Social Media Research with Word Association Thematic Analysis

Brand new course for 2021!

Date: 9 June 2021
Time: 9:30am - 4pm
Instructor: Mike Thelwall
Level: Intermediate
Fee: £60


This course is a practical walk-through of the word association thematic analysis (WATA) method to investigate sets of social media (or other short) texts. This method is suitable for identifying gender, national, time, or topic differences in a set of 10,000+ tweets or other short texts. The method finds word-level differences that are then translated into different themes. The procedure starts with using the free software Mozdeh to gather or import the texts, then uses Mozdeh to produce lists of words occurring more in one subset of the texts than another (e.g., male vs. female vs. nonbinary; UK vs. USA; recent vs. old; topic 1 vs. topic 2; topic 1 vs the rest). Next, a two-stage manual thematic analysis is applied to identify themes within the words found. The result is a set of themes characterising substantial differences between the texts. The course goes through all these stages with a small set of texts.

Course objectives

In this course, participants will learn:

  • how to apply word association thematic analysis to a set of social media texts
  • how to use the word association thematic analysis functions in the free software Mozdeh. 


 To enrol in this intermediate course, participants must have either:

You will also need:

  • a Windows computer
  • a Twitter account and familiarity with using Twitter
  • basic knowledge of statistics.

If you have any questions about the course prerequisites, please get in touch.

Recommended reading

Thelwall, M. (2021). Word association thematic analysis: A social media text exploration strategy. San Rafael, CA: Morgan & Claypool.

Thelwall, M., Makita, M., Mas-Bleda, A., & Stuart, E. (2021). “My ADHD hellbrain”: A Twitter data science perspective on a behavioural disorder. Journal of Data and Information Science, 6(1).

About the instructor

Mike Thelwall is a professor of Data Science and head of the Statistical Cybermetrics Research Group at the University of Wolverhampton. He develops and applies software and methods to analyse social media texts.