Fig 1 - available via license: Creative Commons Attribution-ShareAlike 4.0 International
Content may be subject to copyright.
Download
View publication
A chart with descriptions of each Myers-Briggs personality type [24]

A chart with descriptions of each Myers-Briggs personality type [24]

Source publication
Fig. 1. A chart with descriptions of each Myers-Briggs personality type...
Fig. 5. Proportionality diagram of "MBTI" types
Fig. 8. Unique word cloud for individual "MBTI" types
Fig. 9. "MBTI" Personality Type Dataset [12]
Personality Type Based on Myers-Briggs Type Indicator with Text Posting Style by using Traditional and Deep Learning
Preprint
Full-text available
  • Jan 2022
The term personality may be expressed in terms of the individual differences in characteristics pattern of thinking, feeling, and behavior. This work presents several machine learning techniques including Naive Bayes, Support Vector Machines, and Recurrent Neural Networks to predict people personality from text based on Myers-Briggs Type Indicator...
Cite
Download full-text

Contexts in source publication

Context 1
... Type Indicator" by a psychiatrist named "Carl Jung". Then, "Katharine Briggs" and "Isabel Myers Briggs" created the "Myers-Briggs Type Indicator" for testing personality in the 1920s, based on "Jung's theory of psychological types" [5,8,30]. This model instrument has 16 personality types represented by a "personality types key" as shown in Fig. 1 [7]. In the "MBTI" system, for example, people classified as "INTPs" prefer "Introversion (I)", "Intuition (N)", "Thinking (T)", and "Perception (P)" personality traits. We can classify the needs or behaviors of individuals according to labels, and then the machine can learn the ...
Context 2
... on "Recurrent Neural Networks" As shown in Fig. 10, we utilize the embedding word to define the indexes into dense vectors of fixed size with a total length of vocabulary of 256. We decided to utilize "CONV1D" on "Recurrent Neural Networks" because "CONV1D" moves along a single axis. It makes perfect sense to apply this type of convolution layer to sequential data, such as text. Then, ...
Context 3
... we utilize the embedding word to define the indexes into dense vectors of fixed size with a total length of vocabulary of 256. We decided to utilize "CONV1D" on "Recurrent Neural Networks" because "CONV1D" moves along a single axis. It makes perfect sense to apply this type of convolution layer to sequential data, such as text. Then, as shown in Fig. 11, to improve the performance of the "Recurrent Neural Networks" model, we added "Bi-directional Long Short-Term Memory (BI-LSTM)" with a size of 64, allowing the "Recurrent Neural Networks" to store sequence information in both directions, backward (future to past) and forward (past to future). Table I shows that the "Recurrent Neural ...
Context 4
... the "Recurrent Neural Networks" outperform, the confusion matrix of the "Recurrent Neural Networks" model is shown in Fig. 12. For each "MBTI" model, the results are mostly positioned as "True Positive" which means they are projected as positive and turn out to be true. which is a false positive, implying that the prediction is positive but ...
Context 5
... the classification report of the "Recurrent Neural Networks" is shown in Fig. 13 and Fig. 14. This shows that the F-score or F-measure, which is a weighted average score of the true positive (recall) and precision, is around 76% when (2) calculated as the mean of all ...