Development Of Error Analysis

DEVELOPMENT OF ERROR ANALYSIS MARKING TOOL FOR MARKING ESL WRITING AT IHLS 01-01-02-SF0092

Prof. Madya Dr. Saadiyah Darus Dr. Nazlia Omar Dr. Tg Nor Rizan Tg Maasum Prof. Madya Dr. Siti Hamin Stapa Dr. Mohd Juzaiddin Abdul Aziz

ABSTRACT

Writing in a second language is not an easy task. Research have shown that ESL learners write differently from native English speakers (NES). Errors in second language (L2) are an important construct that is central to L2 writing. Written errors made by adult L2 learners are often quite different from those made by NES. Marking essays written by L2 learners could be an overwhelming task and time consuming for lecturers especially when classes become larger. Larger classes reduce opportunities for learners’ feedback on written work and learners in turn may have little contact with their lecturers. With the development of automated essay marking systems, opportunities for learners’ essay feedback could be increased and their writing quality improved. 400 essays written by undergraduate students who enrolled in Written Communication course at the School of Language Studies and Linguistic, Faculty of Social Sciences and Humanities, Universiti Kebangsaan Malaysia were analysed using Markin 3.1. This poster illustrates an approach for developing an automated marking tool for tenses in English as second language (ESL) and introduces heuristics and rule-based approach to detect grammatical errors in tenses. Based on the observation of English sentence structure and grammar, the

formation of heuristics can be further developed to improve the accuracy of the result. For future work, weights may be assigned to each of the heuristics in order to support the level of confidence of each of the heuristics. The results show that heuristics and rulebased approach is useful and can improve the effectiveness of automated essay marking tool for writing in ESL. The next step is the development of algorithm based on the heuristics and rule-based approach for detecting errors in learners’ essays. Based on these algorithms, the automated marking tool will be developed.