Teaching and understanding Qur`an using adaptive intelligent system for collaborative online learning

Abstract

Nearly eighty percent of the world`s Muslim populations are non-native speakers of Arabic; according to Pew Research Centre, this constitutes almost one billion people. Muslims consider the Qur’an as the divine revelation, compiled in a book which was recited and preserved in the original Arabic language. According to Islamic rulings, it is obligatory for Muslims to read and listen to the Qur`an in Arabic during prayers. Because of this reason, Muslims are required to memorize or learn at least a part of the Qur’an in the Arabic language. Consequently, an extraordinary social phenomenon has taken place in some regions of the Muslim world - Muslims, men, and women are taught the complex phonological rules of the Arabic language in the context of the Qur`an. They learn these rules and recite the "sounds" of the Qur`an understanding very little of what they are reciting. Similarly, when listening to the Imam reciting the Qur`an in prayer, they barely understand what they are listening to. This lack of comprehension has given rise to a demographic segment, who are consumers of Arabic language classes, language learning books, and software to overcome this particular language barrier. Despite the availability of resources for this purpose, according to our detailed investigation, no empirical research has yet identified the learning environments and the unique learning requirements of the target demography to examine the problem from the perspective of Computer Assisted Language Learning. In this thesis, we re-framed the problem from second language learning into a stimulus response problem. We gather substantial evidence from secondary analysis of learning theories and based our hypothesis on both the learners’ background and the specific requirements of learning. Based on these assumptions we proposed an innovative and unique intelligent and adaptive e-learning framework for learning Arabic specifically for this target demography. To test the validity of this hypothesis initially, we implemented a web-based prototype of the proposed system using task models derived from our projected assumptions to build a community of learners and content developers. This web-based platform helped us in creating a real-life laboratory with the genuine stakeholders of the system which is essential for the design-enactment-reflection-refinement iterations used predominantly in cognitive research professed by Design-Based Research Methodology. Through this process, we were able to contribute a novel, efficient and practical solution which can be adapted and applied to the field of Computer Assisted Language Learning where Language for Specific Purposes is concerned. The heuristics and algorithms described in this thesis helped extract combine and cluster pedagogical elements to assemble learning objects for our system. This kind of computational linguistics research has never been undertaken from the standpoint of classical Arabic and the Qur`anic text. The validation of the model was successfully accomplished through analysing system information, user data, and user feedback. The results of the analysis confirmed the model’s capability of producing valid results that can be used to obtain an in-depth understanding of this category of problems for further refinements and extensions.