Article Per Year (5 Year)
p-Index From 2021 - 2026
1.399
P-Index
This Author published in this journals
All Journal Jurnal Nasional Komputasi dan Teknologi Informasi Jurnal Teknologi Informasi, Komputer, dan Aplikasinya (JTIKA ) Jurnal Dinamika Informatika (JDI) Arcitech: Journal of Computer Science and Artificial Intelligence Jurnal Ilmu Teknologi Informasi Indonesia (JITIFNA) Jurnal Simki Economic Jurnal Komputer, Informasi dan Teknologi
Harun Al Rosyid
Universitas Negeri Surabaya
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Neuroscience Transportation

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Pengaruh Uang Saku dan Penggunaan Media Sosial terhadap Perilaku Konsumtif Mahasiswa Universitas Negeri Surabaya: Studi Kasus: Program Studi S1 Ekonomi Islam Angkatan 2022 Eliya Rahmawati; Dafina Nur Faiza; Miranda Dwi Febrianti; Cahya Dwi Rahmawati; Mohammad Abdul Rosyid; Nasyiwa Ega Palupi; Suci Wahyuni Haddad; Harun Al Rosyid
Jurnal Simki Economic Vol 9 No 1 (2026): Volume 9 Nomor 1 Tahun 2026
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/jse.v9i1.1473

Abstract

In the digital era, student consumer behavior is influenced by pocket money and social media usage. Pocket money used for daily needs can come from parents or personal income through part-time work. Meanwhile, social media functions as a platform for accessing information, interacting with others, and receiving various advertisements. In this regard, this study aims to analyze the influence of pocket money and social media usage on student consumer behavior. Therefore, the data were analyzed using statistical tests such as validity, reliability, classical assumption tests, and multiple linear regression. This study shows that pocket money has no significant effect on student consumer behavior, while social media usage has a significant and positive influence. Simultaneously, pocket money and social media usage have a significant effect on consumer behavior, with a contribution of 55.1%. Of the two factors, social media has a more dominant role in driving student consumer behavior.
Analisis Sentimen Komentar Youtube Rencana Pemerintah terhadap Pemblokiran Roblox Menggunakan Model Naïve Bayes Firdiawati Firdiawati; Salvia Nabillah Syifa; Harun Al Rosyid
Jurnal Komputer, Informasi dan Teknologi Vol. 6 No. 1 (2026): June
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v6i1.3454

Abstract

Perkembangan teknologi digital telah meningkatkan popularitas platform permainan daring seperti Roblox. Namun, rencana pemerintah untuk memblokir platform tersebut memunculkan beragam respons publik yang terlihat pada kolom komentar YouTube. Penelitian ini bertujuan untuk mengidentifikasi kecenderungan sentimen masyarakat terhadap isu pemblokiran Roblox. Data penelitian terdiri dari 2.500 komentar YouTube yang diperoleh melalui YouTube Data API, kemudian melalui tahapan preprocessing dan pelabelan sentimen berbasis lexicon hingga tersisa 2.427 komentar yang layak dianalisis. Data selanjutnya diubah menjadi fitur TF-IDF dan diklasifikasikan menggunakan metode Naïve Bayes algoritma Multinomial Naïve Bayes dengan skema pembagian data 90:10 dan 80:20. Hasil terbaik diperoleh pada skema 80:20 dengan akurasi 71,19%, precision 73,31%, recall 71,19%, dan f1-score 70,23%. Hasil yang didapat dari penelitian menunjukkan bahwa opini publik didominasi sentimen netral dengan kecenderungan negatif. Penelitian ini menyimpulkan bahwa Multinomial Naïve Bayes efektif dalam mengklasifikasikan sentimen komentar berbahasa Indonesia terkait isu pemblokiran Roblox.
Analisis Sentimen Pengguna X Terhadap Cryptocurrency di Platform X dengan Pendekatan Data Mining Menggunakan Classifier Naïve Bayes Moch. Anang Ardiansyah; Raka Tegar Wicaksono; Harun Al Rosyid

Publisher :

