Analytics in Education Measuring & Shaping Student Progress
Educational institutions are now looking at analytics for generating information on how they can adapt their teachings to help the students
By Mohd Ujaley
Recently when Prime Minister Narendra Modi and German Chancellor Angela Merkel visited the facilities of German automotive major Bosch in Bangalore, they were shown a presentation on how data analysis and data mining can help in the real time prediction of road accidents. The predictive abilities of data analysis and data mining can also be useful for the education sector. A humongous amount of data is being held by the schools, colleges, universities and education bodies across the country. This data can be analysed to uncover insights that will boost the student achievement and improve operational effectiveness across educational institutions.
It is important for educational institutes to track and record the data related to demographics, performance, attendance, co-curricular activities and placement records. They need to closely monitor the financial planning and budgeting process, faculty data and other operational data. “Analytics can provide interesting insights in several areas such as faculty attrition, popular courses and student preferences. Insights into educational performance can act as a strong guide for institutes to help students opt for courses in higher studies, and thereby aid them in selecting the ideal career path,” says Noshin Kagalwalla, Managing Director, SAS, India.
Mitesh Agarwal, Vice President & CTO, Oracle India, has similar views. He says, “Education sector can leverage the power of analytics to increase student, faculty and staff productivity, to better manage finances, streamline operations, and ensure the success of the students. They can also track the metrics around segments like student admissions, student records and financial management.”
Capturing the Basic Data
Presently the educational institutions are mostly capturing the data related to students and teachers age, qualifications, demography, attendance, test score, socio-economic status and placement. “Schools capture the scores of students in various tests, attendance and in some cases performance of students in extra-curricular activities. The attendance data and test-scores are analysed to find out the levels of interest in schooling for a specific student. If the student is losing interest, it will be manifested in the attendance and in grades,” says Sameer Dixit, Head-Big Data and Analytics, Persistent Systems.
Analytics can be helpful for correlating attendance with scores to identify the target scores and the minimum numbers of classes required. However, some experts are of the view that as most of the institutions are capturing only the basic data, they tend to lack the ability for extracting meaningful insights. According to Krishna Kant, Head, EMC Academic Alliance, South Asia & Russia, data generated by students, faculty and administration, can be analysed to discover useful, but for that a good analytics tool is needed. “At present most institutions don’t have access to better analytics tools,” he says.
Sanjeev Kumar Gupta, Managing Director-Health & Public Service, Government Relations and Corporate Affairs, Accenture, says that currently the schools are having a system for tracking the data on the performance of students and teachers, but as they lack dedicated and structured process, the data is not stored for a substantial duration. The short period for which the data is stored is not enough to generate meaningful insights. He suggests that ideally, an education institute should store data for at least 5-6 years.
Capturing more with Analytics tools
Today the data flows into the higher education institutions from all directions such as online applications; online classroom exercises; assessments, both online and offline; social media; blogs; and student surveys. The role that cutting-edge analytics software can play in deriving insights from a wide variety of data is well established.
“Analytics has made it possible to track the student’s entire learning curve. This gives rise to possibilities where tweaks can be made according to the pace and skill levels of the students. Tracking digital content also takes data tracking into a new space by providing student engagement metrics and identifying successful and unsuccessful learning content and initiatives,” says Saugata Das, Offering Leader, Cloud Business Solutions, Personalised Learning Solutions, IBM.
“Given the technology advancement, every bit of data can be captured and stored. The cost of capturing, processing and analysing data has come down significantly. For instance, now there are schools that store the classes conducted by experts,” says Gupta of Accenture.
Social media analytics is another area of importance. The groups that the educational institute may have on social media platforms like Facebook, Twitter, etc., can be used to deliver meaningful insights on the learning styles, behaviour and preferences. Video channels like edX, Coursera and even YouTube can be an important resources for generating students related data.
“When a student watches a video, the data on which videos he watched, for how long, how many times the video was paused, after how much time did the student dropped off, can be captured. Even the data on the order in which different videos were watched can be captured. The comments and questions posted by students can also be captured and analysed. The e-learning tests can also be captured to develop insights on what questions the students skipped and on what questions the student spent lot of time,” says Dixit of Persistent Systems.
