Educational Technology - Artificial Intelligence
M. Rezaei; E. Pazouki; R. Ebrahimpour
Abstract
Background and Objectives: Today, due to the increasing development of technology all over the world, e-learning systems are expanding rapidly. With the progress of electronic education, the movement from traditional education (the approach of providing one education for all) to personalized education ...
Read More
Background and Objectives: Today, due to the increasing development of technology all over the world, e-learning systems are expanding rapidly. With the progress of electronic education, the movement from traditional education (the approach of providing one education for all) to personalized education began. Personalized education is an educational approach that aims to customize learning based on a learner's strengths, skills, interests, and needs. This method of education, like any other new method, has its strengths and weaknesses. In fact, increasing motivation and acquiring self-defense skills can be considered as one of the important benefits of this type of training. On the other hand, as the weaknesses of this method, we can mention the time-consuming training, the challenge in implementation, and the lack of clarity in the method of application. Due to the availability of many data from learners, the use of artificial intelligence to personalize education will both increase the quality and make education more attractive. Nowadays, one of the ways to personalize education is to provide it based on the preferences of learners. Learner preferences can be self-identified and explicitly identified and extracted by directly asking the learner or implicitly and collecting and monitoring data. Today, modeling user preferences is one of the most challenging tasks in e-learning systems that deal with a large amount of information. The aim of this research was to extract the implicit preferences of the learner by using an online interactive intelligent educational system that models the learner's preferences using conceptualization for learning objects through profile expansion and the use of artificial intelligence algorithms. The model was trained with the collected interactive data and provides new learning objects based on the learner's preferences. This research was practical in terms of purpose.Methods: In this research, according to the society available to us, 29 male and female undergraduate students of computer sciences, with an average age of 21.5 years, who had not taken the machine learning course, were included as the participants. After registration, the participants were randomly divided into two control and experimental groups. The experimental group was presented with personalized content that matched their preferences, and the control group was presented with content that did not match their preferences. After the training, the learning rate and cognitive load of the participants were measured by the designed performance test and the NASA workload index questionnaire. At the end, the significance level of the obtained results of the two groups was evaluated using the independent t-test.Findings: Based on the obtained results, the average performance test scores of the experimental group who received content matching their preferences had no significant difference compared to the average of the control group with a value of p=0.7 (while learning), but the cognition of the control group was significantly lower with p=0.00 compared to that of the experimental group.Conclusion: Based on the findings of the research, providing personalized educational content based on learners' preferences using the profile expansion technique significantly reduced the cognitive load during learning. So, Providing educational content based on learners' preferences, as one of the personalized educational methods in e-learning, plays an important role in reducing the cognitive load of learners.
Technology-based learning environments
M. Moatari; E. pazouki; R. Ebrahimpour; M.R. Rezaee
Abstract
Background and Objectives: Today, e-learning is considered as a transformational technology and an important tool in the process of education and educational activities. On the other hand, the need to learn English as the first language in the world in order to exchange information and communicate with ...
Read More
Background and Objectives: Today, e-learning is considered as a transformational technology and an important tool in the process of education and educational activities. On the other hand, the need to learn English as the first language in the world in order to exchange information and communicate with other nations in order to use up-to-date knowledge is undeniable, so the use of information technology to produce and provide educational services to improve English language teaching and learning is effective. Identifying the effective factors in achieving learning is one of the important and researched cases. Since the factors affecting learning are very wide and extensive, it is important to identify these factors in solving the problems and shortcomings of the educational system. One of these factors is cognitive style. People use different learning styles according to their individual differences. Cognitive style can be defined as the way people process new information and experiences in their minds; therefore, it is necessary to create a personalized environment based on the cognitive style of individuals in order to better adapt the educational strategy to the needs and abilities of the user and increase the efficiency of the learning process. In this research, Riding’s cognitive style, which divides people into two dimensions, verbal-imagery and wholistic-analytic, is used as an effective factor in learning. This study aims to predict the cognitive style of riding, based on the mouse movement of users in a language teaching software. In this regard, the language training software was designed and implemented, in which all the user's mouse movements are recorded on a millisecond scale when reading the English text and using the media designed in the software. Next, by using machine learning methods and interactive data stored from users while working with the software, an intelligent model was presented that categorizes people in two dimensions based on Riding’s cognitive style. This research is practical in terms of purpose.Methods: In this study, Peterson’s cognitive style test is used to extract learners' cognitive style with the aim of constructing labeled data. Also, individuals’ mouse data is recorded when interacting with software, and artificial intelligence-based machine learning algorithms and models are used to build intelligent models for classifying and predicting individuals' cognitive styles. The process of training and building smart models is done through labeled data. Finally, the models used are evaluated by comparing the results of the cognitive style test and the outputs of the intelligent models. In the exams, male and female students aged between 22 and 35, with bachelor's and master's degrees familiar with English participated.Findings: Users stored interactive data was used as the input to the five classifiers of the decision tree, neural network, nearest neighbor, support vector machine, and random forest. Patterson test results were also used as labels for these models; thus, individuals were categorized into two dimensions based on Riding’s cognitive style. The best classification was related to the decision tree with 90% accuracy in the verbal-imagery dimension and 87% accuracy in the wholist-analytic dimension of the results of this research.Conclusion: According to the findings of this study, the designed language teaching system can intelligently extract the cognitive style of people when reading the English passage with appropriate accuracy. Therefore, in the future, the ability to provide personalized content in accordance with the cognitive style of people can be added to the designed software.
