Open AccessAuto-analysis of writing database based on corpus model
Author(s) -
Aiqin Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1941/1/012050
Subject(s) - computer science , class (philosophy) , reflection (computer programming) , word (group theory) , natural language processing , corpus linguistics , artificial intelligence , mathematics education , database , linguistics , psychology , programming language , philosophy
The paper presents corpus-based writing database analysis and its application to college English writing classes. A small writing database was built by collecting 88 students’ 264 writing samples in one semester. Corpus model was used in the research for analysing connector using, cluster score and word frequency. The contrastive connector analysis reveals the difference between the collected samples and the existing Corpus SWECCL. The cluster and word frequency analysis introduces a new approach to analyse writing samples. The paper also details some classroom activities designed from research findings. Students’ in-class performance and after-class feedback both indicate that they are interested in the analysis-based classroom activities. At the beginning and the end of the semester, the study collected students’ English writing scores in the tests and adopted SPSS to assess their achievements. The paper ends with a short reflection on the enlightenments and limitations of the research.