The web nowadays is overloaded with huge volumes of disparate information and linked data (i.e. Big Data) which requires the use of specific tools, Data Science methods (e.g. Machine Learning) and emerging technologies in big data in order to improve transparency and recognition of domain specific skills through the web. Job profiles contain general job description, expected competencies, skills and duties. Moreover, job centers and agencies typically aim at matching desired job profiles with suitable candidates. However, job seekers face difficulties in better understanding of the required job knowledge and competences through reviewing job profiles. Moreover, public and private sectors need IT-based tools to simplify transparent recognition of domain specific job knowledge while setting up their job profiles. It becomes more challenging when different countries provide different priorities and job descriptions due to various job market characteristics, vocational and educational trainings (VET) and demographic circumstances. This challenge prevents mobility of skilled workers, youth and workforce across Europe. It is shown that unemployment problem and risk of social exclusion hit more youth and young workforce in the European countries. Specially, the current refugee crisis caused by large amount of refugees and asylums in Europe enforces further difficulties to earlier stated challenges. Considering all stated challenges, the massive amount of information on the web such as job announcements, forums and wikis, is a gold mine for job knowledge discovery. The main issue in this regard is how to retrieve, cleanse, explore, visualize and interpret such huge volume of web data and put them in a sort of Job Knowledge Base (JKB). In addition, semantic web mining promotes exploitation of semantic structures in the JKB formed through web mining. Accordingly, enriched JBK using web data analytics (1) improves construction of job profile templates, (2) contributes to job analytics, labor market demand analysis, wage analysis, (3) facilitates skilled worker mobility, (4) supports identification of required skills and qualifications and (5) helps strengthening key competences in VET curricula.DISKOW will provide a neat Job Knowledge Base (JKB) as a prototype which collects job specific data from the web and provides recommendations through analytics. Job knowledge catalogue of a job definition in the JKB will be equipped with a template of the most typically required competences and skills for that job. Job seekers will be able to use the JKB in order to develop their domain specific skills and competences based on recommendations in specific job knowledge catalogue. In this regard, the mined information of jobs as well as their relevant competences and skills can be used to identify list of top demanding jobs, skills and competences and provide predictive analytics.The consortium consists of four partners, namely the L3S Research Center at the Leibniz University of Hanover in Germany, the Institute of Economic Research at the Slovak Academy of Sciences (IER SAS), Engineering as a large enterprise in software development and skill analysis modeling provider in Italy and Petanux GmbH as a private data science and research exploitation company in Germany. The consortium as a whole provides professional competences for fulfilling the objectives and promises of DISKOW. In addition, the project partners will disseminate the project results in cooperation with their networks through governmental as well as private employment agencies, VET providers and other related stakeholders to flourish the results and outcomes and sustain the project and the platform in long term.From the non-technical point of view, DISKOW aims at analyzing the labor market at the level of consortium partnership countries whereas the proof of concept can be used to the labor market analysis at the European level. As a result, DISKOW will be able to provide a streamline of the workforce development and provide predictions and road-maps for the future of specific required competences and jobs. Accordingly, data science has moved to the top of European labor markets’ list. Due to the importance of data science jobs in the European labor market, DISKOW will focus on the identification of skills and qualifications in the data science sector as a specific case study. The final solution will be ready to be adapted to a wide variety of sectors and workforces. This proposal has been once accepted for funding last year with great scores. The University of Koblenz had internal difficulties with EU to sign the contract, therefore we agreed to resubmit the proposal once through LUH this year. Furthermore, thanks to reviewers of last year, we even improved the quality of proposal in terms of review critics from last year, meaning that this year's submission targets even review comments after acceptance of last year for having higher quality project.

Five Noncommunicable Diseases (NCD) – diabetes, cardiovascular disease, cancer, chronic respiratory disease and Mental Health Disorders (MHD) – account for 86% deaths and 77% disease burden in the WHO Europe region. Of these five NCDs, MHD is unique as it has a complex bi-directional relationship with the other four major NCDs, meaning that, on one hand, it could be the initiator of the other NCDs, or other NCDs could lead to MHD which, in turn, can further aggravate the primary NCD leading to a vicious circle. Recent research identified MHD as the highest ranked NCD in adolescent population. A specific group in this population that is 3 - 6 times more vulnerable for developing MHD and subsequent NCD is the adolescents diagnosed with Autism Spectrum Disorders (ASD). There is no Evidence Based Intervention (EBI) for preventing MHD in an ASD adolescent since 1) the major risk factors are in-grained in their biological process and 2) they present with multiple MHD comorbidity. Personalisation is the key to prevent their already vulnerable mental states making transition to an MHD - "which" EBI is appropriate for "which" ASD adolescent and "how" to choose it - an unsolved question. Because of their neurobiological characteristics, personalisation must be done at biological level. Recent research showed how the environmental factors can alter gene expressions that leads to an MHD through Epigenetic-Genetic/metabolomic-Mental health (EGM) process. Using quantitative modelling of this process, ETHREAL will develop a personalised, flexible, single service delivery model that will empower an ASD adolescent to self-control their environmental factors while seamlessly accessing the community care services to prevent their mental health making transition to an MHD - a unique solution for sustainable prevention of MHD and subsequent NCDs in this population. Without loss of generality, the proposed solution could be adapted to prevent MHD in wider adolescent population.