Claim Missing Document
Check
Articles

Found 3 Documents
Search

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.
A Measurement for Social Experience and Its Evaluation: A Case Study of University Student Felix, Felix; Regina, Sharlene; Ohyver, Margaretha; Gunawan, Alexander Agung Santoso; Ngarianto, Heri
Business Economic, Communication, and Social Sciences Journal (BECOSS) Vol. 7 No. 2 (2025): BECOSS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/becossjournal.v7i2.13651

Abstract

Social experience refers to interactions and relationships that individuals have with others within their environments. According to researchers, higher levels of social experience can affect many aspects that an individual has, such as self-awareness, social skills, moral reasoning, intelligence, and emotional intelligence. Despite its importance, it is difficult to determine the valid and reliable measurement of social experience. The writer decided to create a survey as a measurement of social experience with 2 latent variables: self-efficacy and self-regulation to know the influence of both indicators on the measurement of social experience with 300 Bina Nusantara University students as its respondents. From the results of the survey, we conclude that verbal persuasion is the most impactful source from self-efficacy that influences social experience, while motivation is the most impactful source from self-regulation that influences social experience. All self-efficacy and self-regulation statements both are valid and reliable with convincing results. Although our results are convincing, it is essential to bear in mind that this study is not without limitations. These limitations include a limited sample size and the potential for biases in sampling and response due to the characteristics of our participants. Therefore, it is advisable for future research endeavors within this field to select participants from various universities and implement preliminary testing procedures to authenticate the survey.