iFeel: A Web System that Compares and Combines Sentiment Analysis Methods

Sentiment analysis methods are used to detect polarity in thoughts and opinions of users in online social media. As businesses and companies are interested in knowing how social media users per-ceive their brands, sentiment analysis can help better evaluate their product and advertisement campaigns. In this paper, we present iFeel, a Web application that allows one to detect sentiments in any form of text including unstructured social media data. iFeel is free and gives access to seven existing sentiment analysis methods: Sen-tiWordNet, Emoticons, PANAS-t, SASA, Happiness Index, Sentic-Net, and SentiStrength. With iFeel, users can also combine these methods and create a new Combined-Method that achieves high coverage and F-measure. iFeel provides a single platform to com-pare the strengths and weaknesses of various sentiment analysis methods with a user friendly interface such as file uploading, graph-ical visualizing, and weight tuning