alexrutherford/hausa_detection

A IPython notebook to grab content in the Hausa language (dominant in Nigeria) from the BBC Hausa account using the Twitter API. This in turn can be used for language detection based on the distribution of n-character sequences #Summary Notebook to grab URLs of recent BBC Hausa articles using Twitter API, grab text content and clean for parameterising language detection module based on 3 character sequence (langid) You can view the notebook online here NBViewer #Dependencies * Python Twitter * Mining the Social Web Recipes