Modeling of Personalized E-Learning Environment Based on Intelligent Agents

• Main Authors: Bahman Saeidi Pour, Mehran Farajolahi, Mohammad Reza Sarmadi, Hanieh Shahsavari
• Format: Article
• Language: English
• Published: Shiraz University of Medical Sciences 2017-09-01
• Series: Interdisciplinary Journal of Virtual Learning in Medical Sciences
• Subjects: modeling; e; learning; intelligent; agents
• Online Access: http://ijvlms.sums.ac.ir/article_44816_1d31f9983d16aaf61d8e3a082d1bf560.pdf
• ISSN: 2476-7263; 2476-7271

Background: The present study aimed at investigating the designing dimensions of personalized e-learning environment scale based on intelligent agents and presentation of an integrated model from 11 intelligent agents. Methods: This study was an applied research with respect to its nature and purpose, and a descriptive and survey research with regards to data collection methodology. The population of the study was 3 main groups: (1) professors in Payame Noor University (15 samples), (2) Ph.D. students in Payame Noor University of Tehran (48 samples), and (3) MA students of E-learning Center in Payame Noor University of Isfahan (112 samples) during the educational year of 2015 and 2016. To collect data, a researcher made questionnaire of personalized e-learning environment scale for intelligent agents was administered. Data were summarized and analyzed using Lisrel 8.5 software and SPSS 16 via descriptive indexes and inferential statistics. Using SPSS, the correlation coefficient between dependent and independent variables were measured, and the path analysis scale was performed to design a casual model, and finally the proposed fitting scale was measured using Lisrel software. Results: Results revealed that among the components of personalized e-learning environment pattern based on intelligent agents, user and electronic content factors were, respectively, the most and least important in the proposed design. Conclusions: The entire path of the research model was significant, which indicated a proper fitness of the proposed model to the real world data. Also, research hypotheses were approved, which means designing personalized e-learning environments by proposed intelligent agents increases the effectiveness of these courses.