Sistem Pendukung Keputusan Pemilihan Jurusan Berbasis Analisis MBTI Menggunakan Data Teks Media Sosial
Abstract
Ketidaksesuaian antara kepribadian mahasiswa dengan jurusan kuliah yang dipilih sering kali menyebabkan penurunan motivasi belajar, rendahnya prestasi akademik, hingga peningkatan risiko putus studi. Faktor penyebabnya antara lain kurangnya pemahaman diri, pengaruh tren atau tekanan eksternal, serta keterbatasan layanan konseling karier. Penelitian ini mengembangkan sistem rekomendasi jurusan kuliah berbasis analisis kepribadian Myers-Briggs Type Indicator (MBTI) dengan memanfaatkan data media sosial dan metode machine learning. Data dikumpulkan dari platform X (Twitter) melalui scraping akun pengguna yang mencantumkan tipe MBTI pada profil, kemudian diproses melalui tahapan pre-processing meliputi tokenisasi, penghapusan stopword, lemmatisasi, normalisasi bahasa tidak baku, dan penghapusan emoji. Fitur yang digunakan mencakup Term Frequency–Inverse Document Frequency (TF-IDF), analisis sentimen, dan distribusi topik untuk menangkap pola linguistik yang relevan.
Enam algoritma machine learning diuji, yaitu XGBoost, AdaBoost, Gradient Boosting, Support Vector Machine (SVM), Complement Naive Bayes, dan Logistic Regression. Hanya algoritma SVM dengan akurasi sebesar 84% dan Logistic Regression dengan akurasi 83% yang berhasil melampaui target minimum akurasi sebesar 80%. Sementara itu, model lain seperti XGBoost, Gradient Boosting, AdaBoost, dan Complement Naive Bayes masih menunjukkan akurasi yang lebih rendah, yakni pada rentang 60% hingga 72%. Model terbaik diimplementasikan pada aplikasi web berbasis Flask yang dapat memprediksi tipe MBTI dari input teks manual maupun postingan terbaru akun X, kemudian memetakan hasilnya ke rekomendasi jurusan yang relevan. Uji coba kepada responden menunjukkan 85% merasa rekomendasi yang diberikan sesuai dengan minat dan karakter mereka. Temuan ini membuktikan bahwa analisis kepribadian berbasis machine learning dari data media sosial berpotensi menjadi alat bantu pengambilan keputusan akademik yang efektif.
Kata Kunci: Analisis Kepribadian, MBTI, Rekomendasi Jurusan Kuliah, Model Algoritma, Flask.
References
Z. Mushtaq, S. Ashraf, and N. Sabahat, “Predicting MBTI Personality type with K-means Clustering and Gradient Boosting,” Proc. - 2020 23rd IEEE Int. Multi-Topic Conf. INMIC 2020, no. November 2020, 2020, doi: 10.1109/INMIC50486.2020.9318078.
Mawadatul Maulidah, “Klasifikasi Kepribadian Menggunakan Algoritma Machine Learning,” J. Inform. Dan Tekonologi Komput., vol. 3, no. 1, pp. 66–73, 2023, doi: 10.55606/jitek.v3i1.1292.
R. S. Z. Sungjun Won, Eric M. Anderman, “Longitudinal Relations of Classroom Goal Structures to Students’ Motivation and Learning Outcomes in Health Education,” vol. 5079, no. November, 2019.
S. C. Hamm, “The Myers- Briggs Type Indicator and a Student’s College Major,” J. Undergrad. Res. Sch. Work, vol. IV, pp. 1–19, 2019, [Online]. Available: http://rr.lib.utsa.edu/handle/20.500.12588/65
Y. Mehta, N. Majumder, A. Gelbukh, and E. Cambria, “Recent trends in deep learning based personality detection,” Artif. Intell. Rev., vol. 53, no. 4, pp. 2313–2339, 2020, doi: 10.1007/s10462-019-09770-z.
Wijoyo A, Saputra A, Ristanti S, Sya’ban S, Amalia M, and Febriansyah R, “Pembelajaran Machine Learning,” OKTAL (Jurnal Ilmu Komput. dan Sci., vol. 3, no. 2, pp. 375–380, 2024, [Online]. Available: https://journal.mediapublikasi.id/index.php/oktal/article/view/2305
F. Huang, X. Li, C. Yuan, S. Zhang, J. Zhang, and S. Qiao, “Attention-Emotion-Enhanced Convolutional LSTM for Sentiment Analysis,” IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 9, pp. 4332–4345, 2022, doi: 10.1109/TNNLS.2021.3056664.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.
P. Beja-Battais, “Overview of AdaBoost : Reconciling its views to better understand its dynamics,” 2023, [Online]. Available: http://arxiv.org/abs/2310.18323
Y. Freund and R. E. Schapire, “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” J. Comput. Syst. Sci., vol. 55, no. 1, pp. 119–139, 1997, doi: 10.1006/jcss.1997.1504.
J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001, doi: 10.1214/aos/1013203451.
G. L. Praphulla, I. B. Kishore, B. Venkatesh, B. Praveen, and P. S. Rao, “Personality Prediction Using Machine Learning Techniques,” AIP Conf. Proc., vol. 2794, no. 1, pp. 41–44, 2023, doi: 10.1063/5.0174316.
Z. He, D. Lin, T. Lau, and M. Wu, “Gradient Boosting Machine: A Survey,” pp. 1–9, 2019, [Online]. Available: http://arxiv.org/abs/1908.06951
L. W. Rizkallah, “Optimizing SVM hyperparameters for satellite imagery classification using metaheuristic and statistical techniques,” Int. J. Data Sci. Anal., 2025, doi: 10.1007/s41060-025-00762-7.
J. Watt, L. Mitchell, and J. Tuke, “Personality Profiling: How informative are social media profiles in predicting personal information?,” Proc. Australas. Lang. Technol. Work., vol. 22, pp. 153–163, 2024.
S. J. Lin, C. C. Liu, D. M. T. Tsai, Y. H. Shih, C. L. Lin, and Y. C. Hsu, “Prediction Models Using Decision Tree and Logistic Regression Method for Predicting Hospital Revisits in Peritoneal Dialysis Patients,” Diagnostics, vol. 14, no. 6, pp. 1–13, 2024, doi: 10.3390/diagnostics14060620.
scikit-learn, “LogisticRegression.” https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html (accessed Aug. 12, 2025).
J. D. M. Rennie, L. Shih, J. Teevan, and D. Karger, “Tackling the Poor Assumptions of Naive Bayes Text Classifiers,” Proceedings, Twent. Int. Conf. Mach. Learn., vol. 2, no. 1973, pp. 616–623, 2003.
Scikit-learn.org, “Naive Bayes.” https://scikit-learn.org/stable/modules/naive_bayes.html (accessed Aug. 12, 2025).
S. Ye et al., “Flask: Fine-Grained Language Model Evaluation Based on Alignment Skill Sets,” 12th Int. Conf. Learn. Represent. ICLR 2024, pp. 1–54, 2024.
Z. Khalid, “MBTI Personality Types 500 Datasetle.” 2021. [Online]. Available: https://www.kaggle.com/datasets/zeyadkhalid/mbti-personality-types-500-dataset
