Garuda - Garba Rujukan Digital

Analisis Sentimen Terhadap Opini Publik Tentang Kebijakan Regulasi Kripto Di Indonesia Menggunakan Metode Regresi Logistik Nazka yasidi; Rendra Gustriansyah; Lastri Widya Astuti
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 2 (2025): Agustus: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i2.5733

This study investigates public sentiment toward cryptocurrency regulation policies in Indonesia by employing a logistic regression approach on social media data. A total of 300 Indonesian-language tweets were collected from platform X between January 2022 and April 2025 through a web scraping method using targeted keywords related to cryptocurrency payment regulations. Data preprocessing included text cleaning, case folding, stemming with the Sastrawi library, stopword removal, and tokenization, followed by feature extraction using TF-IDF. Sentiment labels were manually assigned in collaboration with legal experts to ensure classification accuracy. The logistic regression model achieved strong predictive performance, with 91.67% accuracy on the test set and stable results across K-Fold Cross Validation, yielding an average accuracy of 92–93%. The sentiment analysis revealed that the majority of public opinion expressed positive sentiment (85%), while negative sentiment represented only 15%. Positive sentiment was primarily associated with terms such as “protect,” “regulate,” “benefit,” and “legality,” highlighting public support for regulatory measures that enhance investor protection and provide legal certainty. Conversely, negative sentiment featured terms including “forbidden,” “restrict,” and “obstruct,” which reflected concerns regarding regulatory barriers and religious considerations surrounding cryptocurrency usage. The findings demonstrate that Indonesian society generally perceives cryptocurrency regulation as a constructive initiative toward building a secure and trustworthy digital asset ecosystem. Furthermore, the empirical evidence contributes to the growing literature on public perception of financial technology regulations in developing countries. For policymakers, the results emphasize the importance of transparent communication and balanced regulatory frameworks to maintain public trust while addressing potential risks. Overall, this research provides valuable insights into how sentiment analysis can inform the design of more effective regulatory strategies in the evolving landscape of digital finance.

Perbandingan Kinerja Algoritma Support Vector Machine dan Random Forest dalam Analisis Sentimen Ulasan Hotel di Kota Palembang pada Google Maps Ari wiyanto; Shinta Puspasari; Lastri Widya Astuti
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 2 (2025): Agustus: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i2.5802

The growth of the tourism sector in Palembang City has encouraged an increase in the need for quality hospitality services. In the digital age, user reviews on the Google Maps platform are an important source of data to assess customer satisfaction. This study aims to analyze and compare the effectiveness of two sentiment classification algorithms, namely Support Vector Machine (SVM) and Random Forest, in processing hotel reviews in Indonesian. A total of 1000 review data was used and processed through the stages of text cleanup, letter normalization, tokenization, stopword removal, and stemming. The evaluation was carried out with two approaches: 80:20 data sharing and cross-validation using the K-Fold technique. On data sharing, Random Forest showed 88% accuracy and 100% recall, while SVM recorded 87% accuracy and 99% recall, with equivalent precision and F1-score. However, cross-validation showed that the SVM was more stable and consistent, with 92% accuracy, 94% accuracy, 98% recall, and 96% F1-score, outpacing Random Forest's 91% accuracy and 95% F1-score. These results show that the SVM algorithm is superior in analyzing hotel review sentiment on Google Maps. These findings provide recommendations for tourism information system developers to adopt an SVM-based approach to review data processing to support more accurate and responsive decision-making.

Penentuan Tingkat Kekumuhan Permukiman Kumuh Kota Palembang Dengan Metode Algoritma K-Means Clustering Dan Algoritma ID3 Endah Puspita Sari; Lastri Widya Astuti; Imelda Saluza; Faradillah Faradillah; Rini Yunita
INTECH Vol. 2 No. 1 (2021): INTECH (Informatika Dan Teknologi)
Publisher : Informatics Study Program, Faculty of Engineering and Computers, Baturaja University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54895/intech.v2i1.869

Slum settlers are a condition of uninhabitable settlements. Slums are devided into 4 levels, namely : high slums, medium, light and not slum. To produce these four levels, method is used namely K-Means Clustering Algorithm and the ID3 Algorithm is used to give priority with pre determined attributes then accumulated with the results of clustering classified as slum level. The accuracy test is performe by using the confusion matrix method, where the data results from the K-Means Clustering method compared to the baseline data. The results obtained from the accuracy with confusion matrix is 0,70%, which means the level of truth (accuracy) between the result of the baseline data with research data is 70%.

