Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Asia Information System Journal Data : Journal of Information Systems and Management Jurnal Ilmu Komputer
Wiharjo, Sudarno
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Phishing Email Classification Approach Using Machine Learning Algorithms - A Literature Review Firman; Tukiyat; Wiharjo, Sudarno
Data : Journal of Information Systems and Management Vol. 3 No. 3 (2025): July 2025
Publisher : Indonesian Scientific Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61978/data.v3i3.692

Abstract

Email phishing is one of the cybersecurity threats that continues to grow, utilizing social engineering to obtain sensitive data. Various machine learning-based approaches have been researched to detect and classify phishing emails. This article presents a literature review of phishing email classification methods, including the K-Nearest Neighbor (KNN) algorithm, Naïve Bayes, Support Vector Machine (SVM), Random Forest, and deep learning-based approaches. The discussion included feature extraction techniques (TF-IDF, Word2Vec, BERT), handling data imbalances, and model performance evaluation. This review identifies current research trends, challenges, and gaps for further research.
Analisis Sentimen Pelayanan Pelanggan Mini Market Alfamart Pada Media Sosial Twitter Dengan Naïve Bayes Classifier Aziz, Awaludin; Susanto, Agung Budi; Wiharjo, Sudarno
Jurnal Ilmu Komputer Vol 1 No 2 (2023): Jurnal Ilmu Komputer (Edisi Desember 2023)
Publisher : Universitas Pamulang

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

Abstract

Twitter is one of the social media that is currently popular, here the public is free to have opinions, write, and comment on anything. PT Sumber Alfaria Trijaya with its trademark Alfamart is a company engaged in the retail sector. Not infrequently consumers submit complaints, criticisms, and suggestions through this social media. Community opinion can be used as evaluation material in improving services. In this study, sentiment analysis for Alfamart minimarket customer service was carried out based on data obtained from Twitter. This sentiment analysis aims to classify Alfamart's customer service tweets into positive, negative, and neutral sentiments using the naive Bayes classifier algorithm. The data used is 2000 tweet data and then preprocessing is carried out so that 1691 tweets are clean data. Of the 1691 data analyzed, 1017 positive tweets, 297 negative tweets, and 377 neutral tweets were obtained. Then the data will be divided into 80% training data and 20% test data. The results of the accuracy value are 70% with a Precision value of 70%, a Recall value of 70%, and an F1-Score value of 66%.
ALGORITHMIC OPTIMIZATION INFORMATION AND STRATEGIES FOR INCREASING THE REACH OF BEGINNER CREATOR ACCOUNTS ON FACEBOOK PRO IN INDONESIA Chairul, Muhammad Ilham Firizkillah; Waskita, Arya Adhyaksa; Wiharjo, Sudarno; RA, Okta Reni Azrina
Asia Information System Journal Vol. 4 No. 2 (2025): Asia Information System Journal
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/qa0g3q17

Abstract

The evolution of algorithmic systems on digital platforms has fundamentally transformed the logic of content distribution, shifting from chronological feeds to AI-driven recommendation ecosystems that act as active regulators of creator visibility. While discussions on algorithmic visibility are extensive for platforms like TikTok and Instagram, a significant research gap remains regarding the Indonesian creator ecosystem on Facebook Pro, particularly concerning how human–algorithm interaction shapes content performance. This study aims to analyze algorithm optimization strategies among beginner creators on Facebook Pro by examining the critical relationship between content format consistency, engagement velocity, and algorithmic distribution. Research Method: Adopting a qualitative-descriptive design, a case study was conducted on two Indonesian creator accounts—Muhammad Ilham Firizkillah and Sejenak Hening—representing contrasting storytelling-educational and motivational production paradigms. Primary data were collected from Facebook Pro Insights between July and October 2025, utilizing Python-based analytics to evaluate Reels performance, retention rates, and audience growth. The results indicate a striking contrast in performance: the Sejenak Hening account achieved an 876% increase in reach and 1.1 million views by maintaining consistent themes and visuals, allowing the algorithm to recognize stable patterns for exponential distribution. Conversely, the Ilham Firizkillah account saw a 52% decline in views due to high format variation and weak early interaction (2%), triggering algorithmic momentum decay. Findings confirm a perfect correlation (r = 1.00) between format stability and algorithmic reach. Implication and Recommendation: These findings emphasize that sustainable organic growth is determined by the synchronization between predictable upload patterns and the machine-learning system’s real-time evaluation of interaction efficiency. It is recommended that beginner creators prioritize the "three-second hook" to capture initial attention and maintain strict discipline in narrative and visual formats to build algorithmic credibility.
Co-Authors Agung Budi Susanto Aziz, Awaludin Chairul, Muhammad Ilham Firizkillah Firman Okta Reni Azrina RA Tukiyat Waskita, Arya Adhyaksa