A Method for MBTI Classification Based on Impact of Class Components

Predicting the personality type of text authors has a well-known usage in psychology with practical applications in business. From the data science perspective, we can look at this problem as a text classification task that can be tackled using natural language processing (NLP) and deep learning. Th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ninoslav Cerkez, Boris Vrdoljak, Sandro Skansi
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Binary classification compound class labels cross-entropy loss custom loss function deep learning machine learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/ed92212f07e44fd3a3b5f1f5f4a981fe
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ed92212f07e44fd3a3b5f1f5f4a981fe
record_format	dspace
spelling	oai:doaj.org-article:ed92212f07e44fd3a3b5f1f5f4a981fe2021-11-09T00:01:14ZA Method for MBTI Classification Based on Impact of Class Components2169-353610.1109/ACCESS.2021.3121137https://doaj.org/article/ed92212f07e44fd3a3b5f1f5f4a981fe2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9578983/https://doaj.org/toc/2169-3536Predicting the personality type of text authors has a well-known usage in psychology with practical applications in business. From the data science perspective, we can look at this problem as a text classification task that can be tackled using natural language processing (NLP) and deep learning. This paper proposes a method and a novel loss function for multiclass classification using the Myers–Briggs Type Indicator (MBTI) approach for predicting the author’s personality type. Furthermore, this paper proposes an approach that improves the current results of the MBTI multiclass classification because it considers components of compound class labels as supportive elements for better classification according to MBTI. As such, it also provides a new perspective on this classification problem. The experimental results on long short-term memory (LSTM) and convolutional neural network (CNN) models outperform baseline models for multiclass classification, related research on multiclass classification, and most research with four binary approaches to MBTI classification. Moreover, other classification problems that target compound class labels and label parts with binary mutually exclusive values can benefit from this approach.Ninoslav CerkezBoris VrdoljakSandro SkansiIEEEarticleBinary classificationcompound class labelscross-entropy losscustom loss functiondeep learningmachine learningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 146550-146567 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Binary classification compound class labels cross-entropy loss custom loss function deep learning machine learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Binary classification compound class labels cross-entropy loss custom loss function deep learning machine learning Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ninoslav Cerkez Boris Vrdoljak Sandro Skansi A Method for MBTI Classification Based on Impact of Class Components
description	Predicting the personality type of text authors has a well-known usage in psychology with practical applications in business. From the data science perspective, we can look at this problem as a text classification task that can be tackled using natural language processing (NLP) and deep learning. This paper proposes a method and a novel loss function for multiclass classification using the Myers–Briggs Type Indicator (MBTI) approach for predicting the author’s personality type. Furthermore, this paper proposes an approach that improves the current results of the MBTI multiclass classification because it considers components of compound class labels as supportive elements for better classification according to MBTI. As such, it also provides a new perspective on this classification problem. The experimental results on long short-term memory (LSTM) and convolutional neural network (CNN) models outperform baseline models for multiclass classification, related research on multiclass classification, and most research with four binary approaches to MBTI classification. Moreover, other classification problems that target compound class labels and label parts with binary mutually exclusive values can benefit from this approach.
format	article
author	Ninoslav Cerkez Boris Vrdoljak Sandro Skansi
author_facet	Ninoslav Cerkez Boris Vrdoljak Sandro Skansi
author_sort	Ninoslav Cerkez
title	A Method for MBTI Classification Based on Impact of Class Components
title_short	A Method for MBTI Classification Based on Impact of Class Components
title_full	A Method for MBTI Classification Based on Impact of Class Components
title_fullStr	A Method for MBTI Classification Based on Impact of Class Components
title_full_unstemmed	A Method for MBTI Classification Based on Impact of Class Components
title_sort	method for mbti classification based on impact of class components
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/ed92212f07e44fd3a3b5f1f5f4a981fe
work_keys_str_mv	AT ninoslavcerkez amethodformbticlassificationbasedonimpactofclasscomponents AT borisvrdoljak amethodformbticlassificationbasedonimpactofclasscomponents AT sandroskansi amethodformbticlassificationbasedonimpactofclasscomponents AT ninoslavcerkez methodformbticlassificationbasedonimpactofclasscomponents AT borisvrdoljak methodformbticlassificationbasedonimpactofclasscomponents AT sandroskansi methodformbticlassificationbasedonimpactofclasscomponents
_version_	1718441436135817216

A Method for MBTI Classification Based on Impact of Class Components

Ejemplares similares