Article Per Year (5 Year)
p-Index From 2020 - 2025
11.137
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Jurnal Teknologi Informasi dan Ilmu Komputer Register: Jurnal Ilmiah Teknologi Sistem Informasi Indonesian Journal on Computing (Indo-JC) IJoICT (International Journal on Information and Communication Technology) Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Sisfokom (Sistem Informasi dan Komputer) JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) TEKNOLOGIA Jurnal Linguistik Komputasional Building of Informatics, Technology and Science Journal of Computer System and Informatics (JoSYC) Journal of Data Science and Its Applications Charity : Jurnal Pengabdian Masyarakat KLIK: Kajian Ilmiah Informatika dan Komputer Prosiding Konferensi Nasional PKM-CSR Journal of Renewable Energy, Electrical, and Computer Engineering Jurnal Indonesia Sosial Teknologi eProceedings of Engineering Community Service Seminar and Community Engagement (COSECANT) Dike Jurnal INFOTEL CSRID LOGIC: Jurnal Penelitian Informatika
Kemas Muslim Lhaksmana
Universitas Telkom, Indonesia
Arts Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Mathematics Nursing Public Health Social Sciences Other

Published : 116 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 116 Documents
Search

 8   9   10   11   12 
Retweet Prediction Using ANN Method and Artificial Bee Colony Jondri, Jondri; Farisi, Kamaludin Hanif; Lhaksmana, Kemas Muslim
CSRID (Computer Science Research and Its Development Journal) Vol. 15 No. 2: June 2023
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.15.2.2023.83-92

Abstract

In the ongoing modern era, the rapid dissemination of information takes place, utilizing various channels for data exchange. One such platform is the social media platform Twitter, renowned for its swift and extensive information propagation. A pivotal factor contributing to information distribution on Twitter is the retweet feature, whereby users can redistribute content to their audience. A study has been conducted to forecast this retweet activity by employing the Artificial Neural Network classification method in conjunction with the Artificial Bee Colony optimization approach. This study leverages diverse features, encompassing content-based feature, user-based feature, and time-based feature. The evaluation results from this study reveal that the proposed method achieves an accuracy value of around 83% with the highest accuracy value reaching 84%. These findings indicate that the fusion of the Artificial Neural Network classification method executed with optimization using the Artificial Bee Colony algorithm yields dependable and consistent performance in predicting retweet activities.
Klasifikasi Multilabel pada Topik ayat Al-Qur’an Menggunakan Random Forest dan Naïve Bayes Zulkarnaen, Imran; Lhaksmana, Kemas Muslim
eProceedings of Engineering Vol. 12 No. 2 (2025): April 2025
Publisher : eProceedings of Engineering

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

Abstract

Al-Qur'an, sebagai kitab suci umat Islam, menyimpan makna yang mendalam, mencakup aspek akidah, ibadah, dan etika sosial. Namun, kerumitan bahasa dalam Al-Qur'an menimbulkan tantangan dalam pengelompokan ayat-ayatnya ke dalam kategori tematik tertentu, terutama dengan pendekatan tradisional yang sering kali tidak dapat menggali hubungan semantik antar kata secara mendalam. Untuk mengatasi tantangan ini, penelitian ini mengembangkan sistem klasifikasi multilabel yang berbasis graph mining, dengan memanfaatkan pengukuran centrality. Sistem tersebut melibatkan pembuatan graf kata untuk merepresentasikan hubungan antar kata, serta penerapan algoritma random forest dan naïve bayes dalam mengklasifikasikan ayat-ayat Al-Qur'an ke dalam delapan kategori tematik. Proses pengolahan data mencakup penghapusan kata henti (stopwords), tokenisasi, dan ekstraksi fitur berdasarkan centrality, seperti closeness, betweenness, dan eigenvector. Hasil penelitian menunjukkan bahwa penggunaan betweenness centrality dengan penggunaan kata henti memberikan performa terbaik, dengan nilai Hamming loss sebesar 0.1631 pada random forest. Temuan ini menekankan keunggulan pendekatan berbasis graf dalam memahami hubungan kompleks antar kata dalam teks Al-Qur'an serta berkontribusi pada pengembangan metode klasifikasi tematik berbasis teknologi yang lebih efisien. Kata kunci— klasifikasi Multilabel, Tematik, Al-Qur’an, Graf, Sentralitas, Graph Mining, Hamming Loss
Prediksi Employee Attrition Menggunakan Metode Decision Tree dan XGBoost dengan Seleksi Fitur ChiSquare Putri, Arla Sifhana; Lhaksmana, Kemas Muslim
eProceedings of Engineering Vol. 12 No. 3 (2025): Juni 2025
Publisher : eProceedings of Engineering

