Article Per Year (5 Year)
p-Index From 2021 - 2026
12.517
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) TEKNIK INFORMATIKA Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Bulletin of Electrical Engineering and Informatics Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Indonesia Symposium on Computing Indonesian Journal on Computing (Indo-JC) IJoICT (International Journal on Information and Communication Technology) JOIN (Jurnal Online Informatika) Jurnal Teknologi dan Sistem Komputer JOIV : International Journal on Informatics Visualization Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi JURNAL MEDIA INFORMATIKA BUDIDARMA Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control JITK (Jurnal Ilmu Pengetahuan dan Komputer) Building of Informatics, Technology and Science Journal of Computer System and Informatics (JoSYC) Jurnal Teknik Informatika (JUTIF) JINAV: Journal of Information and Visualization eProceedings of Engineering Eduvest - Journal of Universal Studies Scientific Journal of Informatics Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika
Erwin Budi Setiawan
Telkom University
Aerospace Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Library & Information Science Mathematics Neuroscience Social Sciences

Published : 131 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 131 Documents
Search

 10   11   12   13   14 
Content Based Filtering on Culinary Tourism Recommendation System Based on Social Media X Using Bi-LSTM Khamil, Muhammad Khamil; Erwin Budi Setiawan
International Journal on Information and Communication Technology (IJoICT) Vol. 10 No. 2 (2024): Vol.10 No. 2 Dec 2024
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v10i2.967

Abstract

Advancing technology, especially on social media platforms like X, created a vibrant space for users to share culinary experiences and recommendations through opinions and reviews. X became critical in presenting reviews and recommending places to eat with an excessively high number of active users. Facing the challenge of information overload on X, this research proposed a culinary tourism recommendation system using the Content-Based Filtering (CBF) method with Word to Vector (Word2Vec) and Bidirectional Long Short-Term Memory (Bi-LSTM) for classification. Utilizing culinary tourism data from Tripadvisor and user threads on Twitter, the dataset used included 2,645 tweets and five web crawling results, resulting in a matrix with a total of 200 culinary places and 44 users. Data pre-processing, such as the calculation of sentiment polarity scores using TextBlob and the application of SMOTE technique to balance the data, contributed to the improved accuracy of this research. In addition, optimization of the Bi-GRU model with various optimization methods, such as Adam, and hyperparameter tuning using Learning Rate Finder, resulted in a maximum accuracy of 94.99%, an increase of 29.4% from the baseline. The results of this research contributed significantly to the development of a more accurate and personalized culinary tourism recommendation system.
Hate Comment Detection On Twitter Using Long Short Term Memory (LSTM) With Genetic Algorithm (GA) Nindya Erlani, Dea Alfatihah; Setiawan , Erwin Budi
Eduvest - Journal of Universal Studies Vol. 4 No. 11 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i11.1758

Abstract

In the era of social media like today, one social media that is currently quite popular is Twitter. This study explores the use of the Long Short Term Memory (LSTM) method optimized with the Genetic Algorithm (GA) to detect hate speech in Twitter data in Indonesia. We use TF-IDF and GloVe feature extraction techniques to produce effective word vector representations in natural language processing. This study also introduces feature expansion and similarity corpus construction to improve the performance of the LSTM classification model. Evaluation is carried out through a confusion matrix to measure accuracy, precision, recall, and F1 score. The results show that the LSTM model with TF-IDF and GloVe feature extraction achieves the best performance with an accuracy of up to 92.91%. We also found that the combination of Unigram + Bigram + Trigram, max feature 10000, and Glove corpus with Top 20 similarity gave optimal results. In addition, parameter optimization using genetic algorithms has been shown to improve accuracy and F1-Score. The resulting LSTM model is able to classify test data with high accuracy, which has the potential to help in the detection and handling of hate speech on social media, as well as improving the model's ability to identify and understand text content in the Indonesian language context.
Genetic Algorithm Optimization of Hybrid LSTM-AutoEncoder in Tourism Recommendation System Sanjaya, Bayu Surya Dharma; Setiawan, Erwin Budi
JURNAL TEKNIK INFORMATIKA Vol. 17 No. 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.39760

