Claim Missing Document
Check
Articles

Found 34 Documents
Search

ANALISIS SENTIMEN KEBIJAKAN KAMPUS MERDEKA MENGGUNAKAN NAÏVE BAYES BERDASARKAN KOMENTAR PADA YOUTUBE Rizky Herdiansyah, Moh; Yuliana, Ade
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 8 No. 6 (2024): JATI Vol. 8 No. 6
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v8i6.11963

Abstract

Perkembangan teknologi telah memudahkan akses informasi melalui internet dan mendorong pertumbuhan platform digital seperti YouTube, yang memberikan informasi dalam format audio-visual. Kementerian Pendidikan dan Kebudayaan (Kemendikbud) memanfaatkan YouTube sebagai media publikasi kebijakan "Kampus Merdeka," yang bertujuan mempersiapkan mahasiswa menghadapi kebutuhan zaman di tengah perubahan sosial, budaya, dunia kerja, dan teknologi. Kebijakan ini mendapat beragam tanggapan dari publik, baik positif maupun negatif, yang tercermin dalam kolom komentar video terkait. Untuk menganalisis sentimen masyarakat terhadap kebijakan ini, penelitian ini menggunakan crawling data di Google Colab dan algoritma Naive Bayes untuk klasifikasi sentimen dari komentar YouTube. Algoritma Naive Bayes dipilih karena memiliki keunggulan dalam komputasi cepat, kesederhanaan, dan tingkat akurasi yang baik dalam berbagai penelitian sebelumnya. Berdasarkan hasil klasifikasi sentimen terhadap 553 komentar di video "Kemerdekaan Belajar Episode: 2 'Kampus Merdeka'," ditemukan bahwa mayoritas sentimen publik bersifat positif, yaitu sebanyak 330 komentar, disusul oleh 78 komentar netral dan 110 komentar negatif. Analisis ini menunjukkan dukungan yang cukup kuat terhadap kebijakan "Kampus Merdeka," meskipun ada beberapa kritik. Hasil evaluasi algoritma Naive Bayes menunjukkan tingkat akurasi sebesar 70%, dengan presisi 79,72%, recall 70%, dan F1-score 62,57%.
Peningkatan Kapasitas Masyarakat Cimanggu Melalui Ecobrick dan Sabun Ramah Lingkungan sebagai Solusi Marlina, Lusi; Damayanti, Eva; Yuliana, Ade; Paryati, Retno
PUAN INDONESIA Vol. 6 No. 2 (2025): Jurnal Puan Indonesia Vol 6 No 2 Januari 2025
Publisher : ASOSIASI IDEBAHASA KEPRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37296/jpi.v6i2.329

Abstract

This community service activity aims to realize the work program of the chemical engineering study program, serve the community, build a spirit of mutual cooperation and social care, and prepare students in accordance with the development and demands of society. The target of the activity is the community of Cimanggu Village, Ngamprah District, West Bandung Regency. This activity is based on Pancasila, Tri Dharma Perguruan Tinggi, and chemical engineering study program. The activity took place over two days, June 24-25, 2023, in Cimanggu Village. The first day was filled with persuasion to the community, and the second day was filled with socialization about making ecoenzymes from vegetable and fruit waste as soil fertilizers, and making tofu nuggets with the residents. This activity has been carried out well, and the entire series of events have been realized, including persuasion of residents, making ecoenzymes, socializing tofu nuggets, and helping residents with gardening. The response of the residents was quite enthusiastic.
PEMBERDAYAAN KEMANDIRIAN EKONOMI DAN KESADARAN LINGKUNGAN MELALUI PELATIHAN PRODUKSI SABUN CUCI PIRING RAMAH LINGKUNGAN Yuliana, Ade; Andini, Melli; Purwani, Rina
Jurnal Gembira: Pengabdian Kepada Masyarakat Vol 3 No 01 (2025): FEBRUARI 2025
Publisher : Media Inovasi Pendidikan dan Publikasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pelatihan pembuatan sabun cuci piring ini ditujukan untuk Ibu-ibu PKK (Pemberdayaan dan Kesejahteraan Keluarga) RT 03 RW III di Kelurahan Rejasari, Kecamatan Purwokerto Barat, untuk meningkatkan keterampilan dan kemandirian ekonomi rumah tangga. Sabun cuci piring, sebagai kebutuhan sehari-hari, seringkali membebani anggaran keluarga. Peserta diajarkan cara membuat sabun yang ekonomis, efektif, dan ramah lingkungan menggunakan bahan-bahan yang mudah didapat. Program satu hari ini menggabungkan teori dan praktik langsung, mencakup komposisi bahan, teknik pembuatan, serta tips menghasilkan sabun berkualitas. Selain untuk kebutuhan rumah tangga, pelatihan ini juga membuka peluang penghasilan tambahan bagi Ibu-ibu PKK. Tujuannya adalah memberdayakan peserta untuk memproduksi sabun secara mandiri dan mempromosikan produk ramah lingkungan di masyarakat. Pelatihan ini juga mendorong semangat kewirausahaan dan kemandirian ekonomi di tingkat desa. Dengan mengurangi ketergantungan pada produk komersial, peserta dapat menciptakan usaha berkelanjutan yang memberikan manfaat lingkungan dan ekonomi. Inisiatif ini mendorong pengembangan keterampilan, kesadaran lingkungan, dan kemandirian finansial.
The Influence Of Social Media Influencers On The Buying Interest Of The Young Generation With Consumer Attitude As A Mediation Variable Yuliana, Ade; Novandari, Weni; Setyawati, Sri Murni
Jurnal Fokus Manajemen Vol 5 No 1 (2025): February
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jfm.v5i1.7975