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

Abstract

Employee attrition adalah peristiwa di mana suatuperusahaan kehilangan karyawan karena berbagai alasan.Employee attrition dapat berdampak negatif terhadapproduktivitas dan stabilitas perusahaan, sehinggaperusahaan perlu mengambil langkah pencegahan yangtepat terhadap terjadinya hal tersebut. Dalam penelitianini, metode klasifikasi yang digunakan adalah DecisionTree dan XGBoost, dengan menerapkan seleksi fitur Chisquare. Metode Decision Tree dipilih karena kemudahaninterpretasi dan implementasinya, sementara XGBoostdipilih karena memiliki kinerja prediksi yang sangat baik.Seleksi fitur Chi-square digunakan untukmengidentifikasi fitur-fitur yang memiliki hubungansignifikan dengan fitur target. Evaluasi performa antarakedua metode dilakukan menggunakan metrik sepertiaccuracy, precision, recall, dan f1-score. Hasil penelitianmenunjukkan bahwa metode Decision Tree mencapaiakurasi tertinggi sebesar 93.58% dengan memanfaatkan20 fitur dengan nilai Chi-square tertinggi. Sementara itu,metode XGBoost berhasil mencapai akurasi terbaiksebesar 98.65% dengan memanfaatkan 25 fitur dengannilai Chi-square tertinggi. Penggunaan seleksi fitur Chisquare secara signifikan meningkatkan performa modelprediksi. Hal ini menunjukkan bahwa model denganmetode XGBoost lebih unggul dalam memprediksikemungkinan terjadinya employee attrition dibandingkandengan metode Decision Tree. Kata kunci: employee attrition, prediksi, decision tree, xgboost, chi-square
Klasifikasi Multilabel pada Teks Effect Kartu Monster Permainan Kartu Yu-Gi-Oh! Pamungkas, Danit Hafiz; Lhaksmana , Kemas Muslim
eProceedings of Engineering Vol. 11 No. 4 (2024): Agustus 2024
Publisher : eProceedings of Engineering

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

Abstract

Abstrak —Yu-Gi-Oh! Trading Card Game adalah sebuahpermainan kartu dimana pemain membangun deck, menyusunstrategi dan menghubungkan kemampuan atau effect suatukartu dengan kemampuan kartu lainnya. Saat ini terdapat lebihdari 10000 kartu berbeda dengan effect berbeda sehingga dapatmenyulitkan untuk mencari kartu dengan effect tertentu yangcocok dengan strategi yang ingin dilakukan. Terdapat aplikasiresmi yang dapat mencari kartu, termasuk dengan caramencari kemampuan dari kartu tersebut. Namun, aplikasitersebut memiliki kekurangan pada mesin pencariannya yangsangat sederhana dan dapat menghasilkan false positive. Dalampenelitian ini dibangun klasifier multilabel yang dapatmengklasifikasikan effect kartu untuk membantu pencariankartu, dan juga menentukan praproses yang tepat untukklasifikasi ini. Dilakukan pendekatan transformasi problemdimana klasifikasi multilabel dipecah menjadi 6 klasifikasibiner sesuai banyaknya label. Lalu, prediksi klasifikasi binertersebut digabungkan menjadi prediksi klasifikasi multilabel.Klasifikasi dengan menggunakan praproses penghapusan stopword menghasilkan micro average f1-score terbaik dengan nilai0.54. Walaupun begitu, nilai ini kurang baik dan menunjukkanbahwa klasifier belum dapat melabeli data dengan baik,sehingga klasifier yang dibangun belum dapat membantupemain mencari kartu dengan kelas effect yang sesuaiharapan.1 Kata kunci— klasifikasi, multilabel, stemming, penghapusanstop word, yu-gi-oh
Pengaruh Seleksi Fitur Information Gain pada Klasifikasi Berita Hoax di Twitter dengan Menggunakan Metode Naive Bayes Multinomial Andiani, Annisa Dwi; Muslim L, Kemas
eProceedings of Engineering Vol. 11 No. 4 (2024): Agustus 2024
Publisher : eProceedings of Engineering