Abstract

The tourism industry has rapid growth and has become one of the world's leading economic industries in recent years due to advances in information technology, such as the internet and social media. However, the overwhelming amount of information often makes it difficult for travelers to decide on their preferred travel destination. To address these issues, this research proposes a tourism recommendation system that combines Content-Based Filtering and Hybrid LSTM-AE, which is optimized using Genetic Algorithm (GA). There is no research that has developed a recommendation system using a combination of these methods and optimized using GA. So that this research can contribute to providing personalized recommendations and higher accuracy. The dataset consists of 9,504 ratings collected from the Ministry of Tourism and Creative Economy, Twitter, and web sources. The system was able to achieve a rating prediction accuracy of 96.82% by applying SMOTE to handle data imbalance and implementing a GA approach to the Hybrid LSTM-AE model. Accuracy has increased by 18.7% from the baseline model without using SMOTE and optimization. These results underscore that a strong integration between natural language processing and genetically optimized deep learning provides more accurate recommendations.
Optimizing the Learning Rate Hyperparameter for Hybrid BiLSTM-FFNN Model in a Tourism Recommendation System Mustofa, Aufa Ab'dil; Setiawan, Erwin Budi
JURNAL TEKNIK INFORMATIKA Vol. 17 No. 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.40250

Abstract

Indonesia, with its abundant natural resources, is rich in captivating tourist attractions. Tourism, a vital economic sector, can be significantly influenced by digitalization through social media. However, the overwhelming amount of information available can confuse tourists when selecting suitable destinations. This research aims to develop a tourism recommendation system employing content-based filtering (CBF) and hybrid Bidirectional Long Short-Term Memory Feed-Forward Neural Network (BiLSTM-FFNN) model to assist tourists in making informed choices. The dataset comprises 9,504 rating matrices obtained from tweet data and reputable web sources. In various experiments, the hybrid BiLSTM-FFNN model demonstrated superior performance, achieving an accuracy of 93.36% following optimization with the Stochastic Gradient Descent (SGD) algorithm at a learning rate of about 0.193. The accuracy, after applying Synthetic Minority Over-sampling Technique (SMOTE) and fine-tuning the learning rate hyperparameter, showed a 14.3% improvement over the baseline model. This research contributes by developing a recommendation system method that integrates CBF and hybrid deep learning with high accuracy and provides a detailed analysis of optimization techniques and hyperparameter tuning.
Analysis of the Alignment of Bauran System Features Based on Outcome-Based Education Rules Using Feature-Oriented Domain Analysis Wicaksono, Galih Wasis; Saleh, Abd; Wahyuni, Evi Dwi; Setiawan, Erwin Budi
JOIV : International Journal on Informatics Visualization Vol 8, No 3-2 (2024): IT for Global Goals: Building a Sustainable Tomorrow
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.3-2.2895

Abstract

Implementing information systems in higher education curriculum design is a crucial tool for academics, enabling them to design, develop, and evaluate the curriculum more dynamically, responsively, and structurally. However, it is not just about having a tool. It is about ensuring that the tool aligns with curriculum design standards. This study, therefore, measures and analyses the conformity of the Bauran system as a curriculum management information system with the established stages and standards of curriculum design. The analysis is based on the Indonesia National Standards for Higher Education (Standar Nasional Pendidikan Tinggi (SN DIKTI)) by referring to the Guidebook for Higher Education Curriculum Development in Indonesia and best practices in the implementation of Outcome-Based Education (OBE) curriculum design. The method used in this research is feature-oriented domain analysis (FODA), which includes context analysis, domain modeling, and architecture modeling. Experts in the field of OBE curriculum then validate the results of feature measurement and mapping. The study compares 27 Bauran features to 10 stages in the curriculum design guidebook and nine stages in the OBE curriculum design flow. The analysis results show that the Bauran system has implemented 10 out of 10 stages (100%) of curriculum design according to the curriculum design guidebook. However, Bauran has only implemented 8 out of 9 stages (89%) in the OBE curriculum flow. These findings not only provide feature recommendations for future Bauran development and other higher education curriculum management systems but also highlight the potential of the Bauran system for future development.
Ekpansi Fitur dengan Word2vec dalam klasifikasi Hoax di Twitter Cahyudi, Ridho Maulana; Setiawan, Erwin Budi
eProceedings of Engineering Vol. 10 No. 2 (2023): April 2023
Publisher : eProceedings of Engineering

