18 Profiling Lexical Patterns and Usage
18.1 Objectives
- Sentence length
- Syllables
- Types versus tokens
- Usage in word lists
- Lexical diversity
- Readability
- Bootstrapping methods and uncertainty accounting
18.2 Methods
Applicable methods for the objectives listed above.
18.3 Examples
Sentiment analysis.
18.4 Issues
Non-English languages.
Sampling.
Text length and its effect on diversity. Zipf’s law and Heap’s law.
18.5 Further Reading
Additional resources from libraries or the web.
18.6 Exercises
Add some here.