Psyche Mining with PsycheTagger - A C omputational Linguistics Approach to Text Mining

The human elements of personality working behind the creation of a write-up play an important part in determining the final dominant mood of a text. This article is a detailed description of a formal research in Text Mining using purpose-built Computational Intelligence tools, PsycheMap and PsycheTagger. PsycheMap is created to classify documents based on emotive content, while PsycheTagger, is the first semantic emotive statistical tagger in English Language. Working in the lines of statistical Parts-of-Speech Taggers, this tool is adapted to perform efficiently and accurately for emotive content. The tagger self-ranks its choices with a probabilistic score, calculated using Viterbi algorithm run on a Hidden Markov Model of the psyche categories. The results of the classification and tagging exercise are critically evaluated on the Likert scale. These results strongly justify the validity and determine high accuracy of tagging using the probabilistic parser. Moreover, the six-step mining implementation provides a linguistic approach to model semi- structured semantic dataset for classification and labeling of any set of meaningful conceptual classes in English Language Corpus.