Penguatan Kompetensi Guru SMK PGRI Kota Palembang Melalui Pemanfaatan Artificial Intelligence Dalam Perencanaan Pembelajaran Ahmad Sanmorino; Hendra Di Kesuma; Indah Pratiwi Putri; Lastri Widya Astuti; Imelda Saluza; Tasmi; Nining Ariati; Dhamayanti; Faradillah; Fery Antony; Dona Marcelina; Rudi Heriansyah
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 9 No. 1 (2026): Januari 2026
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v9i1.4131

Abstract: The development of artificial intelligence (AI) technology presents new opportunities in education, particularly in lesson planning. However, most vocational high school teachers in Palembang City, including those at SMK PGRI 2, still have limited knowledge and skills in utilizing AI. This problem is the background to the implementation of community service activities (PkM) with the aim of improving teacher competency in using Large Language Models (LLM) such as Gemini and ChatGPT to develop Lesson Implementation Plans (RPP). The methods used included needs surveys, interactive workshops, hands-on practice, and evaluation through post-tests and participant feedback. The results of the activity showed a significant increase, where teacher knowledge increased from 20% to 80% and the application of AI in lesson plans increased from 10% to 65%. The contribution of this activity lies in improving teachers' ability to utilize AI to develop lesson plans more effectively and providing a scientific basis for the application of LLM in lesson planning in vocational education. Keywords: artificial intelligence, lesson planning, vocational school teachers Abstrak: Perkembangan teknologi kecerdasan buatan (Artificial Intelligence) menghadirkan peluang baru dalam dunia pendidikan, khususnya dalam perencanaan pembelajaran. Namun, sebagian besar guru SMK di Kota Palembang, termasuk di SMK PGRI 2, masih memiliki keterbatasan dalam pengetahuan dan keterampilan pemanfaatan AI. Permasalahan ini melatarbelakangi dilaksanakannya kegiatan pengabdian kepada masyarakat (PkM) dengan tujuan meningkatkan kompetensi guru dalam menggunakan Large Language Models (LLM) seperti Gemini dan ChatGPT untuk menyusun Rencana Pelaksanaan Pembelajaran (RPP). Metode yang digunakan meliputi survei kebutuhan, workshop interaktif, praktik langsung, serta evaluasi melalui post-test dan umpan balik peserta. Hasil kegiatan menunjukkan adanya peningkatan signifikan, di mana pengetahuan guru meningkat dari 20% menjadi 80% dan penerapan AI dalam RPP naik dari 10% menjadi 65%. Kontribusi kegiatan ini terletak pada peningkatan kemampuan guru dalam memanfaatkan AI untuk menyusun RPP secara lebih efektif serta penyediaan dasar ilmiah bagi penerapan LLM dalam perencanaan pembelajaran di pendidikan vokasi. Kata kunci: artificial intelligence, guru SMK, perencanaan pembelajaran

Classification of User Age Based on Mobile Device Usage Value Using Support Vector Machine Method: A Comparative Study of SVM Kernels and Grid Search Optimization Muhammad Amaruna Sahona Sahona; Lastri Widya Astuti; Muhammad Haviz Irfani
Jurnal Media Informatika Vol. 7 No. 3 (2026): Edisi Mei - Juni
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v7i3.8798

