RapidMiner

arabic text classification

Contributor II

arabic text classification

Hi
Is rapidmner support other languages like arabic . If yes how can i use it to classify arabic texts

Thank you
7 REPLIES
Elite II

Re: arabic text classification

Hi,
RapidMiner does not care about the language of the texts. All texts, that can be separated in single words, might be used to build a bag of words.
Just use the text plugin as described in its samples.

Greetings,
  Sebastian
Old World Computing - Establishing the Future

Professional consulting for your Data Science problems

ema
Regular Contributor

Re: arabic text classification

Hi,
I presonly worked with it , just add utf8 , or the word unicode in the encoding field
Contributor II

Re: arabic text classification

Hi
If I can use arabic text classification, why there is an english and german stemmers

Thank you
Regular Contributor

Re: arabic text classification

Mmm, a tough one, don't suppose it could be for English or German text classification? Just a wild and uninspired guess.
ema
Regular Contributor

Re: arabic text classification

you  dont need to use the german or the english stemmers ,
Rapid miner does not support arabic stemming ,
what you can do is either use n-grams  or stem the text files outside rapidminer
Contributor II

Re: arabic text classification

helloo

 i am beginner   can you help me please to  change  the encoding   to can work with arabic textes !

 

Contributor

Re: arabic text classification

Hi, Can you please share the sample file.