This project is python based. Its aim is to find context around a given list of words in corpora, which can be divided. For now, it provides :
- Finder of words with their frequency
- Finder of word synonyms within the text
- Finder of sentences in which these words appear
- Sentiment analyser of these sentences
- Frequency of lemma in these sentences
This project needs
- Python 2 or superior
- Pattern.en, Website
The example is withdrawn from the Gutenberg Project. All credits to them.
- Copy elements of source folder in example
- Run test.py
- Pattern runs an error for a too large collection of chapters
- Only plaintext file are supported
- Only text using "CHAPTER" to introduce a new chapter are supported
This project has been developed during a one day code contest at the DARIAH Summer School 2013 in Goettingen (Germany) by
- Christopher Ohge
- Georg Roth-Kleyer
- Irina Savinetskaia
- Michael Ammon
- Nadine Hecht
- Thibault Clerice