TextInfoExp

Why we included this project

This repository holds a set of Chinese NLP experiments built around the Sogou news corpus. Instead of shipping one deployable tool, it walks through the classic text-processing pipeline piece by piece: TF-IDF, classification, clustering, word2vec, sentiment analysis, and relation extraction, each with working code you can read and adapt. For students or developers who learn better from concrete examples than from theory, that is exactly what makes it useful. The code targets Python 2.7 and reads like older course material, but the underlying algorithms still translate cleanly to modern libraries. If you are putting together a Chinese text-mining lab or just want readable reference implementations to borrow from, this is a good starting point.