Recognizing Emotion Presence in Natural Language Sentences

Emotions constitute a key factor in human communication. Human emotion can be expressed through various mediums such as speech, facial expressions, gestures and textual data. A quite common way for people to communicate with each other and with computer systems is via written text. In this paper we present an emotion detection system used to automatically recognize emotions in text. The system takes as input natural language sentences, analyzes them and determines the underlying emotion being conveyed. It implements a keyword-based approach where the emotional state of a sentence is constituted by the emotional affinity of the sentence’s emotional words. The system uses lexical resources to spot words known to have emotional content and analyses sentence structure to specify their strength. Experimental results indicate quite satisfactory performance.