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

Abstract

Abstrak-Media sosial sekarang sudah banyak digunakan untuk berbagi informasi, dan juga tempat untuk berkomunikasi. Dalam berbagi informasi banyak peluang untuk menyebarkan hoax, contohnya seperti diaplikasi Twitter. Terkadang ada ketidaksesuaian kosa kata dalam setiap tweet. Oleh karena itu pada penelitian ini dilakukan penerapan metode fitur ekpansi menggunakan Word2vec untuk meminimalisir ketidaksesuaian kosakata tersebut. metode klasifikasi yang digunakan adalah Naive bayes, ANN, Decision Tree. Hasil dari penelitian ini, nilai tertinggi sebesar 82,44% yang menggunakan ekspansi fitur Word2vec pada metode klasifikasi ANN yang meningkat sebesar 1,17%.Kata kunci - hoax, fitur ekspansi, twitter.
Teknik Recommender System Menu Makanan dengan Pendekatan Contextual Model dan Multi-Criteria Decision Making pada Orang Dewasa Kacaribu, Isabella Vichita; Setiawan, Erwin Budi; Lhaksmana, Kemas Muslim
eProceedings of Engineering Vol. 10 No. 4 (2023): Agustus 2023
Publisher : eProceedings of Engineering

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

Abstract

Wisata Kuliner adalah kegiatan yang popular pada saat ini. Banyak tempat makan yang menawarkan makanan-makanan dengan tampilan yang menarik, murah, atau enak. Beberapa masyarakat mendapatkan informasi mengenai wisata kuliner atau daftar makanan melalui media sosial, berita maupun melalui media cetak. Sehingga banyak dari mereka menentukan menu makanan yang mereka santap melalui media sosial. Banyak kriteria yang digunakan dalam memilih makanan, seperti ada yang melihat kandungan kalorinya, harganya, lokasinya, atau yang lainnya. Seiring berkembangnya teknologi informasi, sistem rekomendasi telah semakin dibutuhkan oleh masyarakat untuk membantu pengguna dalam mendapatkan informasi menu makanan yang relavan. Ada metode untuk merekomendasikan makanan berdasarkan contextual model dan multi-criteria decision yang dapat membantu pengguna memilih makanan yang cocok. Berdasarkan pada metode Weighted Sum Model, penelitian ini ingin membuat suatu teknik yang lebih baik dengan menggunakan terapan Contextual Model. Contextual Model membuat pengguna menjadi lebih mengerti dalam penggunaan sistem dan mudah dimengerti.Kata kunci— wisata kuliner, recommender system, contextual model, multi-criteria decision, weighted sum model.
Analisis Sentimen Multimodal terhadap Opini Publik Mengenai Kesehatan Mental di Media Sosial X dengan Metode CNN BiLSTM dan Ekspansi fitur FastText Nadim Rafli Hamzah; Erwin Budi Setiawan
eProceedings of Engineering Vol. 13 No. 1 (2026): Februari 2026
Publisher : eProceedings of Engineering

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

Abstract

Dalam hal kesehatan masyarakat global, kesehatan mental menjadi perhatian penting. Salah satu situs media sosial yang paling populer, X telah berkembang menjadi forum bagi orang-orang untuk mendiskusikan masalah kesehatan mental dan berbagi cerita pribadi. Menganalisis sentimen dalam percakapan online ini penting untuk memahami persepsi publik dan memandu intervensi kesehatan mental. Penelitian ini mengusulkan model analisis sentimen menggunakan multimodal yang memanfaatkan data tekstual dan visual, dengan fitur teks yang diekstraksi melalui CNN-BiLSTM, TF IDF, dan FastText, dan fitur gambar menggunakan VGG-16. Klasifikasi sentimen dilakukan dengan menggunakan model Hybrid CNN-BiLSTM dengan mekanisme perhatian. Model ini menggunakan fusi tingkat menengah untuk mengintegrasikan fitur teks dan gambar, diikuti dengan tingkat keputusan untuk menggabungkan output dari model teks saja, gambar saja, dan multimodal. 24.742 pasangan tweetgambar dikumpulkan dari platform X dan dianotasi melalui sistem pemungutan suara mayoritas. Untuk membangun korpus kemiripan FastText, 63.512 data dari portal berita digital CNN (Cable News Network) dan X digabungkan. Dengan akurasi 87,92%, model multimodal mengungguli model teks saja sebesar 0,09% dan model gambar saja sebesar 25,10%. Hasil ini menunjukkan keefektifan data modalitas, ekstraksi fitur yang komprehensif, dan multimodal. Keywords—Analisis Sentimen, FastText, Hybrid CNN-BiLSTM, TF-IDF, VGG-16
Deteksi Bunuh Diri pada Media Sosial Twitter Menggunakan Metode CNN-LSTM dengan Ekspansi Fitur Word2vec Fathin Thariq Wiyono; Erwin Budi Setiawan
eProceedings of Engineering Vol. 13 No. 1 (2026): Februari 2026
Publisher : eProceedings of Engineering