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i6.10159

Abstract

Abstrak - Diskusi mengenai aset kripto di platform X mengalami peningkatan pesat, khususnya saat peristiwa Bitcoin Halving yang memicu beragam respon dari pengguna. Studi ini bertujuan untuk mengidentifikasi sentimen publik terkait Bitcoin Halving dengan metode analisis teks. Data dikumpulkan melalui API X dan diproses dengan tahapan pre-processing seperti pembersihan data, normalisasi, tokenisasi, penghilangan kata yang tidak penting, serta stemming agar teks lebih terstruktur dan siap untuk diklasifikasikan. Untuk mengatasi ketidakseimbangan distribusi kelas sentimen, digunakan teknik Synthetic Minority Over-Sampling Technique (SMOTE) untuk menambah data sintetis pada kelas minoritas. Model klasifikasi yang digunakan adalah Complement Naïve Bayes (CNB), varian Naïve Bayes yang sesuai untuk data teks berdimensi tinggi dengan ketidakseimbangan kelas. Evaluasi dilakukan dengan dua variasi rasio pembagian data latih dan uji, yakni 90:10 dan 80:20. Hasil menunjukkan akurasi 64% pada rasio 90:10 yang meningkat menjadi 66% pada rasio 80:20, menunjukkan bahwa proporsi data latih memengaruhi performa klasifikasi sentimen secara stabil. Penelitian ini memberikan gambaran awal terhadap persepsi publik pada Bitcoin Halving dan dapat menjadi dasar untuk penelitian lanjutan dalam bidang analisis sentimen aset kripto.Kata kunci : bitcoin halving; sentimen publik; complement naïve bayes; smote; x; Abstract - Discussions about crypto assets on platform X have been rapidly increasing, especially during the Bitcoin Halving event, which often triggers diverse reactions from users. This study aims to identify public sentiment regarding Bitcoin Halving through a text analysis approach. Data were collected via the X API and processed with several pre-processing steps such as data cleansing, normalization, tokenization, stop-word removal, and stemming to structure the text for classification. To address the imbalanced distribution of sentiment classes, the Synthetic Minority Over-Sampling Technique (SMOTE) was applied to generate synthetic samples for the minority class. The classification model employed is Complement Naïve Bayes (CNB), a variant of Naïve Bayes suited for high-dimensional text data with class imbalance. The model was evaluated using two different train-test split ratios, 90:10 and 80:20. Results showed an accuracy of 64% with the 90:10 split, which improved to 66% with the 80:20 split, indicating that the proportion of training data influences the stability of sentiment classification performance. This study provides an initial understanding of public perception towards Bitcoin Halving and serves as a basis for further research in crypto asset sentiment analysis.Keywords: bitcoin halving; public sentiment; complement naïve bayes; smote; X;
Komparasi Algoritma Naive Bayes dan Support Vector Machine pada Analisis Sentimen Komentar Instagram Laga El Clásico Barcelona vs Real Madrid Muhammad Irvan Maulana; Savana Putra Aditama; Harun Al Rosyid
Jurnal Dinamika Informatika Vol. 15 No. 1 (2026): Vol. 15 No. 1 (2026)
Publisher : Program Studi Informatika Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/jdi.v15i1.432

Abstract

The rapid development of information and communication technology has driven social media to become a primary platform for users to express opinions on various events, including prestigious football matches such as El Clásico between Barcelona and Real Madrid. The high level of interaction among Instagram users generates a large volume of comments with unstructured text characteristics and diverse sentiments, making automatic sentiment analysis necessary to understand public opinion trends. This study aims to analyze the sentiment of Instagram user comments related to the El Clásico match by comparing the Naive Bayes and Support Vector Machine (SVM) algorithms. The dataset consists of 1,526 comments with an imbalanced sentiment class distribution. The research stages include text preprocessing, term weighting using Term Frequency–Inverse Document Frequency (TF-IDF), and sentiment classification. The experimental results show that the SVM algorithm outperforms Naive Bayes, achieving an accuracy of 62.88% and a weighted F1-score of 0.62, while Naive Bayes achieves an accuracy of 59.53% and a weighted F1-score of 0.52. These results indicate that SVM is more effective in handling high-dimensional data and imbalanced class distributions in social media sentiment analysis.
Analisis Sentimen Opini Warga X terhadap Banjir di Sumatera Menggunakan Naive Bayes Novi Eka Rahmawati; Rahmatul Ummah; Harun Al Rosyid
Jurnal Dinamika Informatika Vol. 15 No. 1 (2026): Vol. 15 No. 1 (2026)
Publisher : Program Studi Informatika Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/jdi.v15i1.462