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

Abstract

Abstrak - Indonesia merupakan salah satu negarayang memiliki banyak pengguna media sosial, konsumsimedia sosial yang tinggi tanpa dibarengi dengan sikapkritis dalam melakukan filter informasi yang didapatmembuat berita hoax menjadi semakin mudahtersebarluaskan. Hoax merupakan berita yangdisebarkan dengan tujuan agar publik mempercayaihal yang tidak diketahui kebenarannya. Hoax dapatmenimbulkan adanya kecemasan dan permusuhan bagipihak yang terpapar. Pada penelitian tugas akhir ini,dibangun sistem klasifikasi berita hoax di twitterdengan menggunakan metode naive bayes multinomialyang dikombinasikan menggunakan pembobotan TFIDF serta penggunaan seleksi fitur information gain.Hasil akhir pengujian menunjukkan bahwapenggunaan information gain pada klasifikasi hoax inidapat mengurangi nilai overfitting dari akurasi. Hasilakurasi terbaik yang didapat dari penelitian ini adalahsebesar 79,87% dengan menggunakan klasifikasi NaiveBayes Multinomial, pembobotan TD-IDF, dan tanpapenggunaan seleksi fitur Information Gain. Kata kunci : hoax, twitter, TF-IDF, information gain, naive bayes multinomial
Prediksi Retweet Berdasarkan Fitur Pengguna, Konten, dan Waktu Menggunakan Metode Klasifikasi ANN-Cat Swarm Optimization Syadzily , Muhammad Hasan; Jondri, Jondri; Lhaksmana, Kemas Muslim
eProceedings of Engineering Vol. 11 No. 4 (2024): Agustus 2024
Publisher : eProceedings of Engineering

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

Abstract

Abstrak - Twitter merupakan salah satu saranamicroblogging populer saat ini yang memungkinkanpenggunanya untuk mengirim pesan berupa teks, gambar,atau video, serta berbagi informasi dengan cepat. Salah satufitur utama di Twitter adalah retweet, dengan fitur inipengguna dapat memposting ulang pesan yang diunggaholeh orang lain. Penelitian ini bertujuan untuk membangunmodel prediksi retweet dengan metode klasifikasi ANN yangdioptimasi oleh algoritma CSO menggunakan fitur berbasispengguna, konten, dan waktu. Masalah yang dihadapidalam penelitian ini yaitu ketidakseimbangan kelas yangsering terjadi pada data retweet. Untuk mengatasi masalahtersebut, digunakan teknik oversampling danundersampling. Hasil evaluasi pada penelitian inimenunjukkan bahwa proses klasifikasi ANN dengan CSOdapat mencapai nilai akurasi sebesar 86.70% dan F1-Scoresebesar 86.61% dengan melakukan teknik undersampling. Kata kunci : retweet, prediksi, ANN, CSO, undersampling
SENTIMENT ANALYSIS ABOUT THE 2024 PRESIDENTIAL ELECTION USING CNN METHOD Ahmad, Alif Faidhil; L, Kemas Muslim
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.6457

Abstract

The upcoming 2024 Indonesian General Election (Pemilu 2024) will be interesting news for online media users. With so much news about the election, online media has become one of the most effective media used to guide public opinion. Apart from that, public opinion is that the coverage in online media for each candidate is not balanced or not because a media is considered to have an affiliation with a particular candidate. To prove this opinion, sentiment analysis will be carried out on several online media in order to prove whether people's opinions are correct or not. Although previous research has used various platforms and achieved various levels of accuracy using the Convolutional Neural Network (CNN) and Support Vector Machine (SVM) methods with various features, this analysis will be developed using the Convolutional Neural Network (CNN) method to obtain higher accuracy and will be compared with the Support Vector Machine (SVM) method from the media platforms Detik.com, CNN Indonesia and CNBC Indonesia. The final results prove that the use of the Convolutional Neural Network (CNN) method shows an average combined performance of 65% (Cancidate 1 = 61%, Candidate 2 = 69%, Candidate 3 = 65%) smaller than the performance of the Support Vector Machine (SVM) method. with a combined average of  74% (Candidate 1 = 73%, Candidate Candidate 2 = 77%, Candidate Candidate 3 = 72%). This study provides insights into optimizing sentiment classification techniques for Online Media platforms, emphasizing the importance of leveraging semantic and contextual information in sentiment analysis tasks.
Comparative Analysis of Random Forest and Convolutional Neural Network (CNN) Algorithms for Pneumonia Detection in Chest X-ray Images: Accuracy, Interpretability, and Computational Efficiency Zaena, Siffa; Lhaksmana, Kemas Muslim
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7840