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

Abstract

Deteksi bunuh diri melalui media sosial telah menjadi tantangan besar dalam beberapa tahun terakhir, terutama pada platform seperti Twitter yang berisi unggahan singkat dan emosional. Penelitian ini bertujuan untuk mengembangkan model deep learning hybrid yang dapat mendeteksi potensi bunuh diri pada tweet di Twitter, menggunakan metode CNN-LSTM dan fitur semantik yang diperluas dengan Word2Vec. Dengan meningkatnya angka bunuh diri di kalangan generasi muda, yang membutuhkan sistem deteksi dini berbasis teknologi canggih. Deteksi dini ini dapat membantu memberikan intervensi lebih cepat bagi individu yang berisiko tinggi. Pendekatan yang diusulkan menggunakan kombinasi Convolutional Neural Network (CNN) untuk menangkap pola lokal dalam teks, Long Short-Term Memory (LSTM) untuk memahami urutan kata dalam teks, serta Word2Vec untuk memperkaya representasi semantik kata-kata dalam tweet. Sistem ini memanfaatkan ekstraksi fitur TF-IDF dan ekspansi fitur menggunakan Word2Vec untuk meningkatkan kemampuan model dalam mengenali pola emosional dan semantik yang ada dalam tweet. Hasil eksperimen menunjukkan bahwa model hybridCNN-LSTM dengan ekspansi fitur Word2Vec dan optimasi menghasilkan akurasi sebesar 91,31%. Hasil model hybrid CNN-LSTM belum mununjukkan hasil yang lebih baik dari model non-hybrid. Kontribusi utama dari penelitian ini adalah mengeksplorasi pengaruh ekspansi fitur Word2vec pada model hybrid deep learning untuk deteksi bunuh diri dan mengintegrasikan ekstraksi fitur TF-IDF sertaoptimasi untuk meningkatkan performa klasifikasi teks. Kata kunci— deteksi bunuh diri, hybrid deep learning, word2vec, TF-IDF, optimasi
Deteksi Depresi di Twitter Menggunakan Metode CNN-BiGRU dengan Fitur Ekspansi FastText Muhammad Arif Dwi Putra; Erwin Budi Setiawan
eProceedings of Engineering Vol. 13 No. 1 (2026): Februari 2026
Publisher : eProceedings of Engineering

