These findings are from Phase 1 of our research. For details on our methods, visit our Methodology page.
Top 25 Most Tweeted WOrds
Teachers are tweeting about teaching. This image shows the top 25 words present in the tweets of our 507 teacher accounts. (Bolding indicates one of our moral words).
Average Influence Summary
This table shows the influence of each word in forming the clusters in Autoclass. Words are color coded depending on whether their presence or absence influenced the cluster. Scroll left-to-right to see all.
network of tweets with moral keywords
Using Gephi, we visualized the entire network’s use of moral words within tweets, and each cluster’s network. To explore the entire network, click below:
The entire network (Fig. 1) is a polarized crowd, and appears to be two groups having two distinct conversations about educational issues. Cluster 2 surrounds cluster 3, and likewise, cluster 1 surrounds cluster 4.
There are a few “bridge” accounts, mostly from cluster 3, that have many connections within cluster 4 (Fig. 2).
Also interesting to note that most accounts in cluster 2 have more connections with other cluster 3 accounts than within their own cluster (Fig. 3).