ChatGPTを使った英語の授業デザインの試みと留意点

英語の授業で機械学習を利用する際、DeepL Writeが英語の添削に利用できるのに対して、ChatGPTは授業デザインや問題作成などクリエイティブな側面に強みがあります。授業デザインを作成してみて、是非を検討してみます。この文書は2023年2月2日に書いています。

次の二つの授業デザインを作成してみます。

1.中学1年生向けの英語の授業の授業デザイン
2.大学2年生向けの情報をテーマとする英語の授業の授業デザイン

1.はじめに、練習として、中学1年生向けの英語のレッスンプランを作成してみます。こちらの指示は、
「日本の中学1年向けの英語の授業の計画を立ててください。あいさつをテーマとし、簡単な言葉で二人の会話を書いてください。」
です。

以下のようなレッスンプランが出てきました。
Here's a lesson plan for a 1st-year junior high school student in Japan focusing on greetings in English:

Objective:

Students will be able to greet others in English and respond to basic greetings.

Materials:

Whiteboard
Markers

Procedure:

Introduction (5 minutes):
    Write "Hello" on the whiteboard and ask the students what it means in English.
    Write other basic greetings such as "Hi," "Good morning," and "Good afternoon" on the board and ask the students to repeat after you.

Individual Practice (10 minutes):
    Hand out a piece of paper to each student with a conversation between two people using basic greetings.
    Ask the students to practice the conversation with their classmates.

Class Discussion (10 minutes):
    Ask the students to come up with other basic greetings in English that they know.
    Write the greetings on the board and have the students practice using them.

Conclusion (5 minutes):
    Summarize the greetings learned in the class and ask the students to repeat after you.
    End the class by saying goodbye in English.

Example of a conversation:

    Person A: Good morning!
    Person B: Good morning! How are you?
    Person A: I'm good, thank you. How about you?
    Person B: I'm fine, thank you.

自分で書いた方が早そうですが、ともあれいろいろ修正すれば使えるでしょう。英文の例などの作成には重宝するといったところでした。

2.次に、大学2年生向けのESPの英語クラスのレッスンプランを作成してみます。こちらの指示は、
「日本の大学2年生向けの英語の授業の計画を立ててください。ESPの授業で、Pythonをテーマとし、Pythonに関するテキストと、簡単な言葉でPythonに関する二人の会話を書いてください。時間は90分です。」
です。

以下のようなレッスンプランが出てきました。
Here's a lesson plan for a 2nd-year college student in Japan focusing on English for Specific Purposes (ESP) with a theme of Python:

Objective:

Students will be able to understand basic Python language and code.
Students will be able to engage in a conversation about Python.

Materials:

Whiteboard
Markers
Laptops or computers (optional)
Python textbook or online resource

Procedure:

Introduction (10 minutes):
    Write "Python" on the whiteboard and ask the students what it is.
    Briefly explain what Python is and its use in the programming world.

Lecture (40 minutes):
    Cover the basic concepts of Python, such as variables, data types, control structures, and functions.
    Show examples of code snippets and explain how they work.

Practice (20 minutes):
    Have the students open their laptops or computers and follow along with the examples in the textbook or online resource.
    Assist the students as needed to complete the exercises.

Class Discussion (10 minutes):
    Have the students work in pairs or small groups to discuss their understanding of Python.
    Encourage the students to ask questions and share their experiences with each other.

Conversation (10 minutes):
    Provide a conversation between two people about Python and have the students practice it in pairs.

Example of a conversation:

Person A: Have you been learning Python?
Person B: Yes, I have. I'm really enjoying it.
Person A: That's great. What do you like about it?
Person B: I love how versatile it is and how many applications it has. And it's also relatively easy to learn.
Person A: Definitely. I've heard it's widely used for web development, data analysis, and machine learning.
Person B: Yes, that's correct. It's a great tool to have in your programming arsenal.

Conclusion:

Review the key points learned in the class and ask the students to summarize what they learned.
End the class by asking the students to share their thoughts and experiences with Python.

