本研究旨在探討一線上英文改錯軟體Linggle Write的改錯表現。為回答研究問題，本研究採內容分析法，資料來源為十一篇大考中心公布的英文作文佳作。十一篇佳作在經由Linggle Write修改後，其被偵測的錯誤及改錯內容被歸類於六種錯誤類型（拼字錯誤、標點符號錯誤、詞彙錯誤、文法錯誤、連貫性錯誤，與語用錯誤）與四種改錯表現類型（有效修改、繁冗修改、錯誤修改，與系統錯誤）。

在資料分析後，本研究的主要發現如下：首先，Linggle Write能夠偵測並改正拼字錯誤、標點符號錯誤、詞彙錯誤與文法錯誤，其中以改正文法錯誤表現最佳，約91%的文法錯誤改正為有效修改。第二，Linggle Write目前的些微挑戰為未標記化、無異修改和過嚴修改。雖未臻完美，但Linggle Write 仍是一個能更正拼符階層和文字階層錯誤的有效工具。

This case study aims to investigate the performance of Linggle Write, an English writing correction tool. To address the research questions, this study uses content analysis. Eleven English writings were corrected via Linggle Write for data collection. The corrections were categorized into six error types (misspelling error, mechanic error, lexical error, grammar error, coherence error, and pragmatic error) and four kinds of performances (effective correction, redundant correction, miscorrection, and system bug).

After data analysis, this study identified the following major findings. First, Linggle Write can correct misspelling, mechanic, lexical, and grammar errors. Linggle Write performs best in grammar error corrections. Ninety-one percent of grammar corrections are effective corrections. Second, the minor challenges of Linggle Write are untokenization, identical corrections, and rigorous corrections. Despite these minor shortcomings, Linggle Write is an effective tool to correct errors at substance and text levels.

Chapter 1 Introduction---1
1.1 Background---1
1.2 Significance of the study---8
1.3 Purpose of the study and research questions---9
Chapter 2 Literature Review---12
2.1 Levels of errors---12
2.2 Corrective feedback---19
2.3 Correctability of certain error types---20
2.4 The popularity of automated writing evaluation tools---21
2.5 Empirical studies in Linggle Write---25
2.6 Evaluation of effectiveness performance of correction tools---27
Chapter 3 Methodology---32
3.1 Data collection---32
3.2 Procedure---34
3.3 Data Analysis---34
3.3.1 Error types analysis---35
3.3.2 Evaluation of the performance of Linggle Write---36
Chapter 4 Results and Discussion---43
4.1 Misspelling errors---45
4.1.1 Effective correction---47
4.1.2 Redundant correction---48
4.1.3 Miscorrection---49
4.2 Mechanic errors---50
4.2.1 Effective correction---51
4.2.2 Redundant correction---52
4.2.3 Miscorrection---53
4.2.4 System bug---54
4.3 Lexical errors---55
4.3.1 Effective correction---56
4.3.2 Redundant correction---58
4.3.3 Miscorrection---59
4.3.4 System bug---60
4.4 Grammar errors---61
4.4.1 Effective correction---62
4.4.2 Redundant correction---63
4.4.3 Miscorrection---65
Chapter 5 Conclusion---68
5.1 Summary of major findings---68
5.2 Some thoughts on the future of Linggle Write---71
5.3 Limitations and further studies---73
References---75

1. Boisson, J., Kao, T. H., Wu, J. C., Yen, T. H., & Chang, J. S. (2013). Linggle: a web-scale linguistic search engine for words in context. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 139-144.
2. Celce-Murcia, M., Brinton, D., & Snow, M. A. (2014). Teaching English as a second or foreign language (Fourth edition. ed.). National Geographic Learning.
3. Chang, C. S. (2016). The Effects of Corpus Tools on Assisting EFL Learners to Correct Errors [Unpublished master's thesis]. National Taiwan Normal University.
4. Chen, H. J. H., Cheng, H. W. S., & Yang, T. Y. C. (2017). Comparing grammar feedback provided by teachers with an automated writing evaluation system. English Teaching & Learning, 41(4), 99-131.
5. Chodorow, M., Gamon, M., & Tetreault, J. (2010). The utility of article and preposition error correction systems for English language learners: Feedback and assessment. Language Testing, 27(3), 419-436.
6. Chou, Y. F. (2014). Taiwanese senior high school English teachers’ perspectives on written error feedback and feedback practices [Unpublished master's thesis]. National Chung Cheng University.
7. Dodigovic, M., & Tovmasyan, A. (2021). Automated writing evaluation: The accuracy of Grammarly’s feedback on form. International Journal of TESOL Studies, 3(2), 71-87.
8. Fitria, R. A., Sabarun, S., & Miftah, M. Z. (2022). Students’ perception of the use of grammarly in undergraduate thesis writing. PROJECT (Professional Journal of English Education), 5(2), 366-371.
9. Fitria, T. N. (2021). Grammarly as AI-powered English writing assistant: Students’ alternative for writing English. Metathesis: Journal of English Language, Literature, and Teaching, 5(1), 65-78.
10. Ghufron, M. A., & Rosyida, F. (2018). The role of Grammarly in assessing English as a foreign language (EFL) writing. Lingua Cultura, 12(4), 395-403.
11. Herbold, S., Hautli-Janisz, A., Heuer, U., Kikteva, Z., & Trautsch, A. (2023). A large-scale comparison of human-written versus ChatGPT-generated essays. Scientific Reports, 13(1), 18617.
12. Hsiao, J. C., & Chang, J. S. (2023). Enhancing EFL reading and writing through AI-powered tools: design, implementation, and evaluation of an online course. Interactive Learning Environments, 1-16.
13. Huang, H. W., Li, Z., & Taylor, L. (2020). The effectiveness of using Grammarly to improve students' writing skills. Proceedings of the 5th International Conference on Distance Education and Learning, 122-127.
14. Isnaeni, M., & Datang, F. A. (2017). An error analysis of using punctuations in narrative texts. ELT-Lectura, 4(1), 48-55.
15. James, C. (1998). Errors in language learning and use: Exploring error analysis. Longman.
16. Lin, W. Y., Liu, Y. L., & Yu, C. Y. (2018). The factor structure of multiple‑choice items of the English subtest of the general scholastic ability test. Journal of National Formosa University, 34(2), 89-105.
17. Nova, M. (2018). Utilizing Grammarly in evaluating academic writing: A narrative research on EFL students’ experience. Premise: Journal of English Education and Applied Linguistics, 7(1), 80-96.
18. Oneill, R., & Russell, A. (2019). Stop! Grammar time: University students’ perceptions of the automated feedback program Grammarly. Australasian Journal of Educational Technology, 35(1).
19. Park, C., Yang, Y., Lee, C., & Lim, H. (2020). Comparison of the evaluation metrics for neural grammatical error correction with overcorrection. IEEE Access, 8, 106264-106272.
20. Shang, H. F. (2022). Exploring online peer feedback and automated corrective feedback on EFL writing performance. Interactive Learning Environments, 30(1), 4-16.
21. Thomas, J. (1983). Cross-cultural pragmatic failure. Applied linguistics, 4(2), 91-112.
22. Tlili, A., Shehata, B., Adarkwah, M. A., Bozkurt, A., Hickey, D. T., Huang, R., & Agyemang, B. (2023). What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learning Environments, 10(1), 15.
23. Truscott, J. (2001). Selecting errors for selective error correction. Concentric: Studies in Literature and Linguistics, 27(2), 93-108.
24. Tsai, C. T., Chen, J. J., Yang, C. Y., & Chang, J. S. (2020). LinggleWrite: a coaching system for essay writing. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 127-133.
25. Tsai, P. C., & Cheng, Y. S. (2009). The effects of rhetorical task type, English proficiency, and writing anxiety on senior high school students' English writing performance. English Teaching & Learning, 33(3), 95-131.
26. Tseng, C. C. (2016). Subsumable relationship among error types of EFL writers: A learner corpus-based study of expository writing at the intermediate. English Teaching & Learning, 40(1), 113-151.
27. Üstünbaş, Ü. (2024). EFL learners' views about the use of artificial intelligence in giving corrective feedback on writing: A case study. In Z. Ç. Köroğlu & A. Çakır (Eds.), Fostering Foreign Language Teaching and Learning Environments with Contemporary Technologies (pp. 115-133). IGI Global.
28. Zinkevich, N. A., & Ledeneva, T. V. (2021). Using Grammarly to enhance students’ academic writing skills. Professional Discourse & Communication, 3(4), 51-63.