|
Cycle 5 (2015 Deadline)
Data Science for Improved Education and Employability in Morocco
PI: Ghita Mezzour (ghita.mezzour@uir.ac.ma), International University of Rabat
U.S. Partner: Kathleen Carley, Carnegie Mellon University
Project Dates: February 2017 - January 2020
Project Overview:
The mismatch between the job supply and demand creates major social, political, and economic problems in Morocco. Every year, many graduates are unable to find jobs, and the resulting youth unemployment causes major social and political tensions. Paradoxically, at the same time, employers are unable to find candidates with the required skills, and this skills shortage results in missed economic opportunities for the country. Despite the importance of the studying skill mismatch in Morocco, the topic attracts very limited attention in the literature. Moreover, there is a lack of large data sets that researchers can use to systematically study the issue and identify effective interventions to alleviate it.
 | | The PI and her team at the USAID career center in Tangier. Photo courtesy of Dr. Mezzour |
The goal of this project is to measure the skill mismatch in Morocco and identify measures to align university training with the job market. More specifically, these researchers will collect and analyze multiple large data sets about higher education and the job market in Morocco.
They will build profiles of university graduates and job openings in Morocco and identify areas of misalignment between the two. They will also interview human resources staff from multiple organizations to learn about their concerns in more detail. Finally, they will collect traditional and social media discussions about higher education and jobs in Morocco in order to learn about the general population’s concerns about the topic.
This project should lead to advances in both education and computer science, and the analysis to be conducted should yield deep and novel insight about areas of mismatch between higher education and the job market in Morocco.
Final Summary of Project Activities
To reduce skill mismatch, it is important that higher education institutions have information about job market needs and adapt their curricula to such needs. Youth also need to be aware of job market needs in order to choose education paths that maximize their chances of finding a job. To examine whether higher education institutions and youth receive information about job market needs, the PI and her team analyzed the extent of collaboration between employment stakeholders using surveys and Social Network Analysis. 79 representatives of the private sector, public sector, youth, universities, recruitment agencies and funders took the survey in 3 major Moroccan cities. Their analysis reveals that higher education institutions receive very little information about job market needs from the private sector. Similarly, youth receive limited information about job market needs from the private sector and higher education institutions.
They collected and analyzed official reports and tweets by employment stakeholders (private sector, public sector, universities, vocational schools and youth) in order to identify the mental model and priorities of these stakeholders. They found that universities are concerned about education and research, but pay little attention to employment. On the other hand, companies are concerned about their products and services, but think little of education. The different mental models of stakeholders probably impede collaboration between them.
To help higher education institutions and youth have access to job market information, they collected novel data sets about the Moroccan job market and developed new techniques to analyze such data. More specifically, they weekly collect job ads posted in 10+ top recruitment Moroccan websites. Analyzing job ads would reveal job market needs and trends in Morocco, but such analysis is challenging because the majority of these ads are non-structured or semi-structured. Moreover, duplicate ads need to be removed, but those duplicates are difficult to automatically identify because they appear under different formats in different websites.
In this project, they used a variety of Natural Language Processing (NLP) techniques to remove duplicate ads and to extract and standardize job attributes from job ads. For example, they developed novel NLP technique to extract and standardize soft skills that achieve 0.84 F-score compared to 0.54 F-score achieved in prior work (F-score is an accuracy measure that is between 0 and 1). Other than soft skills, they extracted and standardized the job title, location, languages, recruiting company, education level, experience level and hard skills. They focused on analyzing the needs of 3 promising sectors for the Moroccan economy: automobile, offshore and cybersecurity.
This project has increased the awareness about 1) the importance of building ties between the private sector and higher education institutions 2) the importance of analyzing job market needs and taking such needs into account when designing curricula 3) the interest in using a data science approach to analyzing job market needs that can provide real-time analysis in a cost efficient manner. We have increased such awareness by organizing stakeholder meetings at the International University of Rabat, giving talks at various venues and meeting individually with various decision makers. They have increased awareness in Morocco about the potential of using data science to address societal issues.
Back to PEER Cycle 5 Grant Recipients
|
|
|
|
