Prediksi Tipe Kepribadian Berdasaran Myers-Briggs Type Indicator Menggunakan Metode Klasifikasi Kolmogorov-Arnold Networks

Syamsudin, Afifah Nur Sabrina (2025) Prediksi Tipe Kepribadian Berdasaran Myers-Briggs Type Indicator Menggunakan Metode Klasifikasi Kolmogorov-Arnold Networks. Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 05111940000022-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (1MB) | Request a copy

Abstract

Pembahasan mengenai prediksi tipe kepribadian di media sosial telah meningkat pesat dalam beberapa tahun terakhir. Salah satu tes kepribadian yang ramai diperbincangkan adalah Myers-Briggs Type Indicator (MBTI). MBTI merupakan sebuah metode penilaian kepribadian yang mengklasifikasikan individu ke dalam salah satu dari 16 tipe kepribadian berdasarkan empat dimensi utama: Ekstroversi-Introversi, Sensing-Intuition, Thinking-Feeling, dan Judging-Perceiving. Terdapat banyak cara dalam memprediksi kepribadian seseorang salah satunya melalui analisis tipe kepribadian berdasarkan tulisan di media sosial, metode yang umum digunakan melibatkan beberapa tahapan analisis teks dan pemrosesan bahasa. Pada penelitian ini akan dipelajari proses dan kinerja dari model klasifikasi KAN. Metode klasifikasi baru ini diharapkan dapat digunakan sebagai cara untuk mengkategorikan teks ke dalam tipe kepribadian yang sesuai. Hasil dari penelitian ini nantinya diharapkan dapat mengetahui penggunaan kata pada unggahan media sosial terhadap tipe kepribadian seseorang serta kinerja model klasifikasi dalam mengenali tipe kepribadian berdasarkan aktivitas media sosial. Hasil dari uji coba pada implementasi metode KAN mendapatkan akurasi data uji senilai 0,2545.
===================================================================================================================================
Discussions about personality type prediction on social media have increased rapidly in recent years. One of the most discussed personality tests is the Myers-Briggs Type Indicator (MBTI). MBTI is a personality assessment method that classifies individuals into one of 16 personality types based on four main dimensions: Extroversion-Introversion, Sensing-Intuition, Thinking-Feeling, and Judging-Perceiving. There are many ways to predict a person's personality, one of which is through analyzing personality types based on social media posts, a commonly used method involving several stages of text analysis and language processing. In this research, the process and performance of the KAN classification model will be explained. This new classification method is expected to be used to categorize text into the appropriate personality type. The results of this research are expected to determine the use of words in social media posts on a person's personality type and the performance of the classification model in recognizing personality types based on social media activities. The results of the trial on the KAN method show that the implementation gets a test data metric accuracy of 0.2545.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Tipe Kepribadian, Myers-Briggs Type Indicator, Klasifikasi, Kolmogorov-Arnold Networks, Personality Types, Classification
Subjects:	T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Afifah Nur Sabrina Syamsudin
Date Deposited:	04 Feb 2025 00:44
Last Modified:	04 Feb 2025 00:44
URI:	http://repository.its.ac.id/id/eprint/117237

Actions (login required)

View Item