Members of the IBM Watson Conversation Team visited Bolton College to view Ada - Bolton College's digital assistant for students, teachers and support teams. Students from the College's second year HND Computing programme have been involved in teaching Ada how to respond to questions from fellow students. The project has given them the opportunity to explore natural language processing and the world of digital assistants.
The advent of natural language processing and natural language generation services within the education sector is set to address a number of everyday problems and challenges that are encountered by teachers, support teams and administrators in schools, colleges and universities. In this short article I would like to examine how these services will support the production and distribution of the online student report card.
One of the most interesting aspects about developing a digital assistant for students and teachers has been the potential for the service to support and enhance teaching, learning and assessment. The learning technology team at Bolton College has conducted research to enable the delivery of the following services through Ada:
the ability to deliver personalised, contextualised, differentiated and adaptive learning and assessment materials to each student;
the ability to utilise particular elements of the student dataset to deliver personalised learning to each student. Ada's responses to student questions can be informed by multiple variables such as the academic level of the student, the current performance of the student on the course, student assessment data, the vocational setting of the student, the goals and targets associated with each student and more.
This represents a significant milestone for the ILT team because it means that teachers across Bolton College can offer differentiated and adaptive teaching, learning and assessment materials to the student via Ada as well as Moodle, the College's virtual learning environment.
If we regard schools, colleges and universities as institutions that process information, the management of data represents the first step in many that enables these institutions to deliver education services to their local and wider communities. They start by distilling data into information, information into knowledge, knowledge into wisdom, and wisdom into actions. However, as the volume of data rises within a school, college or university it becomes increasingly difficult for teachers, student support teams and admin teams to convert data into information, knowledge, wisdom and actions which enable them to support the myriad of students in their respective institutions. In this short article I would like to detail the use of oracles and machine learning agents which could help schools, colleges and universities to capitalise on student data.
Bolton College's ILT Team is pleased to announce that Ada, the College's digital assistant for students went live on the 6th of April. Ada has been taught to answer general questions and enquiries about Bolton College and she is able to answer specific questions relating to the student who is making the enquiry.
The service marks a significant milestone in the way students at Bolton College will come to engage with College services.
The College's ILT Team is examining how Ada could support teachers and students in the classroom. As we converse with Ada we are discovering that her place in the classroom presents colleagues at Bolton College with a number of exciting opportunities to enhance teaching, learning and assessment.
The Information Learning Technology (ILT) Team at Bolton College has successfully deployed a number of digital assistants to support the delivery of learning and assessment materials to students. The use of these digital assistants has enabled the personalisation of teaching, learning and assessment at scale. Digital assistants can also be designed and deployed to enhance a range of other services that are used by students and colleagues. One of the projects that the College's ILT Team is currently working on involves the use of a digital assistant called Ada who is being taught how to respond to a wide range of student enquiries across multiple contexts.
The use of machine learning within the education sector provides schools, colleges and universities with multiple opportunities to enhance and transform the heart of their services such as teaching, learning, assessment and student support.
This article seeks to expand on my previous notes on machine learning by providing a number of user case scenarios for each of the machine learning agents that could be employed by institutions on their personal learning environments.
Machine learning offers schools, colleges, universities and the companies who provide digital services to the education sector with an opportunity to improve personalised and contextualised learning to students. In this article I will explore how machine learning can enhance the management of differentiated and adaptive learning; and the management of the student life cycle. I will also examine some of the challenges that arise from the use of machine learning.
The ILT Team at Bolton College can now offer differentiated learning and assessment materials to students according to their learning support needs. In one recent example colleagues in the Careers and Learning Support Teams worked together to produce on an online tutorial which offered advice to students about applying for jobs and preparing for a job interview. The teams wanted to produce content that reflected the learning support need of the student viewing the content.
The use of agents is making personal learning environments smarter as they advance the delivery of personalised and contextualised services to students. In this article I identify a number of these agents and the roles that they play within a personal learning environment.
Within the context of personal learning environments, agents can be described as programs that observe student and teacher behaviour within the learning environment. They carry out data mining activities which enable them to extract meaning and knowledge from the large datasets that are to found in a modern education setting. The agents then direct or combine their activities to satisfy the needs of students, teachers and support teams.
This short article details the four constituent parts that make up Bolton College's Adaptive Learning Environment.
Moodle is Bolton College's Virtual Learning Environment. The research that the College's ILT Team has undertaken has enabled Moodle to deliver adaptive content and assessment activities to each student. The solution means that there is no need to purchase a license for a third party adaptive learning environment. We are planning to undertake additional research which will allow us to explore the delivery of adaptive content and assessment activities in other virtual learning environments.
Adobe Captivate is the eLearning authoring tool which is used to create our adaptive online tutorials. Each tutorial includes a bespoke set of queries that are presented to our Digital Engine. The algorithms within each tutorial use the query results to deliver differentiated and adaptive content and assessment activities to each student.
Student Datasets are made up of the College's core student dataset (Tribal EBS), the College's Learner Journey Management System and the student profile. At the present moment in time the ILT Team's adaptive learning project queries and analyses the data on its current student cohort. As the project progresses colleagues across Bolton College will data mine a much larger historical dataset which will deliver further improvements to our adaptive services.