Abstract

Pneumonia is a lung infection that can be detected through chest X-ray images. Manual diagnosis requires radiological expertise and time, thus an accurate automated method is needed. This study aims to compare the performance of two image classification algorithms, Convolutional Neural Network (CNN) and Random Forest (RF), in detecting pneumonia. The dataset used was obtained from Kaggle, consisting of 5,863 X-ray images categorized into three classes: bacterial pneumonia, viral pneumonia, and normal. Preprocessing steps include image resizing, normalization, and data augmentation. The CNN model was built using multiple convolutional and pooling layers, while RF utilized numerical features derived from histograms and texture. The CNN model demonstrated superior performance, achieving 92.4% accuracy, 93.1% precision, 91.6% recall, and 92.3% F1-score, compared to 82.7%, 80.3%, 85.1%, and 82.6% for Random Forest, respectively. Although CNN offers better accuracy, RF excels in interpretability. In conclusion, CNN is more effective for image-based pneumonia classification, yet RF remains relevant in applications requiring transparent decision-making. Potential biases, such as class imbalance and limited demographic representation in the dataset, could influence model performance and generalizability across different patient populations.
Comparison of Convolutional Neural Network and Support Vector Machine for Student Question Classification in ChatGPT-based Learning Tools Jordan, Brilliant; Lhaksmana, Kemas Muslim
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7841

Abstract

Artificial Intelligence (AI) has revolutionized educational tools by enabling systems that proactively understand and respond to student needs. ChatGPT, a widely used generative model for education in Indonesia. However, it struggles to classify student questions accurately due to ambiguous phrasing, overlapping sentence structures, and difficulty recognizing intent, which limits its effectiveness as a learning assistant. This study compares the performance of Convolutional Neural Networks (CNN), which extract locally important features from word sequences with Support Vector Machines (SVM) in classifying student questions known for handling high-dimensional data and efficiently finding the optimal hyperplane for text classification. A dataset of 2,797 Indonesian ChatGPT interactions (71% clear vs. 29% unclear) was preprocessed through case folding, stop-word removal, stemming, and tokenisation, followed by data augmentation based on synonyms, which was applied to the minority class to balance the dataset. The models were tuned through grid or random search with prediction testing of the best model using 5-fold cross-validation comparisons across three data splits (70:30, 80:20, and 90:10). Results showed that CNN achieved balanced accuracy, precision, recall, and F1-score of 0.90 on the 90:10 split, outperforming SVM, which plateaued at 0.85 accuracy and dropped to 0.76 in F1-score. The embedded filters of the CNN found generality from lexical variation through the process of augmentation, while the TF-IDF sparse vectors in the SVM failed to maintain this level of semantics. These findings underscore that CNN is more adaptive to diverse data and better suited for integration into ChatGPT-based educational tools, particularly in supporting reliable classification and personalised AI feedback in student learning contexts.
Classification of English Language Anxiety Using Support Vector Machine on Twitter User Marozi, Ericho; Lhaksmana, Kemas Muslim
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.8015

