| Bemerkung: |
Description
This project aims to develop a tool that will support students who struggle in online learning courses facilitated by Learning Management Systems (LMSs). To that end, we will follow a two-step approach:
a) identify potentially struggling students using the log files of a Higher Education online course (data will be provided);
b) propose automatic or semi-automatic feedback interventions to support students’ learning.
In order to identify struggling students, we will engineer data-based features (Jiang, et al, 2018) that may indicate - among others - lack of background knowledge, lack of motivation, poor time-planning and self-regulation skills. To design feedback interventions, we will use as a starting point the five levels of verbal and non-verbal interventions that tutors can employ on the learner’s progress (Wood, Wood, & Middlestone, 1978) and the concept of Contingent Tutoring (Wood, 2001).
For this project, we will work in groups of 4 students on a predefined topic (each group will be assigned a different topic). During the first weeks, we will provide an overview of the project, its goals and related theoretical and practical concepts. Then, the groups will work towards three milestones:
a. An initial presentation of their ideas, strategies and workplans to address the project’s topic;
b. A mid-term presentation of the work-progress up to that point
c. A final presentation of the finished project along with a written project report in the form of a scientific article.
If you want to know more about related work, you can find additional information and material at:
www.colaps-project.info
Other info
• During the semester, we will offer bi-weekly meetings and consultation sessions.
• Participation in bi-weekly meetings and consultation sessions is optional, participation in the three milestone events is mandatory.
• This project will take place exclusively online due to the COVID pandemic.
• The working language for this project is English.
• Maximum number of places (students): 20, Registration mode: first come, first served ☺
Target Audience
▪ Komedia Bachelor
▪ Komedia Master
▪ Angewandte Informatik Bachelor
▪ Angewandte Informatik Master
Date and Location
• Monday, 17:00 - 19:00
• Fully Online (real-time webinars, video recordings, group consultation sessions).
• Starts on May, 15th
Prerequisites
• Basic knowledge of data analysis and programming (Python and / or R)
• Interest in data analytics and applied data science
• Imagination (wild)
Instructor
• Irene-Angelica Chounta (www.iachounta.com, iachounta@gmail.com)
References
Wood, D., Wood, H., & Middleton, D. (1978). An experimental evaluation of four face-to-face teaching strategies. International journal of behavioral development, 1(2), 131-147.
Wood, D. (2001). Scaffolding, contingent tutoring, and computer-supported learning. International Journal of Artificial Intelligence in Education, 12(3), 280-293.
Wood, H., & Wood, D. (1999). Help seeking, learning and contingent tutoring. Computers & Education, 33(2-3), 153-169.
Henderson, M., Ajjawi, R., Boud, D., & Molloy, E. (Eds.). (2019). The Impact of Feedback in Higher Education: Improving assessment outcomes for learners. Springer Nature.
Jiang, Y., Bosch, N., Baker, R. S., Paquette, L., Ocumpaugh, J., Andres, J. M. A. L., ... & Biswas, G. (2018, June). Expert feature-engineering vs. deep neural networks: Which is better for sensor-free affect detection?. In International conference on artificial intelligence in education (pp. 198-211). Springer, Cham. |
