Common Text Mining Visualizations
Ted Kwartler · 2017
This chapter constructs simple text mining visualizations from term frequency as a means to reinforce what would probably already be known in the case of DeltaAssist's customer service tweets. It then goes a step further to look at a specific term association. Text mining's association is similar to the statistical concept of correlation. One of the ways to view word connections is to treat them as a network or graph structure. Word networks are often used to demonstrate key actors or influencers in the case of social media. Within the context of text mining, networks can show relationship strength or term cohesion, leading to an assumption of a topic. The chapter guides to make and improve the aesthetics of a hierarchical dendrogram showing basic word clustering. Hierarchical dendrograms are a relatively easy approach for word clustering. The chapter discusses more complex clustering, and provides a basic means of extracting meaningful clusters.