This year, in late October, Rapidminer released an update to their Wordnet Extension. Granted, it’s December and I’m just getting around to playing with it now, but this particular update incorporated the SentiWordnet dictionary as a new operator. Here’s how to do Sentiment Analysis in RapidMiner.
This is really cool because it gives Rapidminer a deeper access to the world of Opinion Mining. Rapidminer has always been able to do Sentiment Analysis from a statistical approach but accessing the realm of Opinion Mining always required you to call processes (i.e. Sentiwordnet) outside of Rapidminer and integrate them into the workflow.
So how do you use it? First you need to have the latest Wordnet Extension installed and download the latest Wordnet (3.0.0) dictionary onto your machine. When you process your text files, it will generate a new sentiment column with numerical attributes ranging from -1 to +1. What these values mean can best explained here.
Sentiment Analysis in RapidMiner
Below are some screenshots of a simple Twitter process searching for iPhone6 tweets and generates sentiment based on the tweet itself.
The New SentiWordnet Operator
Bear in mind, the results I show here are very rudimentary and Tweets are generally very messy. What you would need to do is evaluate the results and apply the appropriate ETL (i.e. remove Tweetbots) or modeling in another process, but you get the idea here. For another great look at the new SentiWordnet operator, check out this post by Andrew.
Pro Tip: Check out the Tutorials page for more great RapidMiner tutorials.