From Web to Data Conference - Day One Presentations
Opening Session and Keynote Speech
Dominika Rogalińska
Albrecht Wirthmann
Marko Grobelnik
Heidi Kühnemann
URL finding: looking back, progress and plans for the future
Jacek Maślankowski
Providing online based enterprise characteristics with the Web Intelligence Hub
Donato Summa
Identifying official firm websites: a comparison of machine learning-based URL retrieval methods and AI-powered search engines
Caterina Liberati
Firms innovation capabilities and corporate websites: evidence on Italian SMEs
Mátyás Mészáros
State of play of the Data Acquisition Service (DAS) of the Web Intelligence Hub (WIH)
Emiline Roger
Leveraging online job advertisements for green skills analysis in France
Vladimir Kvetan
Assessment of classifiers using pre-defined data source
Annalisa Lucarelli
Development of a labour shortage indicator by occupation from OJA data
Mikołaj Tym, Jakub Żerebecki
Online job advertisements classification using encoder-like large language model
Donatas Šlevinskas
Combining online job advertisements with probability sample data for enhanced small area estimation of job vacancies |
Adam Tsakalidis, Antonio Ranieri
Using language models for extracting regions of employment from online job vacancies
Session Three - Online Based Enterprises Characteristics Use Cases
Chair - Olav ten Bosch
Josep Domenech
Evaluating the completeness of business databases: a comparison with official records using web scraping techniques
Ewelina Niewiadomska
Online based enterprise characteristics (OBEC) in Statistics Poland |
Arnout Van Delden
Use of dedicated business website to enhance the statistical business register in the Netherlands
Juergen Amann
Trade links: estimating interregional trade using weblinks
Material will be share upon request - juergen.amann@oecd.org
Vilma Nekrašaitė-Liegė
Applying survey sampling theory to web-scraped data: an analysis of OBEC data using the IPW estimator