Abstract

This research aims to examine the effectiveness of social media influencer advertising on Generation Y and Z, with a focus on source credibility and attractiveness in relation to purchase intention. The study proposes that consumer attitude mediates the relationship between social media influencer characteristics (both exogenous and endogenous) and purchase intention. Structural Equation Modelling (SEM) was employed to test the empirical models, with SMARTPLS and SPSS utilized for the analysis. A total of 193 respondents were sampled. The findings support all the hypotheses except for the direct relationship between source attractiveness and consumer attitudes. Additionally, the study demonstrates that generational differences act as moderating variables in the relationship between consumer attitude and purchase intention.
Bahasa Inggris: Bahasa Inggris Permatasari, Novelia Kiki; Sutihat, Eva; Yunita, Irma; Yuliana, Ade
Jurnal Minds: Manajemen Ide dan Inspirasi Vol 12 No 1 (2025): June
Publisher : Management Department, Universitas Islam Negeri Alauddin Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/minds.v12i1.51521

Abstract

This study investigates the impact of halal branding, brand image, and brand trust on purchasing decisions among Micro and Small Enterprises (MSEs). It contributes to academic discourse by examining how gender equality interacts with brand-related variables within the framework of the Sustainable Development Goals (SDGs)—a perspective rarely addressed in existing literature. Using data from 400 MSE actors selected through cluster sampling and analyzed via PLS-SEM, the study finds that halal branding, brand image, and brand trust each exert a positive and significant influence on consumer decisions. Interestingly, gender equality does not reinforce these relationships but instead appears to weaken them, suggesting that consumer responses may be shaped by deeper cultural and social currents. The findings encourage business actors to view halal branding and trust-building not merely as technical strategies but as part of a broader engagement with community values—requiring locally grounded approaches to gender inclusion and improved relationships.
PENGARUH PEMASARAN POLITIK MEDIA SOSIAL DAN KUALITAS INFORMASI TERHADAP NIAT MEMILIH DENGAN KEPERCAYAAN DAN LOYALITAS PEMILIH SEBAGAI MEDIASI Alim, Ikhwan Nur; Herdian Farisi; Yuliana, Ade
Jurnal Manajemen & Bisnis Jayakarta Vol 6 No 01 (2024): Vol. 06 No. 01 Juli 2024
Publisher : Sekolah Tinggi Ilmu Ekonomi Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53825/jmbjayakarta.v6i01.277

Abstract

This study seeks to determine how political marketing social media and information quality impact generation Z's voting intentions, using voter trust and loyalty as mediators. This study employed a quantitative approach, with 100 respondents selected by purposive selection. Data analysis shows that political marketing on social media increases voter trust and loyalty. The quality of information also has a positive impact, as greater quality information increases voters' confidence and trust, which can result in loyal voters. In addition, voter trust and loyalty influence voting intentions. The more voters trust politicians, the more likely they are to vote in elections.
Improving Diabetes Prediction Performance Using Random Forest Classifier with Hyperparameter Tuning Anggreini, Novita Lestari; Yuliana, Ade; Ramdan, Dadan Saepul; Al-Dayyeni, Wissam
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.4755