形としては授業デザイン(レッスンプラン)なのですが、中身が英語の授業というよりは情報の演習の授業になっています。指示の出し方に工夫をする必要がありそうです。また別にテキスト教材があることを前提としています。

中身となるテキストを書かせてみました。指示は
「Pythonの簡単な説明を英語で書いてください。300ワードで書いてください。」
です。

以下のテキストが出ました。
Text:

Python is a high-level, interpreted programming language that is widely used for various purposes such as web development, scientific computing, data analysis, artificial intelligence, and more. It was first released in 1991 and since then it has become one of the most popular programming languages in the world.

One of the main benefits of using Python is its simplicity and ease of use. The language is designed to be easy to read and write, even for those who are new to programming. It has a relatively small number of keywords and its syntax is straightforward and intuitive.

In addition to its simplicity, Python is also highly versatile. It can be used for a wide range of applications, including web development, game development, scientific computing, and more. Its large and active community of developers has created a large number of libraries and modules that make it easier for developers to solve complex problems.

Another advantage of Python is its strong support for data analysis and scientific computing. It has many libraries and modules that are specifically designed for these purposes, such as NumPy, Pandas, and Matplotlib. These libraries make it easier for data scientists and researchers to work with large datasets and perform complex data analysis tasks.

Finally, Python has a strong ecosystem for machine learning and artificial intelligence. There are many libraries and frameworks, such as TensorFlow, PyTorch, and scikit-learn, that make it easier for developers to implement machine learning models and build intelligent systems.

In conclusion, Python is a powerful, versatile, and easy-to-use programming language that has a wide range of applications. Whether you're a beginner programmer or an experienced software engineer, it's definitely worth learning and adding to your skillset.

こちらはおおむね良いといったところです。自動生成した英文を、批判的に読ませつつ、単語を調べたり、Pythonを使って何ができるか調べて発表させたりなどすれば英語の授業となりそうです。

難点を言えば、自動生成した英文に責任の所在がないことです。正しい知識に基づきかかれたものか、何を目指して書かれたテキスト化、授業の目的に適っているかなど、検討する必要があります。教員に該当テーマについての知識がない場合、内容について判断することができないため、使用するのは避けた方がいいでしょう。

例をあげると、地球温暖化についてのテキストをChatGPTに書かせたとします。多くの場合、英語教員は地球温暖化を専門分野としていないと思われます。出てきた地球温暖化についての文章が、学問分野の中でどのような位置づけにあるのか、社会一般における論点の中でどうとらえられているか、地球温暖化についての知見の全体像の中でChatGPTが書いた文章をどう評価してよいか、語られている内容ひとつひとつの事実は真か偽か、他に文章内で語られていない重要な論点や具体例はないかといった点を、英語教員は判断できません。判断できない責任のとれない文章を学生に読ませることはできません。それはちょうど、道端に落ちていた見知らぬ紙切れを、英語だからという理由で読ませるようなものです。学生の側も専門家でない先生に地球温暖化の話をされても困るでしょう。機械学習によって生成された文章は、人が判断して読ませられる文章であるという太鼓判を押さない限り、信頼をもって受け取ることができないということです。ただし、「本当にこの文章は大丈夫か」と学生に批判させながら読ませることは可能でしょう。

授業の方針・目的を決め、テーマを定め、必要なテキスト・問題・アクティビティを用意し、評価方法を考えるといった作業は、ある程度はChatGPTで自動化できますが、生成された授業デザインを精査し、教員が是非を判断する必要があります。また足りない箇所、修正が必要な個所は都度別に作成し判断する必要があります。CHatGPTなどの機械学習ツールを用いて、授業準備として教員が行う作業は、英語の教科書を作る作業に近いものがあるでしょう。コストを考えると、すでに出版されている英語の教科書を使用した方が労力が少なくすみそうです。

また機械学習ツールによって生成された教材の著作権の問題は、授業で都度使用する分には日本では問題ないと思われますが、教材として頒布や販売をするなどの場合には、著作権の所在者に許可を得たり著作権料を支払う必要が生じる可能性があります。この場合はOpenAPIと、厳密にはおおもとの学習データでしょうか。

まとめると、きちんとした指導方針に基づいて出版された英語の教科書を主として使うべきであり、機械学習を用いて作られた授業デザイン、テキスト、問題などは、批判を行いつつ副次的に使用するのが良いかと思います。



この記事が気に入ったらサポートをしてみませんか?