InVesa 1.0: The Conceptual Framework of Interactive Virtual Academic Advisor System based on Psychological Profiles

Abstract

Interactive Virtual Academic System Prototype (InVesa) is a conceptual automated system dedicated to students where a theory of personality test, Holland Code (RIASEC) is integrated to aid students in selecting the ideal elective subjects for their Cognitive Science course. With InVesa, rather than giving alerts to academic advisors, students are assigned personalized advice by the system on the recommended elective subjects based on their RIASEC result. A student may choose to accept a list of subjects' recommendations from the system or to retake the RIASEC test until they are satisfied with the suggested subjects provided by the system. In addition, students with less time meeting their academic advisors to consult on their subject enrolment may avoid general issues that are common in the standard appointment registration system, such as multiple registrations and long queues when scheduling an appointment. It can be concluded that the proposed application meets the requirements. The proposed application provides a convenient and efficient solution to gain the required information and will benefit the targeted users, which achieves and fulfills the forth of Sustainable Development Goals (SDG) of Quality Education for better education quality for all in terms of gender, age and status.

Systematic Review of Recommendation Systems for Course Selection

“…The classification techniques KNN and Support Vector Machine with Radial Basis Kernel are reviewed, used, and compared during the data-mining process. Additionally, the article seeks to replace the current heuristic process's mathematical underpinning with data mining techniques, (10) Authors in [55] improved the accuracy of course recommendations using a machinelearning approach that utilizes the Naive Bayes algorithm, (11) Authors in [56] developed a list of suggestions for academics and professionals on the choice, configuration, and application of ML algorithms in predictive analytics in STEM education, (12) Based on a variety of criteria, authors in [57] mapped their present-day students to their alumni students. Then, in contrast to earlier articles that employed k-means, they used c-means and fuzzy clustering to find a superior way to predict the student's elective course, (13) The goals of the study [58] were to determine how KNN and Naive Bayes can be used to suggest the best and most advanced course options for students.…”

Applying Design Science Research Methodology for Development of a Mobile-Based Digital Quail Farming Guide

“…The practice of testing is the extent of the ease of use of the design, to be applied to a group of representative users. It entails an observation of users as they try to complete tasks and feedback is obtained from the users by way of interviews or questionnaires about user satisfaction on the product's prototype [27], [28]. According to Macefield [29], five to ten respondents are the least number of respondents required for usability testing.…”