INVESTIGATION ON TEXT CONTENT ORIENTED EMOTION IDENTIFICATION

Abstract
Human-Computer interaction (HCI) researches the use of computer technology mainly focused on the interfaces between human users and computers. Researchers in the domain of HCI observe the ways in which human users interact with computers and propose new technologies that let users interact with computers in narrative ways. Research in HCI is situated at the intersection of various fields like computer science, design, behavioral sciences, media studies and many more areas of study. In the world of digitization HCI is a very powerful and most relevant area of research and needs the digital systems to reproduce the human behavior appropriately. Emotion is one of the important aspects of human behavior and plays an important role in HCI. To exhibit accurately intelligent behavior, this needs to recognize the emotion of human behavior. There are various ways to express the Human emotions like facial expression, written content or texts and speech, nowadays enormous amount of textual data is generated and gathered into the cloud and social media and blogs are among others. This research paper investigates on the overview of emotion recognition from various texts and expresses the emotion detection methodologies. Boundaries of ‘emotion detection methodologies’ are investigated in this paper, those are addressing the text normalization process of useful data using various handling techniques for both plain text and short messages. This paper combines the two most common approaches to emotion classification in text: the rule based approach and the machine learning approach and compares the performance of various classification algorithms.

Authors
S R Adarsh
Samsung R&D Institute, Karnataka, India

Keywords
Human-Computer Interaction, Facial Expression, Plain Text and Language Processing Tools
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 9 , Issue: 2 )
Date of Publication :
Januray 2019
DOI :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.