Extracting the needs of the labor market in Riyadh through Twitter using text classification techniques
Main Article Content
Abstract
Recently, Twitter has attracted a great deal of spread and attention. It is one of the most common social networking sites for sharing ideas, chats, and transfer of information and news through text. The labor market is where the supply and demand for jobs meet, with employees satisfying employer needs for certain services. On the one hand, certain jobs are being eliminated, while others are being replaced by new jobs that were not even possible a few years ago. In this paper, we focused on labor market classification of twitter data belonging to Riyadh city and written in Modern Standard Arabic. We want to classify Arabic jobs’ tweets to determine the trending of required job in Riyadh city. Twitter’s API was used to collect tweets related to labor market. Five different classifiers were used on the dataset namely; Support Vector Machine (SVM), Multinomial Naive Bayes (M-NB), Decision Tree (DT), Gradient Boosting Classifier (GBC), and Random Forest (RF).to classify the tweets based on their related job classes. We evaluated our work by four different measures which are Precision, Recall, Accuracy and F-measure. We made a comparison between the five classifiers based on those measures. The results show that RF achieved the best Accuracy and F-measure, and it equals 93.62%, 93% respectively. In addition, we found that the trend of labor market needed was administrative jobs “وظائ٠ادارية. “. The percentages of that job class that related to 384 jobs about 19.2%.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.