What Does Twitter Say About Self-Regulated Learning? Mapping Tweets From 2011 to 2021

Area of Science:

• Education
• Social Media Analysis
• Computational Social Science

Background:

• Social network services like Twitter offer valuable data for public opinion mining.
• Self-Regulated Learning (SRL) is a growing theory in education, necessitating an understanding of its public discourse.
• Investigating online discussions provides insights into the perception and understanding of educational theories.

Purpose of the Study:

• To analyze public discourse on Self-Regulated Learning (SRL) using Twitter data.
• To identify trends, key topics, and geographical distribution of SRL discussions on Twitter.
• To understand what Twitter reveals about the perception of SRL.

Main Methods:

• Data collection of 54,070 relevant SRL tweets from 2011 to 2021.
• Descriptive analysis to track discussion volume over time.
• Topic modeling using Latent Dirichlet Allocation (LDA) for content analysis.
• Geocoding analysis to determine user geographical distribution.

Main Results:

• SRL discussions on Twitter showed growth from 2011 to 2018, followed by a significant decrease.
• LDA topic modeling identified key computational themes within the SRL discourse.
• Geocoding revealed a globally diverse user base, with a notable concentration of users from the Global North.

Conclusions:

• Twitter discourse on SRL exhibits temporal trends and geographical biases.
• The study provides insights into the online conversation surrounding Self-Regulated Learning.
• Further research can explore the implications of these findings for educational theory and practice.