Please use this identifier to cite or link to this item: http://repository.futminna.edu.ng:8080/jspui/handle/123456789/18770
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMUHAMMAD, Muhammad Kudu-
dc.contributor.authorIshaq, Oyebisi Oyefolahan-
dc.contributor.authorOlayemi, Mikail Olaniyi-
dc.contributor.authorOjeniyi, Joseph Adebayo-
dc.date.accessioned2023-05-09T11:49:19Z-
dc.date.available2023-05-09T11:49:19Z-
dc.date.issued2023-02-28-
dc.identifier.urihttp://repository.futminna.edu.ng:8080/jspui/handle/123456789/18770-
dc.description.abstractThe concept of learning analytics is used for the purpose of aggregating, tracking, and scrutinising learner profiles using the digital and non-digital traits available in the Learning Management System (LMS). This is widespread with educational institutions as means of opening the potential of education through suitable analytics technologies. Recently, the openness of educational repositories to support learner profile learning analytics has raised issues of privacy due to access to sensitive information for diverse purposes. The opportunity to utilize learning technologies to be able to gather, analyze, and measure information about learners and learning environments, and process them into big data. To this end, learners’ private or sensitive attributes in the cloud big data are exposed to sub-consciousness, stalking and theft. Objective: Therefore, concerns about privacy breaches motivated this research to adopt attributes partitioning strategy into sensitive and non-sensitive attributes to enforce privacy during learner profiling using Fuzzy Analytic Hierarchy Process (FAHP) model. Method: This paper develops normalized weights and Attribute Sensitivity Index (ASI) computation index based on the FAHP model to determine top-five sensitive attributes in learners’ profile information. Ten (10) attributed were identified as most relevant for inclusion in the learner’s profile in which five (5) attributes were considered to be most-sensitive to respondents. Results: From these outcomes, top-five sensitive attributes in learner profile information were identified including: Marital Status (19.69%), CGPA (17.10%), Date of Birth (14.64%), Mobile number (14.21%), and Full Name (9.97%). Conclusion: This implies that, the top-five sensitive attributes must be protected to avoid privacy breaches, stalking, abuses, theft, sub-consciousness, harassments, and undue advantages of learners. In future works, preserving the privacy of sensitive LMS learners’ profile information can be performed in a blockchain environment.en_US
dc.description.sponsorshipUniversity Fellowship Studyen_US
dc.language.isoenen_US
dc.publisherIlorin Journal of Computer Science and Information Technology © Department of Computer Science, University of Ilorinen_US
dc.relation.ispartofseriesVol. 5, No. 1 (2022);ISSN: 2141-3959 (print)-
dc.subjectLearning Management System, Learner Profile, Sensitive, Privacy Preservation,en_US
dc.subjectFuzzy Analytical Hierarchy Processen_US
dc.titleFuzzy Analytic Hierarchy Process-based Learner Profile Sensitive Attributes Determination in Learning Management Systemen_US
dc.typeArticleen_US
Appears in Collections:Computer Science

Files in This Item:
File Description SizeFormat 
Muhammad, et al., ILJCSIT Journal Final.docx488.21 kBMicrosoft Word XMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.