I chose to continue text mining with the data previously extracted from Twitter by Dr. Kellogg for my initial social network analysis. As a participant in the conference and an active Twitter user connected to many of the nodes in the data, I thought I could bring useful perspective to the coding process based on experience. “The process is most useful when the data it generates can be further analyzed by a domain expert, who can bring additional knowledge for a more complete picture.” (Rosé, 2014, YouTube).

As a participant, I predicted that most of the tweets were already positive based on experience and a cursory review of the tweets in the csv file. Therefore, I knew that a sentiment analysis of positive/negative would not yield much useful information about what type content was being shared.

While there is value in sharing moments of participation with members of one's Digital Professional Learning Network (DPLNs), how are members moving the profession of tech-infused teaching forward beyond praise in a silo? To what extent can DPLNs affect change in practice after a conference ends? In order to answer these questions, I attempted to analysis the content to discern what was being said by members who actively participated during the conference by tweeting. The initial data set was comprised of over 5,000 tweets.