Direkt zum InhaltDirekt zur SucheDirekt zur Navigation
▼ Zielgruppen ▼

Humboldt-Universität zu Berlin - Faculty of Language, Literature and Humanities - Corpus Linguistics and Morphology

Overview

Overview of the KOMPOST project
Working title

Kom­post ― I­den­ti­fi­ca­tion of in­di­ca­tors for com­pe­tence as­sess­ment of stu­dents’ es­says and de­vel­op­ment of a pro­to­type for com­put­er-as­sist­ed text a­nal­y­sis


Description

Using methods from computational linguistics, this project will identify indicators of the quality of students’ texts in the German language. Special emphasis will be placed on the evolution of those quality indicators across competence levels, i.e. the development of observable parameter values over time as the students’ language skills improve. The study will be based on essays, test results, students’ attitudes and personal information from the city of Hamburg’s longitudinal KESS study, as well as material from other surveys. The core of this dataset is comprised of approximately 9000 essays which were rated along several dimensions.

Language test results from the same pupils serve as an external criterion for the validation of the ratings and will also be related to the indicators in order to detect additional oblique patterns which a less objective and reliable human reader would be unable to find.

The research on the competence indicators will form the basis for the development of an online tool for the automated assessment of text quality. The tool will be created in close consultation with students and teachers and will provide the users with feedback in an easily accessible format. Furthermore, the results of the automated text analysis will be used in turn to inform the continued development of competence models.


Duration

01.11.2009 - 31.10.2012


Staff

Anke Lüdeling, Jasmine Bennöhr, Burkhard Dietterle
To the page with more detailed information


Results

To the overview of posters and talks


Funded by

BMBF