Pregled bibliografske jedinice broj: 1154875
A Method for MBTI Classification based on Impact of Class Components
A Method for MBTI Classification based on Impact of Class Components // IEEE Access, 9 (2021), 146550-146567 doi:10.1109/access.2021.3121137 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1154875 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A Method for MBTI Classification based on Impact of
Class Components
Autori
Cerkez, Ninoslav ; Vrdoljak, Boris ; Skansi, Sandro
Izvornik
IEEE Access (2169-3536) 9
(2021);
146550-146567
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
Binary classification, compound class labels, cross-entropy loss, custom loss function, deep learning, machine learning, MBTI, Myers-Briggs Type Indicator, multiclass classification, natural language processing, personality computing
Sažetak
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.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Interdisciplinarne tehničke znanosti, Informacijske i komunikacijske znanosti, Psihologija, Kognitivna znanost (prirodne, tehničke, biomedicina i zdravstvo, društvene i humanističke znanosti)
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Fakultet hrvatskih studija, Zagreb,
Visoka škola za informacijske tehnologije, Zagreb
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus