查詢結果分析
來源資料
相關文獻
- Investigating the Potential of a Customized AI Chatbot to Automate Writing Assessment in a Compulsory English Course at a Hong Kong University
- Perceptions of Automated Writing Evaluation (AWE) Feedback on L2 Writing
- Investigating L2 Writing: A Comparison of the Use of Rhetorical Organization by Students in Taiwan and Mainland China
- Focus on Form and Focus on Forms: Teaching Issues in Second Language Writing Instruction
- The Use of a Writing Center by Non-native Academic Writers: A Case Study in Taiwan
- Writing Your Voice as a Reader : The Janusian Face of the Text
- An Investigation of the Effect of the First Language on Writing in English as a Foreign Language
- The Application of Translanguaging in an English for Specific Purposes Writing Course
- 語料庫輔助第二語言寫作教學課程設計與實施--以中高級寫作課程為例
- The Effectiveness of Indirect and Metalinguistic Comprehensive Feedback on EFL Students' L2 Paragraph Writing
頁籤選單縮合
| 題 名 | Investigating the Potential of a Customized AI Chatbot to Automate Writing Assessment in a Compulsory English Course at a Hong Kong University=研究人工智慧聊天機器人在香港大學英語必修課中自動進行寫作評估的潛力 |
|---|---|
| 作 者 | 李禕; 楊潔; 何璿子; 蘭舸; | 書刊名 | 外國語文研究 |
| 卷 期 | 42 2025.12[民114.12] |
| 頁 次 | 頁105-135 |
| 分類號 | 312.83 |
| 關鍵詞 | 寫作評估; 生成式人工智能; 第二語言寫作; Writing assessment; Generative AI; Second language writing; |
| 語 文 | 英文(English) |
| DOI | 10.30404/FLS.202512_(42).0005 |
| 中文摘要 | 自從 2022 年 ChatGPT 發佈以來,生成式人工智慧在語言教育的多個方 面產生了巨大影響,例如語言教學、習得和評估。以香港某公立大學爲例, 本研究旨在探究 ChatGPT 是否可以作爲必修英語課程的寫作評估工具。 爲了在這一教學情境中實現生態有效性,本研究構建了一個由人工智慧驅 動的聊天機器人,以模擬英語教師在評估學生寫作任務前需要經歷的完整 培訓過程,例如閱讀作業要求、熟悉評估標準以及審閱學生寫作樣本。該 聊天機器人被用於自動評估 100 篇由母語爲中文的本科生產出的敘述性 作文。研究結果顯示,在三個總體寫作質量等級(A、B 和 C)之間存在 輕微一致性(Kappa 值 κ = 0.126),而機器人評分與教師評分之間存在 正向中度相關(r = 0.446)。該結果揭示了在英語課堂中使用生成式人工 智慧自動評估寫作的機遇與挑戰。最後該研究提出了對未來類似研究和語 言教學實踐的啓示。 |
| 英文摘要 | Since the release of ChatGPT in 2022, Generative AI has brought a large influence on multiple aspects of language education, such as teaching, learning, and assessment. This study aims to explore whether ChatGPT can be used as an assessment tool in a compulsory English course at a Hong Kong university. To achieve high ecological validity in this teaching context, an AI-powered Chatbot was built to replicate the exact training process that English teachers need to undergo before assessing students’ writing tasks, such as reading assignment prompts, familiarizing themselves with the assessment rubric, and reviewing standardization samples. This Chatbot was applied to automatically score 100 narrative essays written by undergraduate students, who speak Chinese as their first language. The findings show a slight level of agreement (Kappa value of κ = 0.126) between three general grade levels (A, B, and C) and a positive, moderate correlation (r = 0.446) between Chatbot scores and teacher scores. These findings reveal both the opportunities and challenges of using GenAI to automate writing assessment in English classrooms. The study concludes with implications for future research and language teaching practices effectiveness of GenAI in this context. |
本系統中英文摘要資訊取自各篇刊載內容。