Computational Personality Recognition and Sentiment Analysis of Select Novels of Cormac McCarthy
Analyzing human language is often a complicated process as it requires dealing with grammatical nuances and linguistic variations of great magnitude. Lack of contextual understanding makes the process of extracting sentiment problematic, but the advances in computational techniques can facilitate th...
Saved in:
Published in | ICFAI journal of English studies Vol. 15; no. 3; pp. 92 - 102 |
---|---|
Main Author | |
Format | Journal Article |
Language | English |
Published |
Hyderabad
IUP Publications
01.09.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Analyzing human language is often a complicated process as it requires dealing with grammatical nuances and linguistic variations of great magnitude. Lack of contextual understanding makes the process of extracting sentiment problematic, but the advances in computational techniques can facilitate the process of regulating the emotion and tone behind a series of texts and derive the attitude, emotion, and opinion of the speaker. Sentiment analysis or opinion mining observes conversations and calculates language and voice inflections to quantify the opinions or emotions of the given database. It is a technique used for determining the expression and tone underlined in the data. Sentiment analysis can be automated wholly or centered on analysis of human or a combination of these two aspects. It provides visual representation of sentiment density and text polarity and enhances the possibilities of interpretation. This paper attempts to analyze personality traits based on computational methods in select novels of Cormac McCarthy. An analysis of the characters portrayed in literary texts is made referring to psychological measurements, employing text analysis tools. The focus is on the efficiency of bringing together advanced text analytics tools and theories of human personality for a better understanding of human personality. |
---|---|
ISSN: | 0973-3728 |