MOBILE APP DEVELOPMENT FOR TRACKING AND CLASSIFYING MOOD WITH ON-DEVICE ARTIFICIAL NEURAL NETWORK MODEL

Saraswati, Desak Putu Mahadewi (2026) MOBILE APP DEVELOPMENT FOR TRACKING AND CLASSIFYING MOOD WITH ON-DEVICE ARTIFICIAL NEURAL NETWORK MODEL. Undergraduate thesis, Universitas Pendidikan Ganesha.

[img] Text (COVER)
2115101001-COVER.pdf
Download (2MB)
[img] Text (ABSTRAK)
2115101001-ABSTRAK.pdf
Download (315kB)
[img] Text (BAB 1 PENDAHULUAN)
2115101001-BAB 1 PENDAHULUAN.pdf
Download (478kB)
[img] Text (BAB 2 LANDASAN TEORI)
2115101001-BAB 2 LANDASAN TEORI.pdf
Restricted to Repository staff only
Download (889kB) | Request a copy
[img] Text (BAB 3 METODELOGI PENELITIAN)
2115101001-BAB 3 METODELOGI PENELITIAN.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
[img] Text (BAB 4 HASIL DAN PEMBAHASAN)
2115101001-BAB 4 HASIL DAN PEMBAHASAN.pdf
Restricted to Repository staff only
Download (4MB) | Request a copy
[img] Text (BAB 5 PENUTUP)
2115101001-BAB 5 PENUTUP.pdf
Restricted to Repository staff only
Download (463kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
2115101001-DAFTAR PUSTAKA.pdf
Download (456kB)
[img] Text (LAMPIRAN)
2115101001-LAMPIRAN.pdf
Download (8MB)

Abstract

Mental health problems, particularly mood disorders, are increasingly prevalent among adolescents and young adults. Limited access to mental health services, social stigma, and low awareness lead many individuals to rely on self-help strategies to manage their emotional well-being. Mood tracking and journaling have been shown to enhance emotional awareness by helping users identify mood patterns and daily triggers. However, conventional journaling methods are often perceived as inefficient and lack user engagement. Therefore, this research develops a mobile application for mood tracking and classification integrated with an on-device Artificial Neural Network (ANN) model. The application enables users to record daily moods and activities, which are processed to classify average daily mood while preserving user privacy through on-device computation. This approach reduces dependency on cloud services and addresses privacy concerns when handling sensitive personal data. The system was developed using the Waterfall method, encompassing analysis, design, implementation, testing, deployment, and maintenance phases. During the analysis stage, the Design Thinking approach was applied to understand user needs. The system was implemented using Kotlin with Room Database as the local database. The target users are individuals aged 15–25 years, including students and workers. The design and features were evaluated by users and validated by a psychology expert to ensure psychological safety. System evaluation included unit testing, black-box testing, and usability evaluation. Unit testing demonstrated that all core functions operated successfully. Black-box testing with 10 users across 15 scenarios confirmed expected system behavior. Usability evaluation using the System Usability Scale (SUS) with 37 respondents resulted in an average score of 85.54, categorized as Acceptable, rated Excellent, assigned Grade A, and positioned above the 90th percentile. Net Promoter Score (NPS) results placed the proposed system in the promoter category. These results indicate that the system is usable and effective in supporting users' emotional self-reflection.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Mental Health, Mood Tracking, Mobile Application, Artificial Neural Network, User Experience
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Teknik dan Kejuruan > Jurusan Teknik Informatika > Program Studi Ilmu Komputer (S1)
Depositing User: DESAK PUTU MAHADEWI SARASWATI
Date Deposited: 26 Jan 2026 08:21
Last Modified: 26 Jan 2026 08:21
URI: http://repo.undiksha.ac.id/id/eprint/27785

Actions (login required)

View Item View Item