Students will understand how machine learning algorithms recognize patterns in text (poetry) and apply these concepts in Scratch programming.
“Machine Learning (ML) Applications"
1. A learning machine will be trained on a set of data (poems) to identify the predominant words.
2. The lesson is based on pattern recognition in ML.
3. Engaging students by combining AI technology with literature
“Integration of Art and Technology”:
1. You will use poetry to show ML's ability to process and understand human language, blending artistic expression with technology.
2. Poetry will help students appreciate the subtleties of language
3. Encouraging creativity in coding, open discussions about poetry and technology, and hands-on activities.
4. Poems from Eminescu's work will be used.
“Lesson Preparation and Evaluation”:
1. Pre-lesson: Introduction to the themes of love and childhood from Eminescu's poems.
2. Post-lesson: Reflective writing on how ML and poetry intertwine.
"Lesson Evaluation"
1. Establishing the theme of the poems by finding the predominant words with the help of ML
2. Creating an interactive and visual interface, facilitating the understanding of the results obtained by programming in Scratch.
2. Apply ML concepts to categorize different poetic themes.
- Brainstorming about love and childhood (one key word each) and create a cluster on the board with these words
- Introduce the concepts specific to the theme of love and childhood, completing the clusters made by the students
- Introduce the concept of ML in the analysis of a poem.
- Provide written instructions and verbal explanations.
- Use hands-on activities in Python/Scratch to complete the tasks described in the worksheet.
1.Task:
Students will create a simple ML model to identify prevalent words. For this, they will introduce the five Eminescu poems received on the worksheet.
The teacher encourages students to experiment with the MLforkids platform, Python and Scratch.
Students will identify prevalent words (using Python) from poems uploaded to the ML platform.
The results obtained by the model are presented in a graphical interface created in Scratch (for example, a word cloud be created).
The teacher offers additional support or differentiated work tasks for students.
2.Organization:
Work in groups to brainstorm and analyze patterns in language.
3.Differentiation:
Depending on the programming skills of the students, they will create models in ML and programming in Python or Scratch.
basic level:
- Data collection: The 5 poems by the same author, named in the worksheet, are searched on the Internet to obtain a homogeneous data set.
level 1: Applying the model: The trained model is used to identify the predominant keywords.
level 2: Visualization: The results obtained by the model are presented in a graphical interface created in Scratch.
level 3: Training the model: A machine learning technique such as prevalent word extraction is used (Python). The model will learn to identify words that appear most frequently and in similar contexts.
Link to Objectives:
- Students identify the type of theme (love or childhood) by comparing the results obtained from the ML model and the clusters made at the beginning of the lesson
- Reflective writing on how ML and poetry intertwine (homework).
Sharing:
Students present their ML models, discuss their word cloud.
Next Lesson:
Introduction to the next lesson on ML applications and analysis of Blaga and his poems in order to identify the theme considering the dominating words/expressions.
- Apps: Scratch, Machine Learning for Kids platform, Python
- Equipment: Computers with internet access, projector for demonstrations.
- Supplementary: Printed worksheets on basic ML concepts, example poems for reference.