Dive deeper: Deep Semantics for Sentiment Analysis

This paper illustrates the use of deep semantic processing for sentiment analysis. Existing methods for sentiment analysis use supervised approaches which take into account all the subjective words and or phrases. Due to this, the fact that not all of these words and phrases actually contribute to the overall sentiment of the text is ignored. We propose an unsupervised rule-based approach using deep semantic processing to identify only relevant subjective terms. We generate a UNL (Universal Networking Language) graph for the input text. Rules are applied on the graph to extract relevant terms. The sentiment expressed in these terms is used to figure out the overall sentiment of the text. Results on binary sentiment classification have shown promising results.