This repository is using the methods in So & Long (2016) on the corpus of Chinese couplets.
Paper's title: Literary Pattern Recognition: Modernism between Close Reading and Machine Learning
Author(s): Hoyt Long and Richard Jean So
- Python 2.7.12
- HaikuClassificationFunctions
- Nltk package. I used cmudict as the author did in his paper.
Chinese couplets raw texts are provided in the excel file "Chinese couplets_TC Lai.xlsx". Calculating results are in "Chinese couplets_TC Lai Count.xlsx".