AI in Education - LUH24 modules
Advanced Data Analytical (AI) Methods for Education
24 items
Updated
Description and Learning Outcome
Teachers
GKGábor Kismihók
GKGábor Kismihók

Description

This hands-on course introduces participants to advanced data analytics and AI methods with a focus on applications in education. Using freely available resources and interactive Google Colab notebooks, students will gain practical skills in Python, Pandas, NumPy, and Scikit-learn. The course covers everything from fundamental data manipulation and visualization to natural language processing (NLP) techniques (such as tokenization, stemming, lemmatization, Bag of Words, and TF-IDF) and key machine learning models for prediction and classification. By working through real examples—including essay scoring with machine learning—participants will build a solid foundation in applying AI-driven data analysis to educational contexts.

You will learn

By the end of this course, participants will be able to:

  • Work with CSV files and perform data manipulation using Pandas and NumPy.

  • Subset, clean, and modify datasets effectively for analysis.

  • Create data visualizations using Pandas plotting tools.

  • Use Google Colab for running Python code and notebooks in the cloud.

  • Apply text preprocessing techniques such as lowercasing, punctuation removal, stopword filtering, tokenization, stemming, and lemmatization.

  • Represent text data using Bag of Words and TF-IDF methods.

  • Understand and implement machine learning tasks in education, including regression and classification.

  • Build and evaluate predictive models using logistic regression and random forests with Scikit-learn.

  • Apply cross-validation to assess and improve model performance.

  • Develop a practical project (e.g., essay score prediction) that demonstrates how AI methods can be applied to real educational challenges.

What’s included
Explore the modules included in this learning path.
1

Read and write csv files using Pandas

Link Content

Description

Learn how to load and save datasets in CSV format using the Pandas library.

Learning Outcome

Participants will be able to read, explore, and export CSV files in Python using Pandas.

2

Subsetting pandas dataframe

Link Content

Description

Explore techniques to filter, select, and subset rows and columns in a DataFrame.

Learning Outcome

Participants will be able to extract meaningful subsets of data for analysis.

3

Modifying data in pandas dataframe

Link Content

Description

Practice editing, adding, or deleting columns and rows within a DataFrame.

Learning Outcome

Participants will be able to clean and transform data within Pandas efficiently.

4

Plotting with pandas

Link Content

Description

Learn to create basic visualizations directly from Pandas DataFrames.

Learning Outcome

Participants will be able to generate simple plots (line, bar, histogram, etc.) using Pandas.

5

Working with numpy

Link Content

Description

An introduction to the NumPy library for numerical computing and array operations.

Learning Outcome

Participants will be able to use NumPy for mathematical operations and efficient data handling.

6

How to work with Google colab

Link Content

Description

Get familiar with using Google Colab to write, run, and share Python code in the cloud.

Learning Outcome

Participants will be able to set up and use Google Colab as their coding environment.

7

Intro to python and pandas - Google Colab notebook

Link Content

Description

A guided walkthrough of Python basics and Pandas functions inside Google Colab.

Learning Outcome

Participants will be able to execute Python and Pandas commands interactively in notebooks.

8

Lower case conversion, remove punctuation and stopwords, text tokenization in python

Link Content

Description

Introduction to fundamental text preprocessing techniques in Python.

Learning Outcome

Participants will be able to clean and tokenize raw text data for analysis.

9

Stemming and lemmatization

Link Content

Description

Explore two key text normalization techniques used in NLP (i.e. Stemming and Lemmatization).

Learning Outcome

Participants will understand the concepts of stemming and lemmatization and their differences.

10

Stemming and lemmatization in python

Link Content

Description

Hands-on practice applying stemming and lemmatization using Python libraries.

Learning Outcome

Participants will be able to preprocess text using stemming and lemmatization in Python code.

11

Bag of words

Link Content

Description

Learn how to represent text data as word frequency vectors.

Learning Outcome

Participants will understand the Bag of Words model and its role in NLP.

12

Bag of words in python

Link Content

Description

Practical implementation of Bag of Words using Python libraries.

Learning Outcome

Participants will be able to build Bag of Words representations for text datasets in Python.

13

Tf-idf

Link Content

Description

Introduction to Term Frequency–Inverse Document Frequency as a text representation method.

Learning Outcome

Participants will understand how TF-IDF highlights important words in documents.

14

Tf-idf in python

Link Content

Description

Learn to apply TF-IDF using Scikit-learn and Python tools.

Learning Outcome

Participants will be able to compute TF-IDF values for text data programmatically.

15

Working with text data in python - Google colab

Link Content

Description

A hands-on notebook for basic working with text data.

Learning Outcome

Participants will be able to process and analyze text datasets end-to-end in Google Colab.

16

Regression vs Classification

Link Content

Description

An introduction to two main types of machine learning tasks: regression and classification.

Learning Outcome

Participants will be able to differentiate between regression and classification problems.

17

Logistic regression

Link Content

Description

Explore logistic regression as a fundamental classification algorithm.

Learning Outcome

Participants will understand how logistic regression works and when to use it.

18

Logistic regression with scikit

Link Content

Description

Hands-on implementation of logistic regression using Scikit-learn.

Learning Outcome

Participants will be able to build and evaluate logistic regression models in Python.

19

Random forest

Link Content

Description

Introduction to random forest, a powerful ensemble machine learning method.

Learning Outcome

Participants will understand the intuition and applications of random forest models.

20

Random forest with scikit

Link Content

Description

Practical application of random forest classifiers with Scikit-learn.

Learning Outcome

Participants will be able to implement and evaluate random forest models in Python.

21

Cross validation

Link Content

Description

Learn how cross-validation helps in evaluating and improving machine learning models.

Learning Outcome

Participants will understand the concept of cross-validation and its importance in model assessment.

22

Cross validation with scikit

Link Content

Description

Apply cross-validation using Scikit-learn functions and workflows.

Learning Outcome

Participants will be able to perform cross-validation on machine learning models in Python.

23

Essay score prediction using machine learning algorithm - Google Colab

Link Content

Description

A real-world project applying machine learning to predict essay scores.

Learning Outcome

Participants will be able to integrate text preprocessing and ML models into a practical educational AI application.

24

AI in Education Course Material - Python Notebooks

File Content

Description

All notebooks as s Zip file for download and local run.