On Demand Video Retrieval Based on Arabic TEXT
Main Article Content
Abstract
Duo to fast digital technology development in recent years and the evolution of digital cameras and social media, which depends mainly on videos, the interest towards video mining and manipulation field, was increasing because of the rich content of the video. Although Arabic videos are not so common to be studied because of the Arabic language complexity and since education in the meanwhile is facing difficulties duo to the medical situation effecting the whole world. A system was designed and implemented to make the electronic learning process easier for students that study in Arabic language. A model that serves the Iraqi students and the ministry of education was pro-posed. The system provides a search engine for students to reach out a specific topic they need to understand and provide a convenient environment to search for their favorite subject. A dataset of educational videos uploaded by the Iraqi educational television on their channel on YouTube platform. Audio feature was extracted from the videos, and then transcripts were generated by converting Arabic audio into text documents. A Stochastic Gradient Decent technique, which is a machine learning technique, was used to classify each of the videos and figure out to which category or subject the video belongs to. A search technique was applied to enable the student search through different categories of Arabic subjects. The results showed high classification accuracy for SGD in compare to other models.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.