The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Getting an output for each input
Legacy User
Member Posts: 0 
Newbie
Hey,
I'm new to rapidminer. I built an application for sentiment analysis. It starts with reading several reviews (with the help of textInput - tokenizer, stopwordfilter, stemmer...) and then it uses support vector machines. So my training process is already done and the generated model works quite well because I get an average accuracy of 84 percent.
But now I would like to set an input with several reviews and rapidminer should give me an output to each review wether it's positive or negative, not an overview how many of them are positive or negative.
I think this should be possible but I can't find how.
Kind regards
I'm new to rapidminer. I built an application for sentiment analysis. It starts with reading several reviews (with the help of textInput - tokenizer, stopwordfilter, stemmer...) and then it uses support vector machines. So my training process is already done and the generated model works quite well because I get an average accuracy of 84 percent.
But now I would like to set an input with several reviews and rapidminer should give me an output to each review wether it's positive or negative, not an overview how many of them are positive or negative.
I think this should be possible but I can't find how.
Kind regards
0
Answers
well you simply have to save the SVM model after learning and save a word list during the text input (see the corresponding parameter in the [tt]TextInput[/tt operator).
Afterwards you can load new texts again with any input operator (do not forget to load the word list you saved before in this step), load the model you saved and then apply it. The new data set should then contain a prediction column with the corresponding label.
Kind regards,
Tobias