As exemplified by the popularity of blogging and social media, textual data is far from dead – it is increasing exponentially! Not surprisingly, knowledge of text analytics is a critical skill for data scientists if this wealth of information is to be harvested and incorporated into data products.
What You'll Learn
- Tokenization, stemming, and n-grams
- The bag-of-words and vector space models
- Feature extraction using singular value decomposition (SVD)
- Training classification models using textual data
- Evaluating accuracy of the trained classification models
