Use an own dictionary for Slang synonyms

na020

Hey guys,

i'm currently trying to create my own dictionnary for some slangwords. The whole task is about implementing an automatic Music Lyrics Analyzer. The MLA uses text analytics methods based on an established platform to analyze the vocabulary used in song lyrics of different interpreters / genres and.build clusters of songs based on their lyrics. In some genres like reggae, there are many slangwords which I try to replace by normal englisch (create my own dictionary). Which operators and which file-type should I choose for the task?

Thanks

 

Telcontar120

Based on what you described, "replace tokens" is probably your best choice.  That will allow you to map all synonyms into a single consistent token for your subsequent analysis.  You can also filter out some custom words entirely with a text filter, either by using "filter tokens" or by "filter stopwords - dictionary", both of which allow you to supply user input to tell RapidMiner which tokens to omit.