The Digital Engine reads, mines and applies updates to the wider student dataset. The present choice of name for the Digital Engine is deliberate because it reflects its current ability to behave and act autonomously. At the present moment in time the Digital Engine relies heavily on teachers and instructional designers to shape and inform its behaviour and the decisions that it makes. Over time, the Digital Engine will gradually evolve into a virtual machine which will have the ability to behave in a more autonomous fashion. That is to say that it will define, test and apply changes to its hypotheses in order to deliver improved adaptive tutorials and assessment activities to each student.
Adaptive learning environments are representative of a new breed of digital services that have emerged within the education sector over the last decade. They have come about because they take advantage of data and the technologies that support data management. The growing use of machine learning and natural language processing will further escalate the development and use of adaptive learning environments within the education sector. The use of these new artefacts will bring about many benefits to students, teachers and educational leaders; but it must be noted that the introduction of adaptive learning environments will also pose many challenges to all stakeholders within the sector. This article seeks to explore (through various scenarios) the use of adaptive learning environments, the benefits that can be derived from them and the challenges that arise from their use.
The ILT Team at Bolton College is currently researching how the College's adaptive learning environment could be used to improve the delivery of online tutorials and assessment activities to each of our students.
Bolton College's adaptive learning environment is proving to be very versatile. One recent success has focused on the platform's ability to use target setting information to differentiate content and assessment activities on Moodle, the College's virtual learning environment. When a teacher and a student agree on a learning target, the tutorial (or SCORM package) that is presented to the student on Moodle reflects that new target.
The advent of the adaptive learning environment is a welcomed addition to the distributive learning landscape because it provides teachers with additional tools to deliver personalised and contextualised teaching, learning and assessment activities to each of their students. The use of machine learning in adaptive learning environments is the most significant development in distributive learning because it marks the time when a new agent is introduced into the classroom. That new agent is the adaptive learning environment which quietly queries and analyses vast quantities of data before it autonomously determines the tutorials and assessment activities to present to a given student. Further progress has yet to be made before adaptive learning environments become common place in our schools, colleges and universities; but the progress that is currently being made with analytics, machine learning, content creation, machine marking and natural language bodes well for the future.
The ILT Team at Bolton College has recently updated the College's adaptive learning environment so that content and assessment activities within an online tutorial follow the learning preferences of students.
In this short article I would like to take the opportunity to explore some of the opportunities and challenges facing the education sector with the emergence of the adaptive learning environment.
At the present moment in time adaptive learning environments take advantage of supervised machine learning techniques to deliver content and assessment activities that are personalised and contextualised to meet the needs of each student. In supervised machine learning teachers define the desired set of outcomes that are expected from an adaptive online tutorial and they also provide regular feedback to the adaptive learning environment which enables it to adjust the paths that it takes to reach a teacher's desired outcomes.
The ILT Team at Bolton College has authored SCORM content that is gender specific on its Moodle Adaptive Learning Environment. One of the recent tutorials that has been completed provides advice and guidance about dressing for job interviews. The tutorial is part of Bolton College's Level 2 employability course. The content is gender specific so the College's male and female students receive content that is specific to them. The adaptive learning environment also adapts content that meets the needs and requirements of transgender students and their preferred gender identify that is registered on the College's information management system.
Teachers and student support teams at Bolton College are working with the College's ILT Team to introduce a Virtual Digital Assistant into the classroom to support the delivery of the College's new employability unit.
The employability unit will be delivered to over a 1,000 Level 2 students across all academic departments at the College. Teachers and support teams will continue to develop, author and distribute teaching, learning and assessment material via the classroom and via Moodle, Bolton College's Virtual Learning Environment; but in 2016-17, colleagues will be supported by the College's new Virtual Digital Assistant (VDA).
Put simply, the VDA is a suite of algorithms which query the student dataset to determine the most suitable teaching, learning and assessment material to present to each student on Moodle. The dataset includes variables such as student name, the student's unique ID, department name, course title, gender, entry qualifications for Maths and English, diagnostic test results, on-going assessment data, intended destinations and more.
The adaptive assessment solution at Bolton College operates on mutiple levels. These are summarised as follows:
Adaptive assessment based on entry qualifications to a course: This is particularly useful when conducting diagnostic tests at the start of a course. The test that is presented to the student is based on the student's entry qualifications to the course such as a GCSE English or a GCSE Maths grade. The test adapts as the student progresses through the test.
Adaptive assessment based on answers during a test: As each student progresses through an online test the questions presented to the student adapt to his or her responses. For example, if a student demonstrates that he or she can correctly answer questions at a particular level he or she will be subsequently presented with questions of a higher level. The reverse applies if a student struggles to correctly answer questions at a given level.
Adaptive assessment based on previous assessment activities in Moodle: Students at Bolton College are regularly asked to complete online tests on their Moodle courses. The results of previous tests are used to inform subsequent online tests taken by each student. Moodle and the scorm packages that make up the online tests are able to instantaneously query the student, his or her unique ID, course title and previous assessment scores before presenting the most appropriate content to each student.
Adaptive assessment based on course title: Occasionally students at Bolton College will undertake online tutorials that are also undertaken by other students across the College. The adaptive learning and adaptive assessment solution at Bolton College enables vocationally specific content slides and assessment activities to be presented to each student. This means that cross Colleges online tutorials on health and safety, induction or employability can be tailoured to suit the vocational interest of each student.