3.2 From Text to Data
1. From Text to Data
In this video David looks at the sorts of analyses that can be performed on textual data - typically at the end of the NLP Pipeline.
In the video David describes two important analytical methods:
- TF-IDF - which attempts to quantify which words are the most important within a document.
- LIWC - which attempts to classify words and then looks at how words are distributed across those classifications.