felerminoali/stop-word-emakhuwa-tetun
Domain:
natural language processingCreator:
fel
Host:
**A Novel Approach for Stopwords Detection Using Network Properties**
By: Felermino Ali and Gabriel de Jesus
This project generates co-ocurrence network based on text data. Also, for each word calculates** DF, NIDF, and TF-IDF, TF, NTF.**
**Data Folders:**
- wikiclir/portuguese.txt
- wikiclir/english.txt
- tetun-emakhuwa/emakhuwa.txt
- tetun-emakhuwa/tetun.txt
To generate the nodes run:
python node.py
To generate the edges run:
python edges.py