Using Machine Learning Techniques to Identify Teachers' Activities from Positioning and Speech Data

Primary supervisor

Roberto Martinez-Maldonado

This project focuses on the automated classification of teachers' activities and co-teaching behaviors using positioning data captured via sensors and microphone data. The main task involves developing and applying machine learning techniques to analyse multimodal datasets, combining positioning and speech data to identify and categorize various teaching activities. By leveraging large language models (LLMs), Generative AI (GenAI), and Natural Language Processing (NLP), the project aims to extract features that enhance the accuracy and effectiveness of these classification tasks. This innovative approach will enable a deeper understanding of classroom dynamics and provide valuable insights for improving teaching practices through automated analysis and classification.

 

Banner of a team of teachers leading a class

Student cohort

Double Semester

Aim/outline

Project Aims

  1. Develop machine learning models: Create and refine machine learning algorithms to classify teachers' activities and co-teaching behaviors based on positioning and microphone data.

  2. Feature extraction: Utilize large language models (LLMs), Generative AI (GenAI), and Natural Language Processing (NLP) techniques to extract and enhance features from speech data that improve classification accuracy.

  3. Algorithm optimization: Optimise the performance of the classification algorithms to ensure high accuracy and reliability in identifying teaching activities.

  4. Real-time analysis: Explore methods for real-time processing and analysis of positioning and speech data to provide immediate feedback to educators. The ultimate aim is to use the classification during classroom activities to provide feedback to the teachers.

  5. Visualisation tools: Optionally, there is room for developing visualisation tools to present the classified activities and behaviors in an intuitive and informative manner, aiding teachers in reflecting on their teaching strategies.

URLs/references

Example publication related to this opportunity: Martinez-Maldonado, R. (2019) “I Spent More Time with that Team”: Making Spatial Pedagogy Visible Using Positioning Sensors. International Conference on Learning Analytics and Knowledge, LAK 2019

Required knowledge

- Basic understanding of machine learning concepts and algorithms.
- Basic skills in data cleaning, preprocessing, and analysis.
- Proficiency in programming languages such as Python.
- Familiarity with large language models (LLMs), NLP or GenAI concepts. 
- Good communication skills.
- Awareness of ethical issues in AI and data privacy.