Learning Support Agents


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.

What are agents?
Within the context of personal learning environments, agents can be described as programs that observe the behaviour of students, teachers and support teams within the learning environment; and 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.

Academic Agents
The following academic agents enable teachers, teaching assistants and learning support teams to support students as they progress with their studies.

  1. Instructional Design Agent - this agent reviews a student's profile and compiles instructional and assessment materials on a given topic on the course. The agent uses a wide ranging dataset on the student such the academic level of the course being studied, grades scored thus far on the course, predicted grades, targets, gender, learning support needs and more. The use of the instructional design agent enables the student to receive timely, personalised and contextualised learning and assessment materials. The design of the adaptive learning environment enables the instructional design agent to deliver learning and assessment materials to students with or without the input of the teacher.
  2. Assessment Agent - this agent monitors coursework grades, initial diagnostic test results, interim test results, end of unit test results, qualifications at the start of the course, exam dates and more to compile assessment materials before presenting them to each student on the personal learning environment. The agent can utilise information such as actual grades, target grades and predicted grades to help it compile appropriate tests before presenting them to the student. The agent is designed to support and prepare students for formal exams and tests and to maximise the grades achieved by students. Like all other agents that are utilised by the personal learning environment, the assessment agent will not act in isolation. For instance, it will exchange information to and from other agents to inform its behaviour and to inform the behaviour of other agents. In the following example a student needs to achieve a distinction grade on her current course in order to meet the entry requirements for her chosen university. If the student is performing at a level below a distinction grade average the instructional design and assessment agents will work in unison to deliver learning and assessment materials that will support the student to gain the desired distinction grade.
  3. Academic Support Agents - this group of agents review a wide variety of datasets and knowledge sources on any given student and act in a manner that reflects the overall profile of the student. As mentioned earlier, if a student is falling short of achieving the grades required to get into university the academic support agent can adapt tutorials and assessment materials on the course that will support the student to achieve a higher a grade profile on his or her course. The agent can also prompt the student to schedule an appointment to see the course tutor or the agent may schedule the appointment on behalf of the student and tutor. The agent will also monitor if students are failing to communicate on a regular basis with their teachers. The reason for monitoring the communication channels between students and teachers is to identify those students who are at risk of not succeeding on their courses. Algorithms make use of the hypothesis that those students who not communicate regularly with teachers are more likely to withdraw from the studies or they may not succeed in getting their desired grades on the course. The agent can also monitor what is being communicated between student and teacher; and act accordingly. This facet of the academic support agent is discussed further in this article.
  4. Learning Agents

  5. Library Agent - this agent reviews the schedule of classes that a student is timetabled for. The agent references the topic of each class or tutorial, the reading list associated with the class or module and the topics associated with the coursework or assignment currently being undertaken by the student. The library agent will then correlate this information with the catalogue of books, journals and online resources that are indexed in the library management system that is licensed to the school, college or university. As students login into their personal learning environment they will be presented with timely and contextualised resources, suggested articles to read and even the availability of books or journals that can be loaned out to them.
  6. Timetabling, Calendar and Booking Agent - this agent provides timely and contextualised prompts and notifications to students regarding the start and end of the academic term, assignment or coursework hand-in-dates, the time and room of their next one-to-one tutorial, their next appointment with the finance office, the campus nurse, the appointment with the student support team, due dates for library book loans and any events on or off the campus. The agent can also go beyond providing simple prompts and notifications to the student. For example, the agent will gather information from other agents within the personal learning environment and offer available meeting slots with the tutor if it identifies that the student is falling behind with his or her work. The agent may schedule an appointment between the academic support team and the student if it is notified by other agents within the personal learning environment that the student is struggling to achieve his or her desired grade for any given unit or module on the course.

Course Management Agents
The following agents help course teams to effectively manage their cohort of students, teachers and the resources that are required to support the course.

