Welcome to edu-convokit’s documentation!

The edu-convokit is an open-source framework designed to facilitate the study of language data in educational settings. It provides a practical and efficient pipeline for essential tasks such as text pre-processing, annotation, and analysis, tailored to meet the needs of researchers and developers. This toolkit aims to enhance the accessibility and reproducibility of educational language data analysis, as well as advance both natural language processing (NLP) and education research. By simplifying these key operations, the edu-convokit supports the efficient exploration and interpretation of text data in education.

Installation

You can install the latest version of the edu-convokit from the GitHub repository:

!pip install edu-convokit

Colab Notebooks

Basics of edu-convokit

• Tutorial on Text Pre-Processing
• Tutorial on Annotation
• Tutorial on Analysis

Datasets with edu-convokit

• Tutorial on the NCTE dataset with edu-convokit
• Tutorial on the Amber dataset with edu-convokit
• Tutorial on the TalkMoves dataset with edu-convokit

Contents

Main Modules:

• Pre-Processing
  • Text Pre-Processing
  • Token Pre-Processing
• Annotation
  • Annotator
• Analyzers
  • Qualitative Analyzer
  • Quantitative Analyzer
  • Lexical Analyzer
  • Temporal Analyzer
  • GPT Conversation Analyzer

Tutorials: Basics of edu-convokit:

• Tutorial on Text Pre-Processing for Education Language Data
  • 📚 Learning Objectives
  • Installation
  • 📑 Data
  • 📝 Anonymizing Data with Known Names
  • 📝 Anonymizing Data with Unknown Names
  • 📝 Standardizing Data for Downstream Annotation and Analysis
  • 📝 Conclusion and Where to Go From Here
• Tutorial on Annotating for Education Language Data
  • 📚 Learning Objectives
  • Installation
  • 📑 Data
  • 📝 Annotating Talk Time
  • 📝 Annotating Student Reasoning
  • 📝 Annotating Teacher Focusing Questions
  • 📝 Annotating Conversational Uptake
  • 📝 Conclusion and Where to Go From Here
• Tutorial on Analyzers for Education Language Data
  • Motivation on Analyzer
  • 📚 Learning Objectives
  • Installation
  • 📑 Data
  • 🔍 Qualitative Analysis
  • 📊 Quantitative Analysis
  • 💬 Lexical Analysis
  • 📈 Temporal Analysis
  • 🤖 GPT Analysis
  • Data Entry Points for Analyzer
  • 📝 Conclusion and Where to Go From Here

Tutorials: Datasets with edu-convokit:

• Tutorial on edu-convokit for the Amber dataset
  • Installation
  • 📑 Data
  • 📝 Text Pre-Processing and Annotation
  • Analysis
  • 🔍 Qualitative Analysis
  • 📊 Quantitative Analysis
  • 💬 Lexical Analysis
  • 📈 Temporal Analysis
  • 📚 Conclusions and Next Steps
• Tutorial on edu-convokit for the TalkMoves dataset
  • Installation
  • 📑 Data
  • 📝 Text Pre-Processing and Annotation
  • Analysis
  • 🔍 Qualitative Analysis
  • 📊 Quantitative Analysis
  • 💬 Lexical Analysis
  • 📈 Temporal Analysis
  • 📚 Conclusions and Next Steps
• Tutorial on edu-convokit for the NCTE dataset
  • Installation
  • 📑 Data
  • 📝 Text Pre-Processing and Annotation
  • Analysis
  • 💬 Lexical Analysis
  • 📈 Temporal Analysis
  • 🤖 GPT Conversation Analysis
  • 📚 Conclusions and Next Steps

Citation

If you use the edu-convokit in your research, please cite the following paper:

TODO: coming soon...

Contributing

We welcome contributions to the edu-convokit! Feel free to make a pull request or submit an issue on GitHub: https://github.com/rosewang2008/edu-convokit.

Contact

If you have any questions, please contact Rose E. Wang at rewang@cs.stanford.edu.