Article Preview
Top1. Introduction
Internet of things (IoT) emerges due to advanced sensors entrenched in different smart devices, like personal digital assistance (PDA) and smartphone, which has generated substantial data and saved it in different data storage centers, which is collectively known as big data. In this context, service recommendation is considered as one of the noteworthy methods in extracting imperative information from huge data considering diverse domains, like education. In general, the analysis of chronological education involved the quality of service produced by the educational users dispersed in different platforms (Kaviyaraj and Uma, 2021), and the recommender system help to extract the impending interest of the target user with lightweight recommendation techniques (Gong et al., 2018). For enhancing the work and providing qualitative education, the practitioner of school requires interoperable data of students and illustration of processes involved in school, which exist in a different system. The commonly associated concept in education includes the hope of privacy. The privacy concern in most cases relate to the protection of student data like educational records and other information that are personal and like medical records. Also, there is variety of issues contributing to concerns over student privacy in online education. Like, any personal information going public needs to be used in a generic context. Interoperability amongst various systems is described as the capability for communicating the usage and operations of various peer models (Amalarethinam and Balakrishnan, 2012; Amalarethinam et al., 2012) and there is a usual faultless communication flow and information exchange amongst cooperative models. With more digitized school infrastructures, the data management models and automated content of sharing data and its functionalities become extremely complicated. In addition, the issues of interoperability can limit the capability of education stakeholders for productively computing the efficiency of the school and determine and assess learning issues to devise reasonable interventions and devise suitable tools to learn, instruct and access the data (Militello et al., 2013). Today’s schools utilize education technologies with different levels for organizing and storing longitudinal data in managing and storing course content for analyzing students’ performance. Thus, the data is split into irreconcilable models and universal isolation. In most scenarios, the vendor shares the data which puts a load on the instructor for physically inserting new data in the school for analyzing the progression of students (Hillman and Ganesh, 2019).