Statistical estimation of emotions in speech notes by featured term analogy

Abstract

Human Being is the only creature in the World who can express his emotions in various forms. Capturing the extent of emotions in a particular speech notes through quantification of verbal expressions is undoubtedly a challenging area to study. Either positive or negative, whatever be the emotions are in the notes, if we succeed in assessing the degree of positiveness or negativeness, the impact of the notes while addressing to the intended people can be pre-estimated easily. This paper presents a brief idea of how we can statistically estimate the emotional characteristics of a speech notes by analyzing the content in the speech notes through Information Extraction. Since it is mandatory for any sentence to have atleast a verb, we primarily concentrate on the verbs as featured terms in each sentence and there by statistically estimate the rigorousness of the verb on the entire speech note. The strength of the verb in its severity can be measured by comparing it with strong, medium, light corpus of emotions developed specially. This enables to judge the effectiveness of a speech notes in various emotions.