Cycle 5 (2015 Deadline)
Data Science for Improved Education and Employability in Morocco
PI: Ghita Mezzour (email@example.com), International University of Rabat
U.S. Partner: Kathleen Carley, Carnegie Mellon University
Project Dates: February 2017 - January 2020
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 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.
|The PI and her team at the USAID career center in Tangier. Photo courtesy of Dr. Mezzour|
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.
Summary of Recent Events
In the quarter ending December 2017, Dr. Mezzour and her team continued to analyze job ads pertaining pertaining to the offshore sector in Casablanca in order to identify the needs of the sector in terms of hard skills. They were able to identify and remove duplicate ads that appear in different formats in different websites using the simhash algorithm (an algorithm for detecting near duplicates). They were also able to extract hard skills using a combination of regular expressions, keywords (e.g. salary, contract, and experience) and dictionaries (e.g. the list of programming languages and natural languages).
The PI reports that they find that the most Business Process Outsourcing (BPO) jobs are call center jobs. These jobs require little higher education and provide decent salaries (almost the double of minimal wage). The main focus of these jobs is foreign languages, mainly French. This means that these jobs could be interesting for a significant number of Moroccan youth that have no higher education. These young people would only need to take regular or online courses to help them master French.
The team is also working on identifying skills needed by the automobile sector in Tangiers. They reused some of the methods used for the offshore sector and develop new techniques to adapt to the specificities of the automobile sector. Their preliminary analysis based on a subset of job recruitment websites suggest that a big demand for an educated workforce, having a bachelor degree or a Master degree. French remains the most in demand language, followed by Arabic and English. They are currently working on incorporating more job ads into their analysis and extracting more technical and soft skills from these ads.
In the next 3-6 months, the PI and her team will continue working on extracting soft skills from job ads. Extracting soft skills is more challenging than extracting hard skills because the same soft skill can be referred to using different terms. They are currently investigating the use of Dbpedia (a project that aims at extracting structured content from Wikipedia) and Word2Vec (a powerful text mining algorithm that uses deep learning). They are refining their analysis of the needs of automobile sector in Morocco.
They will also be conducting a deeper analysis of the survey data from 2016 and 2017 about the relationships between employment stakeholders in Morocco. They plan to submit the results of that analysis to a journal. In addition to surveys, they are investigating the use of other data sources such as reports, social media and stakeholder websites to gain insight into stakeholders’ mental models. Analyzing stakeholders’ mental models could help explain why some stakeholders do not collaborate. For example, it could be that two stakeholders do not collaborate because their views of the problems are very different.
Back to PEER Cycle 5 Grant Recipients