Garuda - Garba Rujukan Digital

Perbandingan Pelabelan Data dalam Analisis Sentimen Kurikulum Proyek di platform TikTok: Pendekatan Naïve Bayes Pratiwi, Anissya Agsani; Kamayani, Mia
Jurnal Eksplora Informatika Vol 14 No 1 (2024): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v14i1.1093

Penelitian ini fokus pada analisis sentimen mahasiswa terhadap perubahan kurikulum berbasis proyek di tingkat pendidikan tinggi yang menghilangkan kewajiban skripsi, Data sentimen diekspresikan melalui platform media sosial TikTok, dan algoritma Naïve Bayes digunakan untuk mengklasifikasikan sentimen menjadi positif atau negatif. Proses penelitian mencakup pengambilan data, pembersihan data, preprocessing data, pelabelan data, hingga klasifikasi menggunakan algoritma Naive Bayes. Penelitian ini melibatkan dua tahap pelabelan dalam 913 data: pelabelan pertama manual menghasilkan 510 sentimen positif dan 403 negatif, sementara pelabelan kedua otomatis dengan RapidMiner menghasilkan 415 sentimen positif dan 498 negatif. Beberapa mahasiswa memberikan ulasan positif menganggap hal ini sebagai langkah inovatif untuk persiapan di dunia kerja. Meskipun beberapa merasa khawatir dengan tingkat kesulitan yang lebih tinggi. Hasil penelitian menunjukkan mayoritas tanggapan positif terhadap kurikulum berbasis proyek, dengan nilai pelabelan manual mencapai accuracy 93.98%, precision 100%, recall 87.99%. Sedangkan pelabelan otomatis dengan Rapidminer memperoleh nilai accuracy 70.41%, precision 80.15%, recall 69.96%.

FAKTOR-FAKTOR YANG MEMPENGARUHI MINAT CALON MAHASISWA BARU MENDAFTAR PADA FTII UHAMKA MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (K-NN) Rahman Malik, Luqman Abdur; Kamayani, Mia; Hasan, Firman Noor
Infotech: Journal of Technology Information Vol 9, No 1 (2023): JUNI
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v9i1.163

In accepting new students at Prof. University. Dr. Hamka, many prospective students or parents of students are looking for registration information, this is a great opportunity for Uhamka to gain the sympathy of prospective students to register at Uhamka, especially the Faculty of Industrial and Informatics Technology. The problem in this study is that there is no data processing related to the factors that influence the interest of prospective new students to choose the Faculty of Industrial and Informatics Technology (FTII) Uhamka. The purpose of this study was to determine the factors that influence the interest of prospective new students in choosing majors at the Faculty of Industrial and Information Technology (FTII) Uhamka. The attributes used in this study were 10 attributes, namely full name, major, tuition fee, FII location with domicile, presence of friends/family, accreditation, facilities, PMB services, PMB information, and information of interest. The method that researchers use in this study is the K-Nearest Neighbor Algorithm (K-NN). From the results of testing the researchers used the K-5 fold technique and the confusion matrix obtained an average accuracy of 72.5%, which means it is good.

Menerapkan Algoritma Neural Network Pada Chatbot Mengenai Pariwisata Di Provinsi Bangka Belitung Mahendra, Ristian; Kamayani, Mia
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.678

Bangka Belitung Province, precisely in South Bangka regency, is one of the areas that have the potential to be visited by tourists. However, not all attractions are known by tourists due to lack of information. From these problems, researchers tried to develop a chatbot system. Chatbot is a program that conducts conversations between humans and machines using human language. This chatbot system aims to help tourists do questions and answers automatically to find information about tourist attractions in South Bangka. The chatbot system applies a model with a natural language processing approach and neural network algorithms. This study aims to create a chatbot model that can provide information with good accuracy about paratourism in Bangka Belitung Province, especially South Bangka district. The data used in this study were the results of interviews and filling out questionnaires to the community. Then the data obtained is stored and converted into JSON format consisting of 173 tags, 618 patterns, and 187 responses. Then preprocessing the data was carried out by taking 25 random test questions. The results of the chatbot system accuracy test got an accuracy score of 92% from 25 questions asked randomly by getting an error value of 8%. From the results of accuracy testing, the chatbot system gets a response by looking at the appropriate questions asked by users based on tags, so that they can get the right answer.

