Quantifying Politeness in Online Educational Forums: A Computational Study of Instructor and Student Communication

Primary supervisor

Guanliang Chen

Politeness plays a pivotal role in fostering constructive, respectful communication and maintaining positive social dynamics in educational settings. In online learning environments—such as discussion forums on Moodle—language becomes the primary medium for interaction between instructors and students. While prior studies have highlighted the benefits of politeness in building rapport and encouraging engagement, limited empirical work has systematically examined how politeness is expressed by both instructors and students in these digital spaces. This project addresses this gap by applying computational techniques to quantify politeness levels in educational forum discussions and analyze how various contextual and social factors influence politeness in instructor-student exchanges.

Student cohort

Double Semester

Aim/outline

This project aims to computationally measure and analyze the politeness displayed in online educational forums and to explore how politeness varies across different roles (instructors vs. students), courses, and discussion contexts. The specific objectives are:

  1. Politeness Quantification: Apply Natural Language Processing (NLP) models to detect and quantify politeness in forum posts by instructors and students.

  2. Comparative Analysis: Examine differences and similarities in politeness strategies used by instructors and students.

  3. Factor Analysis: Investigate how factors such as course discipline, discussion topic, type of question, and response timing influence politeness levels by using casual modelling methods (e.g., the widely-used back-door criterion and the state-of-the-art X-learner algorithms)

  4. Foundational Work for Intervention (optional extension): Explore the feasibility of transforming impolite or neutral messages into more polite versions using Large Language Models.

Potential Research Questions:

  1. Descriptive and Comparative

    • To what extent do instructors and students display politeness in their online forum communication?

    • How do politeness levels differ between instructors and students?

  2. Contextual and Influential Factors

    • How do various factors (e.g., post type, private vs. public) affect politeness levels?

URLs/references

  • Lin, J., Raković, M., Li, Y., Xie, H., Lang, D., Gašević, D., & Chen, G. (2024). On the role of politeness in online human–human tutoring. British Journal of Educational Technology, 55(1), 156-180.
  • S. R. Künzel, J. S. Sekhon, P. J. Bickel, and B. Yu. 2019. Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the national academy of sciences 116, 10 (2019), 4156–4165.
  • M.H.Maathuis and D. Colombo. 2015. A generalized back-door criterion. (2015).

Required knowledge

  • Strong programming skills (e.g., Python)
  • Basic knowledge in Data Science, Natural Language Processing, and Machine Learning
  • The following can be a plus: (i) good at academic writing; and (ii) strong motivation in pursing a quality academic publication.