Abstract

This study aims to analyze public sentiment regarding flooding in Sumatra based on data from social media platform X. Flooding is a frequent natural disaster in Sumatra and elicits a variety of public responses, many of which are expressed through social media. Social media platform X was chosen as the data source because it is open and real-time, allowing it to broadly represent public opinion. The research data consists of 1,030 Indonesian-language tweets collected through a crawling process using the official API for X, using keywords related to flooding in Sumatra. After data cleaning, 873 tweets were obtained, which were then processed through text mining stages, including text preprocessing, manual sentiment labeling, and dividing the data into training and test data. The training data consisted of 650 tweets, while the test data consisted of 223 tweets. Sentiment classification was performed using the Naive Bayes algorithm with the assistance of RapidMiner software. Model evaluation was performed using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results showed that the Naive Bayes algorithm performed quite well in sentiment classification. Furthermore, the analysis shows that public opinion regarding the flooding in Sumatra is dominated by negative sentiment. This research is expected to provide insight into public perceptions and inform disaster management policymaking.
Klasifikasi Sentimen Komentar Youtube Demonstrasi DPR RI Menggunakan Support Vector Machine Siti Aulia Rahmadhani; Lia Dwi Rusanti; Harun Al Rosyid
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 5 No. 2 (2025): December 2025
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v5i2.15316

Abstract

Demonstrations against the Indonesian House of Representatives (DPR RI) have triggered extensive public opinion flows on social media; however, sentiment mapping of Indonesian-language comments on YouTube live broadcasts of political issues still requires more structured methodological reporting and evaluation. This study aims to classify public sentiment from 1,493 YouTube comments related to DPR RI demonstrations using the Support Vector Machine (SVM) algorithm. Data were collected via the YouTube Data API and subsequently processed through text cleaning, case folding, normalization, tokenization, stopword removal, and stemming. Sentiment labeling was performed using an Indonesian lexicon-based approach to generate three sentiment classes (positive, negative, and neutral), with neutral sentiment being dominant. Feature representation was constructed using CountVectorizer, and the SVM model was trained using an 80:20 split for training and testing data. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics, achieving an accuracy of 92.4% (weighted performance of 0.924). Word frequency analysis was also employed to identify dominant terms within each sentiment class. These findings demonstrate the effectiveness of SVM in mapping digital public perceptions on political issues and highlight its potential to support data-driven policy evaluation.
Pengembangan Learning Management System Terintegrasi Project Based Learning Untuk Mendukung Hasil Belajar Pada Materi Konfigurasi Routing(Studi Kasus Siswa Kelas Xi Tjkt Smkn 1 Kediri) Husna Lathifunisa Arif; Harun Al Rosyid
Jurnal Ilmu Teknologi Informasi Indonesia Vol. 2 No. 2 (2026): JITIFNA - Juli
Publisher : CV. SINAR HOWUHOWU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70134/jitifna.v2i2.1956

Abstract

This study is motivated by students' low learning outcomes in the subject matter, caused by suboptimal teaching methods and a lack of interactive media to support independent networking practice. This research aims to develop a Moodle-based Learning Management System (LMS) named "SmeksaRoute," integrated with Project-Based Learning (PjBL), to improve student learning outcomes in the Routing Configuration subject at SMKN 1 Kediri. This study employs a Research and Development (R&D) approach using the ADDIE (Analysis, Design, Development, Implementation, Evaluation) development model, along with a quasi-experimental research design to determine the effectiveness of the developed product. The research subjects consisted of 68 students divided into two groups: a control class (34 students) applying the existing teaching method, and an experimental class (34 students) utilizing "SmeksaRoute". Practical sessions were conducted through GNS3 network simulation using MikroTik RouterOS devices. The analysis results indicate that "SmeksaRoute" falls into the "highly valid" category, with validation scores reaching 94% for media, 88% for teaching modules, 88% for learning materials, and 94% for assessment questions. The learning outcome data were analyzed using the Shapiro-Wilk normality test and Levene's test for homogeneity, followed by the Mann-Whitney U hypothesis test due to non-normally distributed data. The average posttest score for the control class was 71.18, whereas the experimental class achieved 78.68. The significance value from the Mann-Whitney U Test was 0.0004428 (< 0.05), indicating a significant difference between the two classes. Overall, "SmeksaRoute," as a PjBL-integrated LMS for the Routing Configuration subject, has proven to be both valid and effective in improving student learning outcomes.  
PENERAPAN DATA MINING MENGGUNAKAN ALGORITMA K-MEANS UNTUK ANALISIS DATA BELANJA ONLINE MAHASISWA Deiva Verlyn Marjuki; Mutyara Safitri; Harun Al Rosyid
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 8 No 1 (2026): Maret 2026
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v8i1.553