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

Abstract

Depresi merupakan gangguan mental yang sering tidak terdeteksi dengan baik, meskipun banyak mempengaruhi individu di seluruh dunia. Media sosial, khususnya Twitter, menjadi platform yang digunakan untuk mengekspresikan emosi, termasuk gejala depresi yang tidak diungkapkan secara eksplisit. Penelitian ini bertujuan untuk mengembangkan model deteksi depresi di Twitter dengan metode hybrid CNN-BiGRU yang dilengkapi dengan ekspansi fitur FastText. CNN digunakan untuk mengekstraksi pola lokal dalam teks, sementara BiGRU memproses urutan kata dari dua arah untuk menangkap konteks yang lebih dalam. Ekspansi FastText bertujuan untuk menangani variasi kosakata dan meningkatkan akurasi dalam mendeteksi makna implisit dalam teks. Penelitian ini penting karena banyak pengguna media sosial yang tidak mendapatkan perawatan depresi yang memadai. Deteksi otomatis melalui teks Twitter dapat menjadi solusi untuk intervensi dini. Pengujian menggunakan dataset tweet berbahasa Indonesia menunjukkan bahwa model hybrid BiGRU-CNN dengan FastText mencapai akurasi tertinggi sebesar 80,65% pada korpus IndoNews dengan optimizer RMSprop. Model ini diharapkan dapat berkontribusi dalam deteksi depresi dan mendukung intervensi kesehatan mental. Kata kunci— Depresi, Twitter, CNN-BiGRU, FastText, Deteksi Emosi, Model Hybrid.
Co-Authors Abdullah, Athallah Zacky Adriana, Kaysa Azzahra Adyatma, I Made Darma Cahya Agung Toto Wibowo Ahmad Zahri Ruhban Adam Aji Reksanegara Aji, Hilman Bayu Alvi Rahmy Royyan Anang Furkon RIfai Anindika Riska Intan Fauzy Annisa Aditsania Annisa Cahya Anggraeni Annisa Cahya Anggraeni Annisa Rahmaniar Dwi Pratiwi Arie Ardiyanti Arki Rifazka Arsytania, Ihsani Hawa Athirah Rifdha Aryani Aufa Ab'dil Mustofa Aydin, Raditya Bagas Teguh Imani Bayu Muhammad Iqbal Bayu Surya Dharma Sanjaya Billy Anthony Christian Martani Bintang Ramadhan, Rifaldy Brenda Irena Brigita Tenggehi Cahyudi, Ridho Maulana Crisanadenta Wintang Kencana Damarsari Cahyo Wilogo Daniar Dwi Pratiwi Daniar Dwi Pratiwi Dede Tarwidi Dedy Handriyadi Dery Anjas Ramadhan Dhinta Darmantoro Diaz Tiyasya Putra Dion Pratama Putra, Dion Pratama Diyas Puspandari Evi Dwi Wahyuni Faadhilah, Adhyasta Naufal Faidh Ilzam Nur Haq Farid, Husnul Khotimah Fathin Thariq Wiyono Fathurahman Alhikmah Fathurahman Alhikmah Fazira Ansshory, Azrina Febiana Anistya Feby Ali Dzuhri Fhina Nhita Fhina Nhita Fida Nurmala Nugraha Fikri Maulana, Fikri Firdaus, Dzaki Afin Fitria, Mahrunissa Azmima Fitria Gde Bagus Janardana Abasan, I Ghina Dwi Salsabila Gita Safitri Grace Yohana Grace Yohana Hafiza, Annisaa Alya Hanif Reangga Alhakiem Hildan Fawwaz Naufal Husnul Khotimah Farid I Gusti Ayu Putu Sintha Deviya Yuliani I Gusti Bagus Bagaskara Kerta Yasa I Kadek Candradinata Ibnu Sina, Muhammad Noer Ilyana Fadhilah Inggit Restu Illahi Inggit Restu Illahi Irma Palupi Isep Mumu Mubaroq Isman Kurniawan Kacaribu, Isabella Vichita Kamil, Ghani Kamil, Nabilla Kartika Prameswari Kemas Muslim Lhaksmana Kevin Usmayadhy Wijaya Khamil, Muhammad Khamil Khoirunnisa, Sanabila Luthfi Firmansah M. Arif Bijaksana Mahmud Imrona Mansel Lorenzo Nugraha Marissa Aflah Syahran Marissa Aflah Syahran Maulina Gustiani Tambunan Mela Mai Anggraini Moh Adi Ikfini M Moh. Hilman Fariz Muhammad Afif Raihan Muhammad Arif Dwi Putra Muhammad Faiq Ardyanto Putro Muhammad Khiyarus Syiam Muhammad Kiko Aulia Reiki Muhammad Nur Ilyas Muhammad Shiba Kabul Muhammad Tsaqif Muhadzdzib Ramadhan Mustofa, Aufa Ab'dil Nabilla Kamil Nadim Rafli Hamzah Naufal Adi Nugroho Naufal Razzak , Robith Nilla, Arliyanna Nindya Erlani, Dea Alfatihah Nisa Maulia Azahra Nur Ihsan Putra Munggaran Nuril Adlan , Muhammad Prahasto, Girindra Syukran Putri, Karina Khairunnisa Rafi Anandita Wicaksono Raisa Sianipar Rakhmat Rifaldy Ramadhan, Ananta Ihza Ramadhan, Helmi Sunjaya Ramadhani, Andi Nailul Izzah Ramadhanti, Windy Rayhan Rahmanda Refka Muhammad Furqon Regina Anatasya Rudiyanto Rendo Zenico Riaji, Dwi Hariyansyah Rizki Annas Sholehat Roji Ellandi Saleh, Abd Salsabil, Adinda Arwa Sanjaya, Bayu Surya Dharma Sari Ernawati Saut Sihol Ritonga Septian Nugraha Kudrat Septian Nugraha Kudrat Setiawan, Rizki Tri Shakina Rizkia Siti Inayah Putri Sri Suryani Sri Suryani Sukmawati Dwi Lestari Syafa Fahreza Syafa Fahreza Syahdan Naufal Nur Ihsan Valentino, Nico Wicaksono, Galih Wasis Wida Sofiya Widiarta, I Wayan Abi Widjayanto, Leonardus Adi Widyanto, Jammie Reyhan Wijaya, Kevin Usmayadhy Windy Ramadhanti Yoan Maria Vianny Yuliant Sibaroni Zahwa Dewi Artika Zakaria, Aditya Mahendra ZK Abdurahman Baizal