- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
The rapid growth of Web usage for advertising job positions provides a great opportunity for real-time labour market monitoring. This is the aim of Labour Market Intelligence (LMI), a field that is becoming increasingly relevant to EU Labour Market policies design and evaluation. The analysis of Web job vacancies, indeed, represents a competitive advantage to labour market stakeholders with respect to classical survey-based analyses, as it allows for reducing the time-to-market of the analysis by moving towards a fact-based decision making model. In this paper, we present our approach for automatically classifying million Web job vacancies on a standard taxonomy of occupations. We show how this problem has been expressed in terms of text classification via machine learning. We also show how our approach has been applied to certain real-life projects and we discuss the benefits provided to end users.
Concluding Remarks and Research Directions
In this paper we have described our approach to Web Labour Market Intelligence along with three real-life application scenarios, focusing on the realisation of a machine learning model for classifying job vacancies. The main benefits of our approach to LMI are: (i) reduced the time-to-market with respect to classical survey-based analyses; (ii) multi language support through the use of standard classification systems - rather than proprietary ones - by overcoming linguistic boundaries over countries; (iii) the ability to represent the resulting knowledge over several dimensions (e.g., territory, sectors, contracts, etc.) at different level of granularity, and (iv) the ability to evaluate and compare international labour markets to support fact-based decision making. Our research goes in two directions. From an application point of view, we have been engaged by Cedefop to extend the prototype to the whole EU community to all 28 EU Member States, building the system for the EU Web Labour Market Monitoring14 . From a methodological perspective, reasoning with Web job vacancies raises some interesting research issues, such as the automatic synthesis of the labour market knowledge through word embeddings, the identification of AI heuristic-search algorithms for path-traversal over big knowledge-graph, as well as the design of novel AI techniques for data cleansing in a big data scenario. We are actually working on applying word-embedding to our labour knowledge graph, as this would allow representing lexicon differences in the different Countries.