Menerapkan Algoritma Neural Network Pada Chatbot Mengenai Pariwisata Di Provinsi Bangka Belitung Mahendra, Ristian; Kamayani, Mia
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.678

Bangka Belitung Province, precisely in South Bangka regency, is one of the areas that have the potential to be visited by tourists. However, not all attractions are known by tourists due to lack of information. From these problems, researchers tried to develop a chatbot system. Chatbot is a program that conducts conversations between humans and machines using human language. This chatbot system aims to help tourists do questions and answers automatically to find information about tourist attractions in South Bangka. The chatbot system applies a model with a natural language processing approach and neural network algorithms. This study aims to create a chatbot model that can provide information with good accuracy about paratourism in Bangka Belitung Province, especially South Bangka district. The data used in this study were the results of interviews and filling out questionnaires to the community. Then the data obtained is stored and converted into JSON format consisting of 173 tags, 618 patterns, and 187 responses. Then preprocessing the data was carried out by taking 25 random test questions. The results of the chatbot system accuracy test got an accuracy score of 92% from 25 questions asked randomly by getting an error value of 8%. From the results of accuracy testing, the chatbot system gets a response by looking at the appropriate questions asked by users based on tags, so that they can get the right answer.

Comparative Analysis of the Effectiveness of Informatics Course Learning Utilizing Chatgpt Utami, Arneitta Dwicahya; Kamayani, Mia; Siduningrum, Estu; Azhar, Nur Chalik
Acta Pedagogia Asiana Volume 4 - Issue 1 - 2025
Publisher : Tecno Scientifica Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53623/apga.v4i1.553

This study examined the effectiveness of conventional teaching methods and ChatGPT in an introductory Algorithms and Programming course at the university level. ChatGPT, an AI-based NLP technology, assisted students in understanding course material through automated responses. However, its effectiveness relative to conventional methods required further evaluation, particularly concerning motivation, interaction, self-regulation, instructional structure, and the instructor's role. Using a sample of 10 students for pretest-posttest analysis, 38 respondents for the User Experience Questionnaire (UEQ), and accuracy analysis via prompt engineering, the results revealed that conventional methods better enhanced motivation and interaction. ChatGPT demonstrated strengths in attractiveness (1.982) and efficiency (2.053) but scored lower in accuracy (1.395) and novelty (1.053). Prompt engineering significantly improved response accuracy when tailored to learning modules, highlighting the importance of precise inputs. The findings suggested that while ChatGPT excelled as a supplementary tool, it was less effective as a standalone teaching method. This study contributed to the growing field of educational technology by providing insights into the integration of AI tools in learning environments.

Implementasi Algoritma NaÃ¯ve Bayes Pada Analisis Sentimen Terhadap Ulasan Aplikasi DeepL Translate Di Play Store Komarudin, Ahmad; Ayyubi, Reza Al; Arif, Zainul; Kamayani, Mia
KOMPUTEK Vol. 8 No. 1 (2024): April
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/jkt.v8i1.2604

Perkembangan teknologi semakin maju dengan pesat, hingga terciptanya sebuah smartphone yang didalamnya tersedia berbagai fitur-fitur canggih. Play Store merupakan layanan yang dibuat oleh Google untuk pengunduhan berbagai aplikasi, game, buku digital, film secara gratis maupun berbayar. Salah satu aplikasi yang tersedia pada Play Store adalah DeepL Translate, yang merupakan aplikasi yang bisa menerjemahkan berbagai bahasa dengan menerapkan Artificial Intelegent (AI) didalamnya. Tujuan penelitian ini yaitu untuk mengevaluasi aplikasi DeepL Translate melalui analisis sentimen pada ulasan menggunakan algoritma NaÃ¯ve Bayes untuk mengetahui seberapa puas pengguna dalam menggunakan aplikasi ini. Pengambilan data ulasan dilakukan menggunakan teknik scrapping dengan Google Colab sebanyak 995 data, kemudian jumlah dataset berubah menjadi 939 ulasan setelah melalui proses preprocessing dengan data positif sebanyak 771 dan 168 untuk data negatif. Dataset kemudian diseimbangkan menggunakan SMOTE dan diklasifikasikan dengan algoritma NaÃ¯ve Bayes. Algoritma ini dipakai karena menggunakan probabilitas yang sederhana dan efektif dalam mengklasifikasikan sebuah data. Hasil implementasi algoritma diperoleh accuracy sebesar 93,71%, precision sebesar 98,84%, dan recall sebesar 88,85%, dengan teknik evaluasi yang digunakan adalah confussion matrix.

