The making of the incredibly differentiated labor market in Austria
We describe the emergence of and the continuous change in the labor market in Austria over a time span of about 100 years from the mid of 19th to the mid of 20th century through the lens of job ads in newspapers. Job ads hold many qualitative information about the vacancy and the candidate which can be assessed using modern natural language processing tools. We document the emergence, development and differentiation of the Austrian labor market. Job ads are one of the means to overcome incomplete information in this market.
We aim for three goals:
- We generate a unique data source for empirical analyses in various fields of humanities and economics, promoting that job advertisements in newspapers are a great source of individuals’ wills, wishes and offers, which are socially embedded but widely unfiltered by others.
- We illustrate the strong change in labor relationships in many dimensions such as extent, regional reach, sector focus, skill requirements, job characteristics, self-perceptions of employers and employees and expected or pretended relationships.
- We test and further develop digital methods for text mining and text analyses on a database of millions of advertisements with fairly heterogeneous content and structure.
A large pool of job ads generated from the ANNO newspaper database provided by ÖNB is the basis of our analysis. From this pool, we use the advertising pages of the 29 highest-circulation German-language newspapers and isolate the individual job advertisements. We identify, separate and translate them into machine-readable language. To assess these short, differentiated texts, we rely on background knowledge about the early Austrian labor market and on theoretical insights from the two-sided matching process. While the human eye recognizes job ads very quickly, an algorithm has to be trained to do so, which is a greater challenge given the different structure, size and statements of the job ads. However, we will have to find computer-aided solutions because the almost 8 million newspaper pages of the 29 newspapers cannot be analyzed manually. Natural language processing techniques (sentiment analysis, topic modeling) is harnessed to assess the huge amount of qualitative information.
Natural language processing is used increasingly in fields where the richness in the detail had been ignored before, because it could not have been handled. The labor market in large scale analyses is such a field, where significant simplifications, generalizations and abstractions have been used in order to cope with heterogeneity and differentiation on both sides of the market: job seekers and open positions. This project aims at removing the lack of detail in describing the early labor market in Austria by supplying a database of millions of job ads from both sides of the market.