KH Coder is a free software for quantitative content analysis or text data mining. It is also utilized for computational linguistics. You can analyze Japanese, English, French, German, Italian, Portuguese and Spanish text with KH Coder. Also, Chinese language data (simplified, UTF-8) can be analyzed with the latest alpha version.
KH Coder provides various kinds of search and statistical analysis functions using back-end tools such as Stanford POS Tagger, Snowball stemmer, MySQL and R.
- Words: Frequency List
- Words: Searching
- Words: KWIC Concordance
- Words: Collocation Stats
- Words: Correspondence Analysis
- Words: Multi-Dimensional Scaling
- Words: Co-Occurrence Network
- Words: Hierarchical Cluster Analysis
- Categories: Developing Your Own Categories or Dictionaries
- Categories: Frequency List
- Categories: Cross Tabulation
- Categories: Correspondence Analysis
- Categories: Multi-Dimensional Scaling
- Categories: Co-Occurrence Network
- Categories: Hierarchical Cluster Analysis
- Documents: Searching
- Documents: Clustering
- Documents: Naive Bayes classifier
This is an excellent software, particularly for Japanese, a language that is not readily covered by most text analytics softwares, even highly priced. The interface is quite old-fashioned but that does not matter as far as the functionality is here. Some complained about BOM errors, but this is quite noemal since the engine would not anallyze the byte order mark (a code preceding texts, proper to Unicode). Now, this is not exctly a newbie's toy. it requires a minimal knowledge in text analysis and the logic it is designed. It makes use of R modules which is doing most of the analytical job. The drawback is that it may be stuck if you are trying to analyze a very very long text. Also, the not-free Mac installer is disturbing. it does not provide any auto update function, so that you have to go to the "webstore" ech and every time you need or want to apgrade it to the latest version. They shoud make the instaler much more user-friendly, since they are asking for money for that, even if it is not too expensive...
This may work well for Japanese, but it absolutely chokes on EVERY English-language txt file, no matter what encoding you try. The error will either be a 'BOM' error, or it will exclaim, 'There's something wrong with the POS tagger!' In addition, the interface is clumsy and clunky, straight out of 1998. The whole program has a shaky feel, as if it's about to freeze at any second... and then it does.
Such a good software for text analysis. The author is also very receptive for questions.
Fascinating and unique piece of software. Not the easiest to install and use, but very rewarding once you get the hang of it.