Perancangan Ulang Desain UI/UX pada Aplikasi ibisPaint X dengan Penerapan Metode The Wheel Novianti, Eka; Kamayani, Mia
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.614

Rapid technological developments have made smartphones not only function as communication devices, but can also be used as a place to draw digitally. Mobile-based graphic design applications, namely ibisPaint X. found problems experienced by users, such as difficulty in using the application, features that are difficult to find, and confusing displays. This study uses the wheel method to overcome problems faced by users which has four main stages, namely analysis, design, prototype, and evaluation focusing on user needs analysis, prototype design using figma, and usability testing using a system usability scale to measure the effectiveness of the resulting design. The results of this study showed a score before the redesign of 38.33, far from the minimum average value of the system usability scale of 68. After the redesign, the score increased very well, the score obtained was 82 indicating success in improving user experience and needs. Changes occurred on the login page, main menu, and the presence of a brush type search feature to make it easier for users when using the ibisPaint X application. This study provides a good contribution to the development of the ibisPaint X application in meeting user needs and is expected to be a reference in order to compete in the increasingly advanced digital era.

Evaluation of Computer Lab at XYZ Institution using BAI & DSS Domains of COBIT 2019 Febriawan, Dimas; Kamayani, Mia; Imanda, Rahmi
Jurnal Ilmiah Matrik Vol. 27 No. 2 (2025): Jurnal Ilmiah Matrik
Publisher : Direktorat Riset dan Pengabdian Pada Masyarakat (DRPM) Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33557/wsbeqv24

This research aims to measure the IT governance implementation in the computer laboratory at XYZ Institution using COBIT 2019 framework. Based on the scope and the problems that were identified, BAI and DSS aspects are the domains chosen to measure the implementation of the IT governance. The methods for this research are focus group discussion and field assessment. The BAI and DSS domains consist of 16 objectives, which are then divided into 104 practices and then divided further into 535 activities. These 535 activities are the processes that we have to determine for each capability level. After determining the capability levels for each process, we summarized the values and then evaluated the average values for each objective. These average values are the values that we used to determine the capability levels for each objective. We presented the result of our self assessment using a radar diagram. XYZ Institution is still in the starting phase of having good IT governance. This condition is reflected by the achievement of each objective’s capability levels ranging from 1 to 2. In addition to this condition, there is only one objective that meets the Institution’s capability level target of 3.

Implementasi CMS Pada Media Pembelajaran Mengenal Alat Musik Tradisional Indonesia Sinduningrum, Estu; Suhendra, Renadi Fadino; Kamayani, Mia
MULTINETICS Vol. 4 No. 2 (2018): MULTINETICS Nopember (2018)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v4i2.1345

Traditional musical instruments were born and developed throughout the archipelago in Indonesia, which is still a hereditary habit in the community to date. This musical instrument is spread in almost all corners of the country and each region has different characteristics. Children in learning and knowing traditional musical instruments are less desirable because traditional musical instruments are considered outdated and old-fashioned, so they are reluctant to learn them. children are made media to introduce traditional CMS-based musical instruments and musical instruments made in 3D, so children want to know and learn traditional musical instruments. System modeling on the construction of this CMS use UML (Unified Modelling Language) with tool activity diagram, use case, class diagram and developed using the method waterfall which is run on system. System testing is permormed using alpha testing and beta testing, for beta testing is done by distributing the system testing questionnaire to the 15 listed respondent. For the result of the percentage is 86,67%, which means the result of this CMS assessment can be categorized very well.

Perbandingan Pelabelan Data dalam Analisis Sentimen Kurikulum Proyek di platform TikTok: Pendekatan Naïve Bayes Pratiwi, Anissya Agsani; Kamayani, Mia
Eksplora Informatika Vol 14 No 1 (2024): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v14i1.1093

Penelitian ini fokus pada analisis sentimen mahasiswa terhadap perubahan kurikulum berbasis proyek di tingkat pendidikan tinggi yang menghilangkan kewajiban skripsi, Data sentimen diekspresikan melalui platform media sosial TikTok, dan algoritma Naïve Bayes digunakan untuk mengklasifikasikan sentimen menjadi positif atau negatif. Proses penelitian mencakup pengambilan data, pembersihan data, preprocessing data, pelabelan data, hingga klasifikasi menggunakan algoritma Naive Bayes. Penelitian ini melibatkan dua tahap pelabelan dalam 913 data: pelabelan pertama manual menghasilkan 510 sentimen positif dan 403 negatif, sementara pelabelan kedua otomatis dengan RapidMiner menghasilkan 415 sentimen positif dan 498 negatif. Beberapa mahasiswa memberikan ulasan positif menganggap hal ini sebagai langkah inovatif untuk persiapan di dunia kerja. Meskipun beberapa merasa khawatir dengan tingkat kesulitan yang lebih tinggi. Hasil penelitian menunjukkan mayoritas tanggapan positif terhadap kurikulum berbasis proyek, dengan nilai pelabelan manual mencapai accuracy 93.98%, precision 100%, recall 87.99%. Sedangkan pelabelan otomatis dengan Rapidminer memperoleh nilai accuracy 70.41%, precision 80.15%, recall 69.96%.

Title

Found 15 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 15 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 15 Documents
Search