Shili Ge
School of English for International Business, Guangdong University of Foreign Studies, Guangzhou, China
ABSTRACT
In order to determine the joint effect of two methods, multiple regression and text categorization, in Automated Essay Scoring (AES) of English writing by Chinese college students, a joint model involving both methods is constructed, applied and evaluated. A corpus of college English writing containing 660 compositions is used as the subject and it is further divided into the training set and testing set. First, a multiple regression model is constructed and testing set compositions are automated scored as the baseline for this research. Then, a joint model of multiple regression and text categorization is constructed mainly using phrasal features. At last, final results are achieved and evaluated. The experimental results show that with the help of the joint model, all indexes including precision, recall, total accuracy and total wrong ratio of the AES model are improved. Though this model cannot be applied into practical use yet, it lays a solid foundation for further research in AES field.
PDF References Citation
How to cite this article
Shili Ge, 2013. Combination of Multiple Regressoion and Text Categorization in Automated Essay Scoring of College English Writing. Information Technology Journal, 12: 7977-7982.
DOI: 10.3923/itj.2013.7977.7982
URL: https://scialert.net/abstract/?doi=itj.2013.7977.7982
DOI: 10.3923/itj.2013.7977.7982
URL: https://scialert.net/abstract/?doi=itj.2013.7977.7982
REFERENCES
- Enright, M.K. and T. Quinlan, 2010. Complementing human judgment of essays written by English language learners with e-rater scoring. Language Test., 27: 317-334.
CrossRef - Laufer, B. and P. Nation, 1995. Vocabulary size and use: Lexical richness in L2 written production. Applied linguistics, 16: 307-322.
CrossRef - Li, Y. and S. Ge, 2008. The validity of word list in automated essay scoring for college students. Foreign Languages Their Teach., 10: 48-52.
Direct Link - Xu, B., X. Guo, Y. Ye and J. Cheng, 2012. An improved random forest classifier for text categorization. J. Comput., 7: 2913-2920.
Direct Link - Zhang, Q.Y., P. Wang and H.J. Yang, 2012. Applications of text clustering based on semantic body for Chinese spam filtering. J. Comput., 7: 2612-2616.
CrossRef