Personalized Learning via Big-Data

Begin Anytime
Supervisor Dr. Julian Kunkel

If you are interested in this topic or similar topics, contact Dr. Julian Kunkel.

Personalized learning promises to aid the practitioner by prescribing suggestions of training that boosts personal strength or weaknesses. Additionally, it may predict the time for conducting a certain training or help to identify deficities. Besides these imminent benefit for student, similar techniques can be applied to assess lecture material and find missing training. We have an online platform to learn the C-Programming language (see: https://oer.hps.vi4io.org), where everyone can autonomously learn. Goal of this work is to develop a concept that harnesses big data for personalized training and to identify lecture deficiencies and to deliver a prototype.

Firstly, a concept is designed that defines which user interaction are relevant and that is able to utilize machine learning techniques to predict time for exercises and prescribes tasks to cope for strength and weaknesses. Secondly, natural language processing techniques are applied to identify related topics of an exercise. Finally, a prototype system is developed, implemented, and evaluated on test data.

While all skills needed to complete this project can be obtained during the time of the project, some skills are beneficial:

  • Basic knowledge about machine learning methods
  • Programming languages:
    • Web-development (HTML/Javascript), Python (intermediate level)
    • C (basic level)

An MSc candidate is expected to bring soft skills (in decreasing order of importance):

  • Communication
  • Problem-Solving
  • Time management
  • Impressum
  • Privacy
  • research/open-theses/msc/personalized-learning.txt
  • Last modified: 2019-02-24 12:20
  • (external edit)