Job quality

This project aims to develop novel indicators of job quality using online job advertisements. We intend to extract and classify a range of aspects mentioned within the adverts, including employment terms (e.g. offers to work flexible hours), benefits (e.g. life assurance) and job design (e.g. mentions of career progression).

We recognise that mentions of these aspects within adverts are likely be ‘noisy’ indicators, as advertised benefits may not always be accurate descriptions of the actual benefits. Nevertheless, these indicators could still provide a timely and low-cost signal of job quality dimensions. The UK has no official measuring system for job quality, and the main indicator is an annual survey.

The algorithms that we develop for extracting dimensions of job quality will be made freely available. We are also using this project to further refine our existing algorithms, which include a skills extractor algorithm and another that detects the industry which the advert sits within.

Our most recent work, using job adverts, is our Green Jobs Explorer which shows how we can use adverts to provide more nuanced insights on the aspects of greenness within occupations.

The project consists of two phases: “extracting selected drivers of job quality and “machine learning (ML) infrastructure & maintenance”.

Phase 1 will involve extracting benefits and other aspects mentioned in adverts, evaluating the resulting data, and comparing these job quality dimensions across occupations, industries and regions.

Phase 2 will involve developing an ML Infrastructure layer for all our data science and labour market projects. This will include building maintainable approaches using python libraries and project refactoring to modify codebases of any existing projects to make use of the new ML infrastructure layer. We will also engage with stakeholders to ensure our models are easy to use.

We are aiming to produce:

• An open codebase, containing a suite of hosted models which extract aspects within online job adverts (such as skills).
• An analysis of job quality, using our algorithms, with a special focus on jobs within the early years sector.

While there have been several efforts to define the dimensions of job quality, there have been far fewer efforts to measure these dimensions. Our approach offers a low-cost approach to quickly detect shifts in the prevalence of different benefits within jobs.

We will use our newly developed algorithms to carry out a detailed analysis of the advertised working conditions in the early years sector. Nesta’s Fairer Start Mission seeks to close the gap in early outcomes between young children growing up in disadvantage and the national average. A key challenge faced by the mission is a shortage of early years practitioners. Comparing aspects of job quality in this sector to others may help to spark ideas for improvements.

By releasing the algorithms, we hope that both the ONS and government departments (who hold their own datasets of job adverts) will be able to monitor aspects of job quality in any industry or occupation, and that these novel measures will provide a useful complement to more traditional approaches.