Course Description
Use of natural language processing techniques to analyze large-scale educational text data, including essays, discussion posts, and feedback. Topics include statistical and machine learning approaches, pre-trained language models, data preparation, feature extraction, modeling, and interpretation.
Athena Title
Text Analytics in Education
Semester Course Offered
Offered fall
Grading System
A - F (Traditional)
Student learning Outcomes
- Students will explain fundamental concepts of computational approaches for educational data analysis.
- Students will describe text preprocessing techniques, including tokenization, stemming, and lemmatization.
- Students will compare different natural language processing methods for preprocessing and analysis.
- Students will evaluate the quality of prior studies using natural language processing in educational research.
- Students will clean and preprocess textual data and extract or engineer features for subsequent analysis.
- Students will apply natural language processing methods to textual data to extract information, classify data, identify relationships, or develop predictive models.
- Students will design and conduct a research study using natural language processing techniques.
Topical Outline
- Introduction to Natural Language Processing
- Regular Expression (Regex)
- Text Preprocessing (Tokenization, Stemming, and Lemmatization)
- Part of Speech (PoS) and PoS Tagging
- Parsing
- Statistical Methods and Rule-Based Classifiers
- Language Models
- Word Embeddings
- Large-Language Models
- Topic Modeling and Sentiment Analysis
