About us
EU Member States have been exploring the use of web sources to produce statistics for a number of years. With the Web Intelligence Hub (WIH), a project under the European Statistical System (ESS) Innovation Agenda, Eurostat seeks to support and coordinate this work across the ESS.
The WIH aims to assemble and provide capabilities to gather and process web content, extracting meaningful information for statistical and analytical purposes. The WIH is supported by the ESS community of web intelligence experts through the Web Intelligence Network (WIN).
Key stakeholders
The WIH provides its services and data to:
- statisticians at national statistics institutes and other producers of official statistics, who can use the WIH’s data to produce timely, high-quality European and national statistics
- data scientists, methodologists, IT experts and other members of the EU's statistical community, who can use and help develop the WIH’s tools and methodologies to improve official statistics.
Additionally, the WIH collaborates with web content providers, including website owners, who provide access to web content for further processing.
Our way of working
The WIH operates in line with the European Statistics Code of Practice and its own principles, rules and procedures.
For web content retrieval, the WIH follows a set of dedicated guidelines, using machine learning and natural language processing to extract relevant information and produce microdata for statistical and analytical purposes.
For more information, please watch this short promotional video.
WIH data domains
The WIH organises its web content ingestion and data extraction activities into specific use cases. The three major use cases include:
- Online job advertisements (OJA): The WIH collects and processes the content of OJA from job portals, producing microdata for statistics on jobs and skills.
- Multinational enterprises (MNE): The WIH collects and processes online data related to MNEs, providing a broad dataset on enterprise groups.
- Online based enterprises characteristics (OBEC): The Web intelligence network collects the urls from enterprises.
Where is data collected and how can I find it?
The Web Intelligence Platform (WIP) supports the capabilities of the WIH by providing technical components and services. Data collection and analysis are conducted through specific use cases, and ESS members can use the platform for their own purposes.
Additionally, OJA data is accessible to ESS members via the DataLab. More information is available on our OJA section.
Resources
The WIH portal includes a comprehensive library with resources such as webinars, handbooks, videos, release notes, presentations, event recordings and training materials. These are regularly updated to ensure relevance.
Whether you are an official statistician, a member of the statistical community, or a website owner, these resources can provide you insights into the WIH's tools and methodologies.