Aim of adaptive learning is to personalize course instruction for individual learners. Today, there is a huge amount of interest in creating learning systems that can support both teachers and students. Adaptive learning aims to support students by providing real-time feedback and adapting to students’ learning nuances. In the case of teachers, adaptive learning can help identify students that are at risk of falling back, and provide insights on how students’ learn concepts to improve the course over time.
A solution that leverages adaptive learning is commonly called an Intelligent Tutoring System (ITS). A typical ITS is depicted below.
The diagram shows that an ITS adapts to students’ needs in three different ways:
For details of each one can refer the link1. Summary is given in Adaptivity Grid below:
Parent involvement is a strong determining factor in the academic performance of almost all students. It refers to a condition where parents are proactively engaged in their children’s education. Several studies2 have shown how it plays a crucial role in students’ development.
Parents want better access to their children's data3 and the schools are also responding to this with educational portals and more detailed report-cards. However, making data available is only first step.
Parents will use data only if they trust it and it is presented in a manner that makes sense to them. Further they must be taught about methods to effectively use that data to support learning goals.
Data Analytics can help in all this. It can be used to design tools that can be used to convert data into actionable insights and information. With the right supports, parents can be savvy data consumers who actively engage with students’ data.
In a large academic institute it is nearly impossible to track each individual professor's performance. However, institutes can take students' feedback using scientifically designed surveys and use NLP to derive actionable insights from them. A data analyst can also help design a dashboard based on metrics which the institute wants to track and which updates weekly or daily.
Another advantage data analytics offers is monitoring and giving information on research performance. Data analytics monitors the number of likes and shares of research papers. E.g. the University of Bath use research performance in staff evaluation.
Student engagement is an active commitment to pay attention, complete assignments, and find value in their academic performance at school. There are three types of student engagement:
Behavioral : Students behave and don’t act out. They bring everything they need during class, follow instructions, work carefully and participate in class discussion.
Emotional : Students feel like they’re a part of the school community and are happy to be there! They greet you with a smile, interact positively with their classmates and look alert during your lessons.
Cognitive : Also known as intellectual engagement, students are eager to learn and think deeply about the subject matter. They ask challenging questions, and often go above and beyond when completing assignments.
Student engagement is important because it’s linked to increased student achievement. Since the 1980s, hundreds of studies4 have found that when teachers use strategies designed to capture students’ attention and actively involve them in the learning process, student achievement soars.
It is clear that to be able to measure student engagement and improve it by finding root cause of lack of it, schools must collect behavioral, emotional and cognitive data apart from academic data and analyze it.
Though retention and graduation are the hallmarks of student success metrics, they are lagging indicators. Schools must use analytics to identify leading indicators, and take a proactive and data-driven approach to student success.
Some leading indicators might be institution-specific, and can be discovered through predictive modeling, while some are common. E.g., completion of gateway courses, credit accumulation, and full-time continuous enrollment. Even more actionable indicators are behaviors such as timely registration, early and/or frequent activity in the learning management system, and participation in advising appointments.
One important challenge faced by educators is to constantly update the curriculum and yet keep it concise enough so that it can be taught in limited hours available. Internet is a huge source of data and techniques like web-scrapping can be used to get a lot of data. More important is making sense of data and distill information out of it. Curriculum update does not just mean updating the content but also updating the tools and techniques of teaching , researching and evaluating students and even predicting future trends and policy changes. Data analytics can help here too.
Today the educational institutes are ranked based on researches and publications made by faculty and students. A data-enabled organization will be far ahead of others. This is due to following reasons:
Large institutes with thousands of students and hundreds of faculty member is impossible to run unless it it data driven. Data Analytics can help in Payroll management, Tracking staff performance, tracking student performance, getting a 3600 analysis of each student and staff members in few click on a well designed dashboard, Predicting future trends in education and updating curriculum, designing learning goals and monitoring in real time (using big data) if they are being achieved and involving parents by providing them information on wards which makes sense to them and on which they can act.
Schools are using data analytics to create tuition systems that suit an individual’s unique capability and requirement and places him at the right level such that he does not need to learn what he already knows. Additionally, it can also reveal areas where a student is underachieving and identify the root cause of poor performance. This is difficult for a human to determine especially in a class environment. if number of students are very large (as is often the case in Indian education system), it may not be possible to cater to needs of each student. However, here also, clusters of students with similar attributes can be made and policies can be tailor-made for each cluster.
Although Indian institutes have only recently started using data science, there are several studies in reputed universities of world, which have proved that incorporating data analytics in academic and administrative functioning greatly improves vital benchmarks.
REFERENCES
