Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sections
Personal tools
You are here: Home Theses Measuring coherence accross media in learning environments

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

Measuring coherence accross media in learning environments

Thesis type
  • Master
Status Open
Supervisor(s)

Multimedia content based indexing delivered a lot of models for the analysis of multimedia materials. In modern educational platforms, e.g. MOOCs and self-regulated learning platforms. In consequence, multimedia materials are produced by educational designers but also by the learners during their learning processes. Coherence is a semantic measure for the local and global connectivity of e.g. sentences, paragraphs, videos, slides among others. Computer linguistics has provided impressive results for measuring the quality of writing, e.g. for automatic essay scoring. To measure the coherence of multimedia materials many computational methods reaching from natural language processing to machine learning needs to be combined in a common coherence model. Goal of this master thesis is to co-develop a coherence model for cross-media coherence and to prototypically combine these computational methods for a webinar.

Multimedia content based indexing delivered a lot of models for the analysis of multimedia materials. In modern educational platforms, e.g. MOOCs and self-regulated learning platforms. In consequence, multimedia materials are produced by educational designers but also by the learners during their learning processes. Coherence is a semantic measure for the local and global connectivity of e.g. sentences, paragraphs, videos, slides among others. Computer linguistics has provided impressive results for measuring the quality of writing, e.g. for automatic essay scoring. To measure the coherence of multimedia materials many computational methods reaching from natural language processing to machine learning needs to be combined in a common coherence model. Goal of this master thesis is to co-develop a coherence model for cross-media coherence and to prototypically combine these computational methods for a webinar.

Related projects

Document Actions