Abstract

This study was conducted to analyze the online shopping behavior of college students using the K-Means algorithm as a clustering technique in data mining. This study was motivated by the lack of systematic segmentation of student shopping behavior, which limits the understanding of purchasing characteristics within this consumer group. Unlike previous studies that mostly examine general retail customers or broad e-commerce users, this study specifically focuses on university students by integrating demographic and behavioral attributes. The originality of this study is reflected in the simultaneous use of six variables, namely gender, shopping time, product type, expenditure level, payment method, and purchase decision factors. Data were collected through an online survey involving 200 active college students. The research stages consisted of data cleaning, data category transformation using One-Hot Encoding, clustering model construction using the K-Means algorithm, and cluster evaluation using the Silhouette method. The evaluation results showed that the optimal number of clusters was k = 3, achieving the of 0.0913. Three distinct segments of college students' online shopping behavior were identified, providing insights that can support more targeted marketing strategies and student-oriented e-commerce services.
Prediksi Tren Saham PT. Telkom Indonesia Tbk Menggunakan Metode OLS Putri Vikho Andini; Atha Maulidan Zuhdi; Harun Al Rosyid

Publisher :

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v9i1.10384

Abstract

Abstrak - Penelitian ini bertujuan untuk meramalkan pergerakan harga saham PT Telkom Indonesia Tbk pada periode 2020–2024 dengan memanfaatkan metode Ordinary Least Squares (OLS). Data historis harian diperoleh dari Investing.com dengan rentang waktu 2 Januari 2020 hingga 30 Desember 2024. Data dibagi menjadi 80% data pelatihan dan 20% data pengujian, kemudian diolah menggunakan bahasa pemrograman Python pada lingkungan Google Colab. Model OLS dilatih menggunakan variabel harga historis dan diterapkan untuk menghasilkan prediksi pada periode pengujian, yaitu 20 Desember 2023 sampai 30 Desember 2024. Hasil peramalan disajikan dalam bentuk visualisasi grafik tren dan tabel perbandingan antara nilai aktual dan nilai yang diprediksi. Evaluasi model dilakukan dengan menggunakan Mean Absolute Percentage Error (MAPE) sebagai indikator akurasi peramalan. Hasil penelitian menunjukkan bahwa model OLS mampu mengikuti pola umum pergerakan harga saham TLKM, dengan nilai MAPE yang berada dalam kategori dapat diterima untuk analisis peramalan berbasis tren. Penelitian ini menyimpulkan bahwa metode OLS dapat digunakan sebagai pendekatan dasar dalam memprediksi tren harga saham dan dapat menjadi acuan untuk penelitian lanjutan yang menggunakan metode peramalan yang lebih kompleks.Kata kunci: Prediksi Saham; Metode OLS; Tren Saham; Forecasting; MAPE; Abstract - This study aims to predict the movement of PT Telkom Indonesia Tbk's share price for the period 2020–2024 using the Ordinary Least Squares (OLS) method. The research utilizes daily historical stock data obtained from Investing.com, covering the period from January 2nd, 2020 until December 30th 2024. The data was divided into 80% training data and 20% testing data, which are processed using Python in the Google Colab environment. The OLS model is trained using historical price variables and then applied to generate predictions on the testing period from 20 December 2023 to 30 December 2024. The forecasting results are presented in the form of trend graph visualizations and comparison tables between actual and predicted values. The model evaluation was conducted using Mean Absolute Percentage Error (MAPE) as a forecasting accuracy indicator. The findings show that the OLS model is able to capture the general movement of TLKM stock trends, with the resulting MAPE value indicating that the model performs at an acceptable level for trend-based forecasting. The study concludes that OLS can be used as a baseline method for stock trend prediction and may serve as a reference for further comparative or advanced forecasting models.Keywords: Stock Prediction; OLS Method; Stock Trend; Forecasting; MAPE;
Co-Authors Atha Maulidan Zuhdi Cahya Dwi Rahmawati Dafina Nur Faiza Deiva Verlyn Marjuki Eliya Rahmawati Firdiawati Firdiawati Husna Lathifunisa Arif Lia Dwi Rusanti Miranda Dwi Febrianti Moch. Anang Ardiansyah Mohammad Abdul Rosyid Muhammad Irvan Maulana Mutyara Safitri Nasyiwa Ega Palupi Novi Eka Rahmawati Putri Vikho Andini Rahmatul Ummah Raka Tegar Wicaksono Salvia Nabillah Syifa Savana Putra Aditama Siti Aulia Rahmadhani Suci Wahyuni Haddad