Welcome to our Community Log!
This page is for those of you who would like to contribute to JobTech Links: an enriched data file in the project Ecosystem for Ads. Arbetsförmedlingen (The Swedish unemployment agency) is collaborating with private owned Job boards and Statistics Sweden (SCB) in order to get better statistics of the labour market and better user search experience.
Short description of what we are aiming for
- Better statistics - Possible with more data from many actors
- Better user experience - Possible to build aggregated job search with the API.
The intention is to have both internal and external contributors in the project where we allow distributed and asynchronous work, a first good step towards an open source community. To simplify the processes with working on the same code base we use a pipe and filter architecture.
We need help. An important use case is to help job seekers that have been out of a job for a longer period of time. When we have around 75 000 ads, how can we present those that a relevant for this segment. Ads are unstructured data. We need help using text analytics to produce metadata for the necessary search and filtering parameters. With AI we think it possible to collect data from different sources and structure it for a better job seeker experience.
Many of the issues in the community log concerns AI and data analysis. We need the following metadata for search and filter
Jobs without education requirements
Jobs without a driver's license requirement
Jobs without previous work experience
Other? (Please come with suggestions).
Translation of skills taxonomy from Swedish to English.
Visualize statistics in new simple ways, the official statistics are based on how many ads there are per occupation and municipality.
General feedback - We want to be open. But are we doing the right thing. Is it possible to understand our source code, project and the data.
To our issue tracker. Please look for issues labeled Community Log.
Manual for creating a step in our pipeline
Job Ad Processing with the JobTech Links Pipeline https://gitlab.com/arbetsformedlingen/joblinks/pipeline/-/blob/develop/docs/pres-fossnorth2021.org
Check the file LICENSE in every repository. For most source code we use Apache 2. The data is licensed with CC0.