Abstract

This study aims to classify expressions of language anxiety in English as a foreign language, as reflected in user-generated texts on Twitter. The research applies machine learning approaches Support Vector Machine (SVM) and Convolutional Neural Network (CNN) to perform automatic classification of anxiety levels. The dataset was collected through Twitter crawling, filtered for relevance, and annotated manually using a three-point scale (low, medium, high) based on psychological indicators such as fear of speaking, avoidance, and self-perceived inability. Preprocessing included text normalization, tokenization, stopword removal, and feature extraction using TF-IDF with unigram to trigram representations. Model training was conducted on a balanced dataset, and performance was evaluated through cross-validation and tuning of key hyperparameters. SVM achieved the highest accuracy of 98.40%, showing strong stability across various test conditions. CNN initially performed competitively but experienced a slight performance drop after tuning, suggesting its sensitivity to parameter settings and data volume. The findings demonstrate that SVM is more robust and suitable for limited-data environments, making it a practical tool for classifying psychological traits like language anxiety in digital communication. This research offers insight into the potential of machine learning in psychological and linguistic analysis, especially through social media platforms.
Co-Authors Abdurrahman, Azzam Abiyyu, Ahmad Syafiq Achmad Salim Aiman Adelia, Dila Adhyaksa Diffa Maulana Aditya Eka Wibowo Aditya Gifhari Soenarya Adiwijaya Aghi Wardani Agni Octavia Agus Kusnayat Ahmad Y, Rafly Ahmad Y Ahmad, Alif Faidhil Ahmad, Fathih Adawi Al Faraby, Said Alberi Meidharma Fadli Hulu Amalia Elma Sari Amien, Iqmal Lendra Faisal Andiani, Annisa Dwi Andini, Bilqiis Shahieza Angraini, Nadya Arda Anisa Herdiani Annisa Miranda Arini Rohmawati Athallah, Muhammad Rafi Aura Sukma Andini Bayu Muhammad Iqbal Bonar Panjaitan Brata Mas Pintoko Chandra Jaya Riadi Chlaudiah Julinar Soplero Lelywiary Choirulfikri, Muhammad Rizqi Damayanti, Lisyana Dana Sulitstyo Kusumo Danang Triantoro Murdiansyah David Winalda Delva, Dwina Sarah Deni Saepudin Denny Darlis Dewantara, Muhammad Pascal Dida Diah Damayanti Didit Adytia dina juni restina Dino Caesaron Donni Richasdy Donny Rhomanzah Dzidny, Dimitri Irfan Eki Rifaldi Eko Darwiyanto Ela Nadila Emrald Emrald Erwin Budi Setiawan Fakhrana Kurnia Sutrisno Farisi, Kamaludin Hanif Fatih, Muhammad Abdurrohman Al Ferdian Yulianto Fhira Nhita Guido Tamara Hadi, Salman Farisi Setya Haga Simada Ginting Haidar, Muhammad Dzakiyuddin Harahap, Rizki Nurhaliza Harmandini, Keisha Priya Haura Athaya Salka Herodion Simorangkir Hutama, Nanda Yonda Ika Puspita Dewi Intan Khairunnisa Fitriani Irgi Aditya Rachman Isman Kurniawan Jofardho Adlinnas Jondri Jondri Jordan, Brilliant Kacaribu, Isabella Vichita Kamaludin Hanif Farisi Kautsar Ramadhan Sugiharto Lukito Agung Waskito Luqman Bramantyo Rahmadi Luthfi, Muhammad Faris M. Mahfi Nurandi Karsana Mahendra Dwifebri Purbolaksono Mahendra, Muhammad Hafizh Marendra Septianta Marozi, Ericho Mehdi Mursalat Ismail Mira Rahayu Moch Arif Bijaksana Mohamad Reza Syahziar Muhammad Adzhar Amrullah Muhammad Arif Kurniawan Muhammad Yuslan Abu Bakar Muhammad Zaid Dzulfikar muhammad zaky ramadhan Muhammad Zidny Naf'an Murman Dwi Praseti Musyafa’noer Sandi Pratama Nanda Yonda Hutama Naufal Furqan Hardifa Naufal Hilmiaji Naufal Rasyad Nibras Syihabil Haq Octaryo Sakti Yudha Prakasa Okky Zoellanda A. Tane Pamungkas, Danit Hafiz Praja, Yudhistira Imam Purwita, Naila Iffah Putri, Arla Sifhana Putri, Meira Reynita Putrisia, Denada R. Fajrika hadnis Putra Rafi Hafizhni Anggia Rahadian, Muhammad Rafi Ramdhani, Muhammad Rifqi Fauzi Rastim Rastim Rayhan, Muhammad Aditya Resky Nadia Rizki Luthfan Azhari Rizky Ahmad Saputra Rizky Aria Mu’allim Rizky, Fariz Muhammad Seno Adi Putra Seto Sumargo Shabrina, Ghina Annisa Siddiq, Ikhsan Maulana Sindi Fatika Sari Sri Utami Sri Widowati Sukmawan Pradika Janusange Santoso Suwaldi Mardana Syadzily , Muhammad Hasan Tri Widarmanti Try Moloharto Try Moloharto Vitalis Emanuel Setiawan Wardhani, Fitri Herinda Widi Astuti Widi Astuti Youga Pratama Yuliant Sibaroni Yusuf Nugroho Doyo Yekti Zaena, Siffa Zaenal Abidin ZK Abdurahman Baizal Zulkarnaen, Imran