A text mining tool for Korean and English
pyTextMiner was orginally designed as a teaching aid for my Text Mining class at Yonsei University. pyTextMiner was developed in Python. Prior to the development of pyTextMiner, I developed the yTextMiner text mining tool in Java for a teaching purpose. I used yTextMiner for my MOOC and K-MOOC courses as well as my courses that I taught at Yonsei University.
In the current version of pyTextMiner, pyTextMiner can handle both English and Korean texts. However, the majority of the compoents is for Korean texts.
pyTextMiner follows the principle of the pipeline architecture where each pipe takes care of its task of processing and representing the incoming text. Pipeline allows for a simple, modularized process of text.
In the future, I plant to include preprocessing techinuqes for other languages such as Chinese, Japanese, and French.