THE IMPLEMENTATION OF A CHATBOT TO PREDICT STUDENTS’ STRESS LEVEL USING NATURAL LANGUAGE PROCESSING ALGORITHM AT MAN 1 INDRAMAYU

SUDRAJAT, MUHAMMAD ROFIQ (2025) THE IMPLEMENTATION OF A CHATBOT TO PREDICT STUDENTS’ STRESS LEVEL USING NATURAL LANGUAGE PROCESSING ALGORITHM AT MAN 1 INDRAMAYU. Tugas Akhir thesis, Informatics.

[img] Text
5210411316_Muhammad Rofiq Sudrajat_Abstrak.pdf
Download (42kB)

Abstract

Stress is a common issue among students at State Islamic Senior High School (MAN) 1 Indramayu and, if left unaddressed, can negatively impact academic performance and mental well-being. This study aims to develop a chatbot capable of automatically predicting students' stress levels using a Natural Language Processing (NLP) approach. The methodology includes collecting labeled textual data based on psychological indicators, preprocessing the data, vectorizing it using TF-IDF, and applying the Naïve Bayes algorithm for classification. Stress level assessment is conducted using the PSS-10 questionnaire, and the system is integrated with the Gemini API to provide responsive and personalized coping recommendations based on the predicted stress level. The testing results demonstrate that the Naïve Bayes model with TF-IDF achieved an accuracy of 94.3%, with precision, recall, and F1-score values each reaching 94%, indicating consistent performance in classifying stressed and non-stressed data. Beyond accurate predictions, the system is also capable of delivering automated, tailored recommendations. Functional testing confirmed the chatbot performs effectively, making it a promising tool to support digital and sustainable student counseling services. Keywords: Chatbot, Stress, Natural Language Processing, Naïve Bayes, PSS-10.

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 16 Jul 2025 06:56
Last Modified: 16 Jul 2025 06:56
URI: http://eprints.uty.ac.id/id/eprint/18169

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.