This work deals with the possible formalization of a theoretical and applicative framework for the design of hardware and software technologies for learning. It is proposed an alternative theorization to what has been developed so far in the field of digital applications enhanced by artificial intelligence and, specifically, the work focuses on the possible use of the adaptive tutoring systems methodology based on artificial agents. The need to investigate these issues, in a formal and applicative manner, arises from the growing market of educational systems and programs that allow for a learning experience customization. They are used in the European students’ learning paths, therefore, is required a greater in-depth analysis of the design, and of the study and development plans. This article presents the formalization of a design scheme for an AI-based learning application, which will have as its starting point a certain learning theory, up to the specific characteristics of the artificial agent. It is also proposed a framework useful to create these kinds of tools, called LET (Learning Enhancer Tools), and the formalization of an artificial agent algorithm analysed in every operating component. The already existing educational technological aids, often represent only a digital transposition of textbooks and exercises and allow only the use of a technological tool, but the LETs are real learning amplifiers, in other words, they are tools, strategies or methodologies (hardware, software) that help to improve the effectiveness and efficiency of the learning process through the ad hoc customization of learning paths and exercises, thanks to the use of AI and data analysis.
Learning Enhancer Tools (LET): un modello teorico per la progettazione di applicazioni educative basate sull’intelligenza artificiale
	
	
	
		
		
		
		
		
	
	
	
	
	
	
	
	
		
		
		
		
		
			
			
			
		
		
		
		
			
			
				
				
					
					
					
					
						
							
						
						
					
				
				
				
				
				
				
				
				
				
				
				
			
			
		
			
			
				
				
					
					
					
					
						
							
						
						
					
				
				
				
				
				
				
				
				
				
				
				
			
			
		
			
			
				
				
					
					
					
					
						
						
							
							
						
					
				
				
				
				
				
				
				
				
				
				
				
			
			
		
			
			
				
				
					
					
					
					
						
							
						
						
					
				
				
				
				
				
				
				
				
				
				
				
			
			
		
		
		
		
	
Angelo Rega
;Raffaele Di Fuccio;Pierpaolo Limone
	
		
		
	
			2024-01-01
Abstract
This work deals with the possible formalization of a theoretical and applicative framework for the design of hardware and software technologies for learning. It is proposed an alternative theorization to what has been developed so far in the field of digital applications enhanced by artificial intelligence and, specifically, the work focuses on the possible use of the adaptive tutoring systems methodology based on artificial agents. The need to investigate these issues, in a formal and applicative manner, arises from the growing market of educational systems and programs that allow for a learning experience customization. They are used in the European students’ learning paths, therefore, is required a greater in-depth analysis of the design, and of the study and development plans. This article presents the formalization of a design scheme for an AI-based learning application, which will have as its starting point a certain learning theory, up to the specific characteristics of the artificial agent. It is also proposed a framework useful to create these kinds of tools, called LET (Learning Enhancer Tools), and the formalization of an artificial agent algorithm analysed in every operating component. The already existing educational technological aids, often represent only a digital transposition of textbooks and exercises and allow only the use of a technological tool, but the LETs are real learning amplifiers, in other words, they are tools, strategies or methodologies (hardware, software) that help to improve the effectiveness and efficiency of the learning process through the ad hoc customization of learning paths and exercises, thanks to the use of AI and data analysis.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
