Automated assessment of student's assignments is used, e.g., for multiple-choice exams. It is a lot harder for a computer to evaluate essays. The goal of this project is to explore what can – and what cannot – be achieved by natural language processing (NLP) and machine learning.
The project will use material from the KAL-project ”Kvalitetssikring av læringsutbyttet i norsk skriftlig”. The aim of this large project was to evaluate the learning outcomes of written Norwegian for students graduating from the basic school (10th grade). The project collected student's exam essays from a four-year period (1998-2001) and analyzed them both quantitatively and qualitatively. The goal was to investigate what the students do – and do not – master, and to which degree the exam grading reflects this.
The first goal of this master's project is to see to which degree it is possible to predict the grades of the essays using tools from NLP and machine learning. From this, the project may take several directions depending on the student's interests and the initial results of the project, e.g.
- Explore the effect of various levels of computational linguistic analysis, like tagging, parsing, etc.
- Compare different machine learning methods.
- The KAL-project considered various qualitative criteria which should be taken into consideration when assessing and grading the student's essays. To which degree can these criteria be reflected in an automated assessment?
Qualifications
Due to the nature of the material, you should have a native competence of Norwegian and good skills in writing Norwegian.
This project is suitable for one student or for two students who want to collaborate.
References
Wikipedia: Automated essay scoring
KAL: Kvalitetssikring av læringsutbyttet i norsk skriftlig - prosjekt og korpus