6533b7d7fe1ef96bd126837a

RESEARCH PRODUCT

Integrating Computational Linguistic Analysis of Multilingual Learning Data and Educational Measurement Approaches to Explore Learning in Higher Education

subject

description

This chapter develops a computational linguistic model for analyzing and comparing multilingual data as well as its application to a large body of standardized assessment data from higher education. The approach employs both an automatic and a manual annotation of the data on several linguistic layers (including parts of speech, text structure and content). Quantitative features of the textual data are explored that are related to both the students’ (domain-specific knowledge) test results and their level of academic experience. The respective analysis involves statistics of distance correlation, text categorization with respect to text types (questions and response options) as well as languages (English and German), and network analysis to assess dependencies between features. The correlation between correct test results of students and linguistic features of the verbal presentations of tests indicate to what extent language influences higher education test performance. It has also been found that this influence relates to specialized language. Thus, this integrative modeling approach contributes a test basis for a large-scale analysis of learning data and points to a number of subsequent, more detailed research questions.