Profiling – update and a few reflections

Right now the first prototype of the profiler agent has been implemented. This prototype clusters all Moodle users depending on different activities that they done/not done on the Moodle server. So, for example, it will analyse all comments made within a specific course. The analysis involves clustering the users into categories from the least active “comment’ers” to the most active, within the specific course.

There are 22 different course specific activities that are clustered and 1 non-course specific activity.

After analysing these the system then performs 3 overall analyses. One that clusters the users depending on their activity levels in all of the course specific activities, and another that clusters on the activities coming from the log, the comments made, forum discussion participation and general posts. The last one clusters users on the actual marks they have achieved.

Below is a table of the different activities that are analysed with a description.

[table id=2 /]

(Updated 09/04/2013)

Reflecting upon the results the the system has produced on the training data there are a few issues or questions.

Here we are performing data mining on a separate training set than the real data. That is analogous to asking a blind man to be a goal keeper in football. Yes, he might be able to hear the shot and therefore estimate where the ball is going, but he cannot see the ball, and therefore might miss it. The system has been tested on two different Moodle installations, but there is no way of finding out if the results produced will be meaningful in the actual pilots. Then it could (and perhaps should) be argued that this is excatly why pilots are necessary. It is definitely expected that changes are needed after the pilots has run. Perhaps even throughout the pilots.

It is also clear that there are big differences between how Moodle is used by teachers. This will have an impact on the importance of different activities. The system is at the moment not changeable by teachers. A question is if it would make sense to create a profiler that would have such a feature?

A more practical problem is when the profiler should be started in a course. Obviously activities build up over time. It does not make sense to start it on day 0, because all students will look like they aren’t active. Perhaps the log activity or the users last access are more interesting in the beginning of a course. Just to give an indication of early activity. However this probably should not be used by any active alerter agent.

Any thoughts on these reflection?


Call for papers

Call for papers for the 16th International Conference on Artificial Intelligence in Education (AIED2013) now open

The 16th International Conference on Artificial Intelligence in Education (AIED2013) is the next in a longstanding series of biennial international conferences for high quality research in intelligent systems and cognitive science for educational computing applications. The conference provides opportunities for the cross-fertilization of approaches, techniques and ideas from the many fields that comprise AIED, including computer science, cognitive and learning sciences, education, game design, psychology, sociology, linguistics, as well as many domain-specific areas. Since the first AIED meeting 30 years ago, both the breadth of the research and the reach of the technologies have expanded in dramatic ways. The theme of AIED2013 therefore seeks to capture this evolution: From education to lifelong learning: constructing pervasive and enduring environments for learning. In line with this theme of expansion, AIED2013 will welcome the Industry& Innovation Track which seeks to capture the challenges, solutions, and results from the transition of AIED technologies into the commercial sector.


Call for papers

Call for papers for the 6th International Conference on Educational Data Mining (EDM 2013) now open
EDM 2013 invites papers that study how to apply data mining to analyze data generated by various information systems supporting learning or education (in schools, colleges, universities, and other academic or professional learning institutions providing traditional and modern forms and means of teaching, as well as informal learning). EDM may require adaptation of existing or development of new approaches that build upon techniques from a combination of areas, including but not limited to statistics, psychometrics, machine learning, information retrieval, recommender systems and scientific computing.


Where are all the Intelligent Tutors?

Beverly Woolf asks in the last section of her book Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning” a very intriguing question. A question which relates to why a project like I-TUTOR is needed.

She asks, after having described methods for creating intelligent tutors, why there really aren’t many of them in existence? The impact of these could after all be huge, and there ought to be a repository somewhere with various different tutor systems.

Beverly answers this herself. These systems requires a lot of man hours to develop, often ~200 hours of development for 1 hours of tutorial. Therefore few are developed and even fewer are shared.

One could now ask: Why does the I-TUTOR project dare to work on this area?

Well, granted it might seem like a big task, but, there is one main difference. This project is not working on any content based tutorial. We are not making tutorial about Chemistry, Programming or Linguistics. We are investigating the possibilities of create intelligent tutor support by looking at meta-learning. How a student performs in a module is very likely correlated to certain ways that the students interacts with the VLE, for instance frequency of usage, posts made, forum questions etc. This is a different level of information, which can be made inferences on at a different level than what you do when you create a bespoke tutorial for a specific module. A different level, which potentially will be transferable between subjects, institutions and nationalities.


Call for Experts

In order to ensure quality control on project aspects and outcomes in relation to Technology Enhanced Learning (TEL) and as part of the overall evaluation and quality assurance measures a review panel composed by 3 reputed experts will be established, covering the three domains of the project: pedagogy, computer science and EU policies in the field of Technology Enhanced Learning.

I-TUTOR Call for Experts

The experts will review and evaluate the project with respect to the design, the techniques to be applied, the development stages, the outcomes, and the best practices. As a consequence they will exploit their respective expertise in the fields of

  • Pedagogy, and in particular:
    • Instructional design
    • Tutoring issues
  • Computer science, and in particular:
    • Design and development of web based software architectures
    • Agent based software
    • Knowledge engineering and management
    • Data mining for educational purposes
    • NLP
    • Automated reasoning
    • HCI and user profiling
  • EU policies in the field of Technology Enhanced Learning.

For the description of the tasks, the application and the remuneration details please, check out the call for experts.

The dead-line for the applications is 12 September 2012!


We are Online!

Dear Visitor,

on behalf of the I-TUTOR Team I would like to welcome you in our project’s website!

The I-TUTOR (Intelligent Tutoring for Lifelong Learning) project started in January 2012 with the aim of developing a multi-agent based intelligent system to support online teachers, trainers, tutors and students.

The aimed intelligent tutoring system, to be applied in open source learning environments, able to monitor, track, analyses and give formative assessment and feedback loop to students within the learning environment and also give inputs to tutors and teachers involved in distance learning to better their role during the process of learning.

Our work during the project includes literature and case reviews of the educational use of artificial intelligence, the design and development of the intelligent tutoring tool, and the training of tutors in order for them to pilot the tool.

At the end of the project in December 2013, a piloted and reviewed intelligent tutoring system will be available. This tool is potentially implementable in all open source platforms.

We are inviting you to follow our work! We will be posting all results and resources here on our website as well as opportunities for you to join us in our work.


Hallo World!

Using a ‘Hallo World’ statement is how I normally start learning new computer languages and environments, so I thought it was appropriate to start the first introduction – mostly aimed at project partners – here this way.

What you see here is the project website. There are still a few things that need some information. Especially the logos on the partner page, and research results that we already have achieved.

But we’ll get that sorted out soon.

If you want (and think you deserve) direct access to the editing facilities then contact me (Karsten).

I hope you like the layout. I / We (got constructive feedback from Gigliola and Eva throughout) have aimed at a very simple layout using the colours from the logo. I hope you like it.

WordPress theme: Kippis 1.15