In this chapter, we learned why we should do topic modeling and how it is important in a world of ever-increasing data. We also looked at the concept of LDA and its use in deciding how topics are selected from a given corpus. We also looked at the use of the MALLET tool for topic modeling on sample data and creating our own custom data. We also learned about the different files that are generated and how to interpret them.

In the next chapter, Chapter 10, Using Parser to Extract Relationships, we will see how to use the parser to extract relationships.