Overview
- Overview
-
A course surveying text preprocessing, keyword and topic analysis, sentiment, embeddings, document classification, and semantic networks.
- Audience
-
This course was first designed for students in IDAS at National Chengchi University. The materials are generally applicable to students of any level and degree program.
- Teaching
-
- National Chengchi University
Content
Course Content
The explosion of digital text represents an unprecedented opportunity for social research. This course surveys text analysis across four stages: preprocessing and exploratory analysis; token-level methods including vectorization, word embeddings, tagging, and named entities; document-level classification and sentiment analysis; and corpus-level latent topics and semantic networks.
Students examine how text analysis supports social-science research and apply these methods to substantive questions. Special attention is given to generative AI and its rapidly changing role in text analysis.
Requirements
No prerequisites or prior coding experience are required. Sample code is provided, and exercises are introduced step by step.
Resources
- Materials
-
- Syllabus
- Module 1: Text Analysis
- Module 2: Latent Topic Modeling
- Module 3: Machine Learning
- Module 4: Semantic Networks
- Coding Task 1.1: Pre-processing
- Coding Task 1.2: Sentiment Analysis
- Coding Task 1.3: Keyword Analysis
- Coding Task 2.1: Latent Topic Model
- Coding Task 2.2: Comparative Latent Topic Analysis
- Relevant Literature
-
Browse references and supporting literature for this training module in the Organization of Power Lab Zotero library.
Open this training module's Zotero collection