is agnostic to epistemic divides in the field, reduces researcher bias, and increases transparency and replicability of data collection. As large providers of digital data such as Facebook or Twitter increasingly restrict access to their data for researchers, web scraping will become more important in the future and deserves its place in the toolbox of migration and mobility scholars. This short and nontechnical methods note introduces the fundamental concepts of web scraping, provides guidance on how to learn the technique, showcases practical applications of web scraping in the study of migrant populations, and discusses potential future use cases.
Abstract
This research involves the usage of Machine Learning technology and Natural Language Processing (NLP) along with the Natural Language Tool-Kit (NLTK). This helps develop a logical Text ...Summarization tool, which uses the Extractive approach to generate an accurate and a fluent summary. The aim of this tool is to efficiently extract a concise and a coherent version, having only the main needed outline points from the long text or the input document avoiding any type of repetitions of the same text or information that has already been mentioned earlier in the text. The text to be summarized can be inherited from the web using the process of web scraping or entering the textual data manually on the platform i.e., the tool. The summarization process can be quite beneficial for the users as these long texts, needs to be shortened to help them to refer to the input quickly and understand points that might be out of their scope to understand.
Raising the bar (final) Elhorst, Paul; Fratesi, Ugo; Abreu, Maria ...
Spatial economic analysis,
10/02/2023, Volume:
18, Issue:
4
Journal Article
Peer reviewed
This editorial summarises the papers in issue 18(4) (2023). The first paper investigates attitudes towards civic engagement in relation to living closer to individuals with the same social status. ...The second paper develops a Bayesian estimator of a dynamic multivariate spatial ordered probit (DMSOP) model. The third paper examines the impact of drug-related activities on violent crime. The fourth paper web-scrapes data from individual firms to provide a better understanding of the determinants of innovation. The fifth paper tests the forecasting performance in post-crises years of spatial dynamic panel data (SDPD) models reformulated in first-differences. The sixth paper applies a count-data econometric model to explain early-stage (GE) business creation. The seventh paper examines patient migration flows among cantons and hospitals using a gravity model extended with spatial lags and a hospital efficiency score as an explanatory variable. The eighth paper studies whether the decision to migrate to pursue a tertiary education negatively affects student achievement at the university level as migration distance increases.
Satysfakcja klientów z oferowanych im usług jest kluczowa dla sukcesu każdego przedsięwzięcia biznesowego, szczególnie w sektorze turystycznym. Celem niniejszego artykułu jest analiza satysfakcji ...klientów polskich hoteli i zweryfikowanie, czy cechy charakterystyczne obiektów hotelowych różnicują zadowolenie ich gości. Badanie oparte zostało na danych zebranych z 2036 profili hoteli dostępnych na portalu Booking.com metodą web-scrapingu oraz poddane analizie ANOVA i obliczeniu współczynnika korelacji Pearsona w programie SPSS. Analiza wykazała, że poziom usług oferowanych przez polskie obiekty hotelarskie jest na zadowalającym poziomie. Satysfakcję polskich klientów najbardziej różnicują: kategoria hotelu, przynależność do sieci hotelowej oraz długość funkcjonowania. Niewielki wpływ na satysfakcję wykazano dla lokalizacji obiektu i jego wielkości. Charakterystyczna dla polskiego rynku hotelowego okazała się wyższa satysfakcja z jakości usług oferowanych przez hotele sieciowe w porównaniu do hoteli niezależnych oraz podobny poziom satysfakcji z jakości personelu. Artykuł wskazuje także na elementy wymagające działań ze strony osób zarządzających obiektami hotelarskimi w celu podniesienia satysfakcji ze świadczonych usług.
INTRODUCTION: Web scraping is a technique that provides organizations with the ability to analyse large amounts of information and gather new information.
OBJECTIVES: Find a group that is a health ...check, a full body test, a blood test, and so on. In this way, the pharmaceutical industry should consider how to improve information, information storage, information retrieval, and capture. For example, the healthcare system may decide to standardize the assessment of speech and allow information to be shared across organizations to improve treatment outcomes in web scraping applications.
METHODS: Web scraping is based on the pharmaceutical industry. From here, we get information about pharmacies, such as drug names in different categories or drug sales. However, we are dealing with diseases and common medicines. Using this information, we can find the most common viruses. There are many factors to consider when creating a junk website for the pharmaceutical industry, such as drug names, tablet categories, and syrups found in the pharmaceutical industry.
RESULTS: As is clearly visible from the output, there are columns for drug names, manufacturers, drug types, and prices. This is the information we get from a website called Net meds, a pharmacy site. With the help of this information, we learn which drugs are most needed, and then we can find the most common diseases today.
CONCLUSION: The results of this web scraping can be very useful and powerful. However, the industry's success in web scraping and data extraction techniques depends on the availability of clean chemical data.
Web data collected via web scraping and application programming interfaces (APIs) has opened many new avenues for retail innovations and research opportunities. Yet, despite the abundance of online ...data on retailers, brands, products, and consumers, its use in retailing research remains limited. To spur the increased use of web data, we aim to achieve three goals. First, we review existing retailing applications using web data. Second, we demystify the use of web data by discussing its value in the context of existing retail data sets and to-be-constructed primary web datasets. Third, we provide a hands-on guide to help retailing researchers incorporate web data collection into their research routines. Our paper is accompanied by a mock-up digital retail store (music-to-scrape.org) that researchers and students can use to learn to collect web data using web scraping and APIs.
Web scraping has numerous applications. It can be used complementary with APIs to extract useful data from web pages. For instance, commercial data is abundant, but not always relevant as it is ...presented on websites. In this paper, we propose the usage of web scraping techniques (namely, two popular libraries – BeautifulSoup and Selenium) to extract data from web and other Python libraries and techniques (vaderSentiment, SentimentIntensityAnalyzer, nltk, n consecutive words) to analyze the reviews and obtain useful insights from this data. A web scraper is built in which prices are extracted and variations are tracked. Furthermore, the reviews are extracted and analyzed in order to identify the relevant opinions, including complaints of the customers.
The development of technology increases data traffic and data size day by day. Therefore, it has become very important to collect and interpret data. This study, it is aimed to analyze the car sales ...data collected using web scraping techniques by using machine learning algorithms and to create a price estimation model. The data needed for analysis was collected using Selenium and BeautifulSoup and prepared for analysis by applying various data preprocessing steps. Lasso regression and PCA analysis were used for feature selection and size reduction, and the GridSearchCV method was used for hyperparameter tuning. The results were evaluated with machine learning algorithms.
Random Forest, K-Nearest Neighbor, Gradient Boost, AdaBoost, Support Vector and XGBoost regression algorithms were used in the analysis. The obtained analysis results were evaluated together with Mean Square Error (MSE), Root Mean Square Error (RMSE) and Coefficient of Determination (R-square). When the results for data set 1 were examined, the model that gave the best results was XGBoost Regression with 0.973 R2, 0.026 MSE and 0.161 RMSE values. When the results for data set 2 were examined, the model that gave the best results was K-Nearest Neighbor Regression with 0.978 R2, 0.021 MSE and 0.145 RMSE values.