Klasifikasi perangkat seluler adalah proses pengelompokan perangkat seperti smartphone berdasarkan karakteristik dan fitur yang dimilikinya. Penelitian ini mengatasi permasalahan kurangnya pemahaman mengenai karakteristik penggunaan perangkat seluler pada berbagai kelompok usia, yang dapat menyebabkan ketidaksesuaian produk dengan kebutuhan pengguna. Tujuan penelitian ini adalah mengklasifikasikan usia pengguna perangkat seluler berdasarkan manfaat perangkat menggunakan metode support vector machine (SVM). Data yang digunakan adalah data sekunder dari dataset platform kaggle, yang mencakup variabel terkait perilaku pengguna, seperti model perangkat, sistem operasi, durasi penggunaan aplikasi, waktu layar menyala, konsumsi daya baterai, jumlah aplikasi terinstal, penggunaan data, dan jenis kelamin pengguna. Pengolahan data melibatkan pembersihan data, ekstraksi fitur, pelatihan model SVM dengan kernel Linear, RBF, Polynomial, dan Sigmoid, serta penyetelan Hyperparameter menggunakan Grid Search. Hasil penelitian menunjukkan bahwa model SVM dengan kernel Linear, Polynomial, dan RBF mencapai akurasi 100%, membuktikan efektivitas metode ini dalam mengklasifikasikan usia pengguna.

Penentuan Tingkat Kekumuhan Permukiman Kumuh Kota Palembang Dengan Metode Algoritma K-Means Clustering Dan Algoritma ID3 Endah Puspita Sari; Lastri Widya Astuti; Imelda Saluza; Faradillah Faradillah; Rini Yunita
INTECH Vol. 2 No. 1 (2021): INTECH (Informatika Dan Teknologi)
Publisher : Informatics Study Program, Faculty of Engineering and Computers, Baturaja University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54895/intech.v2i1.869

Slum settlers are a condition of uninhabitable settlements. Slums are devided into 4 levels, namely : high slums, medium, light and not slum. To produce these four levels, method is used namely K-Means Clustering Algorithm and the ID3 Algorithm is used to give priority with pre determined attributes then accumulated with the results of clustering classified as slum level. The accuracy test is performe by using the confusion matrix method, where the data results from the K-Means Clustering method compared to the baseline data. The results obtained from the accuracy with confusion matrix is 0,70%, which means the level of truth (accuracy) between the result of the baseline data with research data is 70%.

Pelatihan Prompt Engineering dalam Penyusunan RPP Berbasis Project-Based Learning bagi Guru SMK Nining Ariati; Lastri Widya Astuti; Dhamayanti Dhamayanti; Fery Antony; Hendra Di Kesuma
Reswara: Jurnal Pengabdian Kepada Masyarakat Vol 7, No 1 (2026)
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/rjpkm.v7i1.7811

Perkembangan teknologi Artificial Intelligence (AI) telah membuka peluang baru bagi dunia pendidikan, khususnya dalam perencanaan dan pelaksanaan pembelajaran. Namun, sebagian besar guru di SMK PGRI 2 Palembang masih menghadapi kendala dalam menyusun Rencana Pelaksanaan Pembelajaran (RPP) yang inovatif dan terintegrasi dengan pendekatan Project-Based Learning (PjBL). Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan literasi AI dan keterampilan guru dalam menerapkan prompt engineering guna menghasilkan RPP berbasis Kurikulum Merdeka. Metode pelaksanaan menggunakan pendekatan workshop partisipatif dengan model learning by doing yang dilaksanakan pada tanggal 13 September 2025, diikuti oleh 24 guru dari berbagai program keahlian. Evaluasi dilakukan melalui instrumen pre-test dan post-test untuk mengukur peningkatan pengetahuan dan keterampilan. Hasil kegiatan menunjukkan peningkatan signifikan pada pemahaman guru terhadap konsep AI (96% peserta memahami dengan baik), kemampuan menyusun RPP berbasis PjBL (100% peserta meningkat), serta keterampilan membuat prompt terstruktur (92% peserta mampu menerapkan). Kegiatan ini membuktikan bahwa pelatihan berbasis praktik langsung dapat meningkatkan efisiensi, kreativitas, dan kepercayaan diri guru dalam memanfaatkan AI secara etis sebagai asisten pedagogis dalam perencanaan pembelajaran

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search