Abstract

Diabetes mellitus is a chronic metabolic disorder that poses a serious challenge to global healthcare systems due to its increasing prevalence and the high costs associated with treatment. Although machine learning has been widely adopted to support early diagnosis, many predictive models still underperform due to limited preprocessing strategies and inefficient hyperparameter settings. This study proposes a comprehensive machine learning pipeline to enhance diabetes prediction accuracy by utilizing a Random Forest classifier optimized through systematic hyperparameter tuning. The novelty of this method lies in its integrated approach, which includes thorough preprocessing such as removing duplicate records, handling inconsistent unique values, addressing missing data, and applying the SMOTE technique to overcome class imbalance. Additionally, hyperparameter tuning is conducted using GridSearchCV combined with 5-fold cross-validation, and only the most influential features are selected to improve model interpretability and efficiency. The proposed model achieved an accuracy of 95 percent, with a recall of 0.88 and an F1-score of 0.85, indicating its robustness in identifying diabetic cases more effectively than previous studies using standard machine learning algorithms. This model contributes to the development of a reliable and scalable early detection system for diabetes, applicable in clinical decision support environments. Further refinement can be achieved by testing on larger and more diverse datasets or by implementing more efficient tuning techniques such as Bayesian optimization.
A Hybrid LSTM–Smith Waterman Model for Personalized Semantic Search in Academic Information Systems Yuliana, Ade; Anggreini, Novita Lestari; Iskandar, Rachmat; Prasanth, G. Rafi
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.4763

Abstract

The growing complexity of digital learning environments presents a critical challenge in computer science, particularly in designing intelligent academic systems capable of delivering context-aware and personalized content. Traditional academic information systems often rely on literal keyword matching, failing to interpret the semantic intent behind user queries and ignoring historical learning behavior. This study addresses these limitations by proposing a hybrid semantic search and recommendation model that integrates Long Short-Term Memory (LSTM) networks with the Smith Waterman algorithm. The LSTM component models temporal sequences of user interactions, while Smith Waterman enables local semantic alignment between user queries and learning content. Historical query logs and user-clicked topics are transformed into semantic vectors, which are further enhanced through a contextual graph and semantic relation matrix. Experimental results demonstrate the model’s effectiveness, achieving 89% accuracy, an F1-score of 0.89, and an AUROC of 0.88 by epoch 50. The hybrid architecture successfully captures the evolution of user interest and semantic relevance, outperforming baseline approaches. This research contributes to the field of computer science by bridging natural language understanding and sequential modeling to improve adaptive learning technologies. The proposed model offers a scalable foundation for developing intelligent recommendation systems in academic platforms, fostering improved learner engagement and efficiency.
Sistem Informasi Pendaftaran Penduduk Non Permanen Berbasis Web Pada Disdukcapil Kota Cimahi Fariha, Fariha; Yuliana, Ade
Citizen : Jurnal Ilmiah Multidisiplin Indonesia Vol. 5 No. 4 (2025): CITIZEN: Jurnal Ilmiah Multidisiplin Indonesia
Publisher : DAS Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53866/jimi.v5i4.986

Abstract

Administrasi kependudukan merupakan aspek penting dalam mendukung pelayanan publik dan perencanaan pembangunan. Penduduk non permanen adalah penduduk yang bertempat tinggal di suatu daerah lebih dari satu tahun tanpa berniat menetap secara tetap. Kota Cimahi mengalami peningkatan jumlah penduduk non permanen yang menuntut adanya pendataan yang akurat dan efisien. Proses pendataan manual dengan Google Form masih memiliki kelemahan pada aspek validasi, keamanan, dan pelaporan. Penelitian ini bertujuan merancang sistem informasi pendaftaran penduduk non permanen berbasis web menggunakan metode prototype model dengan framework Laravel dan basis data MySQL. Sistem dikembangkan untuk menyediakan fungsi registrasi, login, pengisian data, unggah dokumen, verifikasi petugas, notifikasi status, serta pelaporan digital. Hasil pengujian Blackbox dan User Acceptance Test (UAT) menunjukkan sistem berfungsi sesuai kebutuhan, mudah digunakan, serta meningkatkan efisiensi proses pendaftaran. Sistem ini terbukti layak diimplementasikan sebagai solusi pendataan penduduk non permanen di Kota Cimahi, serta berkontribusi pada peningkatan efektivitas dan transparansi pelayanan publik.
Feature Selection Optimization Using Genetic Algorithm for Naive Bayes-Based Diabetes Mellitus Classification Aris, Nova Arianti; Yuliana, Ade
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7618

Abstract

Diabetes mellitus is a chronic disease with a steadily increasing prevalence each year and poses the risk of severe complications if not addressed early. Therefore, early detection of diabetes risk plays a vital role in prevention efforts. This study aims to enhance feature selection optimization through the use of a genetic algorithm in the classification of diabetes mellitus patients based on the Naive Bayes method. The genetic algorithm was applied to identify the most significant clinical features from patient data, with the expectation of improving the classification model’s accuracy and efficiency. A dataset comprising 1,557 patient records with 29 initial clinical attributes was utilized. Following preparation and selection stages, 7 key features were chosen for model training. Model performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results indicated that the model with selected features achieved an accuracy of 80.99%, precision of 80.99%, recall of 100%, and an F1-score of 89.5%. These findings confirm that genetic algorithms are effective in improving Naive Bayes classification performance for diabetes risk identification. This study is expected to serve as a foundation for the development of more accurate and efficient disease risk prediction systems in the future.