The Application of Learning Theories into Abdullah: An Intelligent Arabic Conversational Agent Tutor

Abstract

This paper outlines the research and development of a Conversational Intelligent tutoring System (CITS) named Abdullah focusing on the novel application of learning theories. Abdullah CITS is a software program intended to converse with students aged 10 to 12 years old about the essential topics in Islam in natural language. The CITS aims to mimic human Arabic tutor by engaging the students in dialogue using Modern Arabic language (MAL), and classical Arabic language (CAL), utilizing supportive evidence from the Quran and Hadith. Abdullah CITS is able to capture the user's level of knowledge and adapt the tutoring session and tutoring style to suit that particular learner's level of knowledge. This is achieved through the inclusion of several learning theories implemented in Abdullah's architecture, which are applied to make the tutoring suited to an individual learner. There are no known specific learning theories for CITS therefore the novelty of the approach is in the combination of well-known learning theories typically employed in a classroom environment. The system was evaluated through end user testing with the target age group in schools in Jordan and the UK. The initial evaluation has produced some positive results, indicating that Abdullah is gauging the individual learner's knowledge level and adapting the tutoring session to ensure learning gain is achieved.

ChatGPT and other AIs: Personal relief and limitations among mathematics-oriented learners

“…So this is a contradiction, and there can be no function from A to ∅. [Response from Bard] AI models can provide an actual mathematical explanation to student questions because it is programmed to respond to user's input [48][49][50] . One student thought that "AI can help because logic in mathematics is fixed" [ Participant 8].…”

A Systematic Literature Review of Intelligent Tutoring Systems With Dialogue in Natural Language

“…Although the application of the EMT strategy is not explicitly indicated in the studies related to Abdullah [54], Lana [55], Beetle II [56], CIRCSIM-Tutor [57], Dialog [58], Geometry Explanation Tutor [59], ITSpoke [60], My Science Tutor [61], Oscar [62], ProPL [63], ReportTutor [64], Rimac [65], RMT [66] and Why2-Atlas [67], after analyzing the way in which they perform the tutoring, we concluded that they belong to this type of ITS. Next, let us justify this conclusion for each of these systems.…”

English and Arabic Chatbots: A Systematic Literature Review

“…Converting a text to be less complicated terms  Providing dependency relationship between words or semantic structure of the text  Same the rules and patterns matching disadvantages [44], [45], [46] Corpusbased: [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63], [64], [65], [66], [67] AIML Represents the knowledge as objects which derived from XML  Advantages of pattern matching  Powerful in designing conversational flow  Building all the possible patterns manually  Difficult to scaling [68], [69], [70], [71], [72], [73], [74], [75], [76], [77]…”

“…Classical Arabic [73], [60], [72] Education English [117], [86], [90], [108], [118],[1 07], [45], [112], [109], [122] Classical and MSA Arabic [50], [51] MSA Arabic [54], [58], [57], [55], [52], [53], [ 67], [66], [110], [63], [65] Arabic dialects: Saudi Arabic dialect and Jordanian [77], [78] Healthcare English [41], [44], [47], [70], [49], [71], [ 119] MSA Arabic [74], [111] Arabic Dialects: Egyptian [100] Tourism and airline English [35], [43] MSA Arabic [59], [75], [46], [113], [115] Business and customer service English [87], [69], [121],…”