Are You an Introvert or Extrovert? Accurate Classification With Only Ten Predictors

Research output: Contribution to journalArticle

1 Downloads (Pure)

Abstract

This paper investigates how accurately the prediction of being an introvert vs. extrovert can be made with less than ten predictors. The study is based on a previous data collection of 7161 respondents of a survey on 91 personality and 3 demographic items. The results show that it is possible to effectively reduce the size of this measurement instrument from 94 to 10 features with a performance loss of only 1%, achieving an accuracy of 73.81% on unseen data. Class imbalance correction methods like SMOTE or ADASYN showed considerable improvement on the validation set but only minor performance improvement on the testing set.
Original languageUndefined/Unknown
Journal International Conference on Artificial Intelligence in Information and Communication
Publication statusAccepted/In press - 2020 Feb 29

Bibliographical note

To be published in IEEE conference proceedings: 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Cite this