Personality Classification Experiment by Applying k-Means Clustering
INTERNATIONAL JOURNAL OF EMERGING TECHNOLOGIES IN LEARNING, cilt.15, sa.16, ss.162-177, 2020 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 15 Sayı: 16
- Basım Tarihi: 2020
- Doi Numarası: 10.3991/ijet.v15i16.15049
- Dergi Adı: INTERNATIONAL JOURNAL OF EMERGING TECHNOLOGIES IN LEARNING
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, Compendex, EBSCO Education Source, INSPEC, Directory of Open Access Journals
- Sayfa Sayıları: ss.162-177
- Süleyman Demirel Üniversitesi Adresli: Hayır
Özet
This paper describes personality classification experiment by applying k-means clustering machine learning algorithms. Several previous studies have been attempted to predict personality types of human beings automatically by using various machine learning algorithms. However, only few of them have obtained good accuracy results. To classify a person into personality types, we used Jungian Type Inventory. Our method consists of three parts: data collection, data preparation, and hyper-parameter tuning. Our testing results showed that the k-means model has 107 inertia value, which is a good number for an unsupervised learning model as an interim result. With the result, we divided the data into 16 clusters, which can be considered as personality types. We continue this research with analysis of large data to be collected in the future.