Detect the Language of a Text 

Import French, English, German, and Spanish texts from the web to use to train a classifier.

In[1]:=

X french = Import["http://fr.wikipedia.org/wiki/Main_Page"]; english = Import["http://en.wikipedia.org/wiki/Main_Page"]; german = Import["http://de.wikipedia.org/wiki/Main_Page"]; spanish = Import["http://es.wikipedia.org/wiki/Main_Page"];

Make a classifier using the training texts.

In[2]:=

X language = Classify[{french -> "French", english -> "English", german -> "German", spanish -> "Spanish"}]

Out[2]=

Test the classifier on simple phrases.

In[3]:=

X AssociationMap[language, {"the house is blue", "la maison est bleue", "la casa es azul", "das Haus ist blau"}]

Out[3]=

Detect the languages of texts.

In[4]:=

X language[ExampleData[{"Text", #}]] & /@ {"AliceInWonderland", "LesFleursDuMal", "DonQuixoteISpanish", "UNHumanRightsGerman"}

Out[4]=