Article Per Year (5 Year)
p-Index From 2020 - 2025
1.168
P-Index
This Author published in this journals
All Journal Business Economic, Communication, and Social Sciences Journal (BECOSS) Engineering, Mathematics and Computer Science Journal (EMACS)
Gunawan, Alexander Agung Santoso
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Industrial & Manufacturing Engineering Mathematics

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

Found 2 Documents
Search
Journal : Engineering, Mathematics and Computer Science Journal (EMACS)

 1 
Classifying Viral Twitter with Transformer Models and Multi-Layer Perceptron Tedjasulaksana, Jeffrey Junior; Gunawan, Alexander Agung Santoso
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 1 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i1.11580

Abstract

The classification of virality levels in Indonesian tweets is explored in this research using advanced natural language processing techniques and machine learning algorithms. Transformer models such as RoBERTa for sentiment analysis and XLNet for text embedding, alongside Multi-Layer Perceptron (MLP) classifiers, are leveraged to address the challenge of predicting tweet virality. Emotion features are incorporated, and cost-sensitive methods for handling class imbalance are implemented, resulting in robust performance demonstrated by our model. Intriguing correlations between tweet sentiment, emotion distribution, and virality levels are uncovered through sentiment analysis and emotion detection. The efficacy of XLNet in capturing contextual nuances, outperforming BERTweet, is highlighted by our findings. Furthermore, the integration of emotion features and cost-sensitive methods enhances the model's predictive accuracy, offering valuable insights for marketers and businesses seeking to optimize their social media strategies. The proposed model achieves an accuracy of 95% and an F1-Score of 59%.
An Experiment to Prevent Malicious Actors from Compromising Private Digital Assets Over a Public Network Hartanto, Feliks; Budiman, Budiman; Gwei, Eldwin; Gunawan, Alexander Agung Santoso; Edbert, Ivan Sebastian
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 6 No. 1 (2024): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v6i1.10389

Abstract

In the current millennium, human society has immensely improved its ability to obtain and distribute information. This change on the other hand, has caused the majority of daily routines to actively involve the usage of computers and mobile devices, which in turn has made people rely heavily on the availability of internet access. This fact was taken advantage of, causing a massive increase in public networks by people or businesses to draw in customers or just as simple public service. This increase gives both ease and risks which this paper will address, specifically on the security measures in network devices that are nearby, and the solution proposed to provide complementary insight on securing the technologies. The authors of this paper supply the main point of the research through experimental efforts i.e., by testing the solution in a real-life scenario. The solution itself involves the configuration of a Raspberry Pi into a VPN server and rerouting all traffic into the Raspberry server so that it will be encrypted and safe from the dangers that will be mentioned in later parts of this paper. The result of the experiment shows that the proposed solution can successfully encrypt the targeted packet so it can’t be read by malicious attackers. Although the solution works it can’t be simply applied to every public network due to internet connection protocols and its inconvenience. Future research will involve the improvement or rework of the solution until the issues mentioned above are solved.
Co-Authors Budiman Budiman Edbert, Ivan Sebastian Felix Felix Gwei, Eldwin Hartanto, Feliks Heri Ngarianto, Heri Ohyver, Margaretha Regina, Sharlene Tedjasulaksana, Jeffrey Junior