Trends in Analytics for Education
The interest in analytics is fuelled partially by the constant innovation that is happening in this area. Today there exist tools that allow the institutions to build ever-stronger links between data, teaching and learning and to maintain a focus on developing the skills and knowledge that we value as a society. The technological tools for e-learning, real time data capture, storage and analysis has been maturing. The adoption of technologies such as text analytics, sentiment analytics and statistical analysis for pattern mining is also on the rise.
“Learning analytics is in many ways applying Big Data to education. It can be used in isolation or in combination with web analytics, artificial intelligence, data mining, social network analysis or traditional statistical techniques,” says Gupta of Accenture. Organisations have been using recommender systems, instant skill assessment tools, social network analysis, personalisation, adaptive content and data visualisation for advanced data analytics.
“Educational data mining combined with Natural Language Processing (NLP), statistical analysis and modelling techniques such as predictive, prescriptive or text can help predict patterns. Machine learning and social network analysis is also an integral part of the analytics being performed,” says Das of IBM. There is a proliferation of digital content pushing learning beyond classrooms. This is giving rise to a large amount of structured and unstructured data which can be positively harnessed to improve learning.
IBM offers an education programme called ‘Career Education for Business Transformation (CEBT)’. “CEBT is aimed at developing skilled professionals who can engineer better outcome in different industries so as to transform business for the modern era,” says Das.
The platform developed by Persistent Systems is called ‘ShareInsights.org’. This platform is free for use by educational institutions provided that they follow certain terms of usage.“Going beyond just creating awareness on data analytics, we have taken a step ahead to address this issue by setting up Persistent Computing Institute to provide new thinking in Computer Science education in India,” claims Dixit.
SAS India conducts regular monthly webinars for academic institutes. Partners, consultants are often invited to deliver guest lectures, host discussion sessions and meetings with schools at several levels ensuring the spread and reach of analytics across the nation. The company offers joint programmes on analytics with leading schools in India such as Indian School of Business (IBS), Hyderabad; Indian Institute of Management (IIM), Bangalore; Indian Institute of Management (IIM), Lucknow.
Accenture India practitioners have been guest faculty at a number of educational institutes. While EMC has been running a successful initiative called EMC Academic Alliance to engage and educate the management of educational institutions, train the faculty and help them skill the students. The students are also able to have free assessment and credentials, which they can populate on their resume.
Awareness, Privacy, Funding
Several challenges have to be overcome for enabling the institutions to take advantage of analytics. The challenges include: the lack of awareness about the benefits that can be accrued from analytics; the absence of a culture that can enable data-driven decision making; and the absence of a promoter or leader who is motivated to get analytics implemented within the institution. Issues like lack of clarity on privacy related issues, and the paucity of funding, is also a cause for concern.
“Privacy is a major issue, organisations need to have the necessary measures in place to ensure that privacy is preserved,” says Deepak Ghodke, Country Manager, Tableau, India. Similar views are being expressed by Raj Mruthyunjayappa, Managing Director, Campus Management. He says “Privacy is an important area of concern. The onus is on campuses to inform students and other stakeholders on the nature of data being collected and where the data would be used and seek their consent before collecting data.”
Other key challenge is low awareness about data analytics use in education. Experts say that one of the foremost ways of addressing this is to increase the collaborative effort between educational institutions and data analytics companies. Creating a curriculum through this methodology will be more effective.
On the challenge of ensuring the availability of limited funding for educational institutes, Kagalwalla says, “Gone are the days when analytics was a tool in the hands of a select few. Innovations such as the cloud and affordable technologies such as Hadoop have helped in democratising analytics and making it available to more consumers at lower cost. So educational institutions that may find the infrastructure for analytics expensive, can definitely explore these options.”
The industry players are optimistic that in due course of time all these challenges will be overcome and institutions will be able to take maximum benefit from analytics. “We are very optimistic that analytics will see a high growth. While specific numbers for analytics in education sector are not available, there is definitely a large opportunity that lies ahead,” says Kagalwalla of SAS India.