  1. Students at Risk Agent - this agent identifies students who are at risk of dropping out of their courses, falling short of predicted grades or those students who will not satisfactorily complete the entire programme of study. As the volume of student data rises course teams are finding it increasingly difficult to draw a satisfactory profile for each of their students. In recent years the use of learning analytics and business intelligence tools within the education sector has helped teachers to draw up a health check of each student in their care; but further progress could still be made in this field. For instance, by profiling applicants to a course, the risk agent can identify the applicants who are likely to be successful or not on the course. In the instance were the risk agent has highlighted a potential 'at risk student' and where the course team has or is about to decline an offer of a place on the course, the marketing or student recruitment agent may suggest other courses that are more suitable to the student.
  2. Attendance Management Agent - this agent monitors the attendance pattern of students across the school, college or university. The agent informs the decisions made by the risk agent and the student support agent within the personal learning environment. The attendance management agent may identify underlying patterns of attendance and correlate these with the performance of individual teachers, the schedule of classes, the performance of students in classes and even the learning preferences exhibited by students during certain times of the week or year. If the dataset that is utilised by the attendance management agent is wide it could even suggest earlier bus times if the student is arriving late for classes. The agent could even take advantage of the GPS technology in a student's mobile device and notify the teacher that the student is running late but is on the way to class.

Other Agents
The use of agents will not be limited to the management of teaching, learning and assessment. For example, the Marketing and Recruitment Agent can suggest and make course recommendations to potential applicants to a college or university. The work of this agent is made easier if the applicant has completed an online registration process which has allowed it to gather valuable information about the applicant. Over time, as tens of thousands of students enter the college or university, the marketing and recruitment agent becomes more informed when it recommends courses to applicants. As the agent's work improves, there will be numerous positive knock on effects to courses and to the wider institution. For instance, less students will drop out of courses and there will be less student transfers between courses at the start of the first semester. The Human Resource Agent can be used to for multiple purposes such as connecting colleagues who are working on similar projects or interests, matching teachers to courses, workforce development, performance management, managing absence and more.

Further developments in agents
As mentioned earlier in this article the academic support agents can monitor what is being discussed between students and teachers. As the use of natural language improves within personal learning environments the communication agent will be able to identify phrases such as suggest:

  • I want to leave the course;
  • I am not happy on the course;
  • I would like to go to university;
  • I am struggling with this assignment and need help;
  • I can't find resources to support me to do this assignment;
  • I would like to progress onto further studies after I have completed this course; or
  • I am running out of money to finance my studies.

Students, parents, teachers and support teams may accept the use of the agent to act in this manner; but what about in the case of the following scenarios?

  • My parents have divorced and I have left home. I have staying in temporary accommodation;
  • I have mental illness and its affecting my ability to focus on my studies; or
  • I am self-harming.

The ethics of monitoring the dialogue between students and teachers and support teams may sound contentious but schools, colleges and universities have always utilised this information to put together services for students requiring additional support and guidance. In the past the source of information would have been via email, letter, hand written notes, voice-mails, phone calls, text messages or face-to-face conversations. The development, management and use of the communication agent to inform the actions of the academic support agent needs to be carefully considered because words and phrases could easily be mis-interpreted or put out of context. For instance, a student may communicate the following message to his or her tutor: "My parents have divorced and I have had an almighty row with them both. I left home and I am basically homeless. My grandparents have been great and they said that I could stay with them." The support agent and the communication agent may not correctly interpret the nuances in this communication and incorrectly conclude that the student is now homeless; and act accordingly. Over time the development of natural language processing will mitigate these concerns; but at the present moment in time, the use of agents in this manner is still problematic.

The use of agents blurs the rigid software boundaries between the traditional virtual learning environment, the learner management system, an institution's pool of information systems, library management systems, communication and news channels, the student home page and the personal learning environment. The boundaries will also be blurred with regard to the agents themselves; particularly when students and teachers will not be able to distinguish the work of individual agents. The interdependency of agents will also mean that agents will be increasingly reliant on each other to fulfill their tasks.

The advent of agents and machine learning within the education sector marks the start of an exciting period where technology companies in partnership with schools, colleges and universities will take their first steps towards developing a personal digital teacher for every student.