Hybrid text affect sensing system for emotional language analysis

Abstract

It is argued that for a computer to be able to interact with humans it needs to have the communication skills of humans. One of the main skills of human computer intelligent interaction is the affective aspect of communication, and language is one of the main ways for humans to express emotions. In order to analyze the emotions in language, it is necessary to study the general tone of conversation and the semantic content. This paper explores the influence of affective information about words in sentiment analysis and presents a hybrid statistical-semantic system for opinion detection in Spanish language texts. Affect sensing analysis in language content is very important for achieving realistic interaction with intelligent virtual agents, however it is still an unexplored field nowadays.