Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Media Ekonomi dan Manajemen Formosa Journal of Computer and Information Science
Tri Noviantoro
Universitas Muhammadiyah Lampung
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Psychographic Profiling of Skincare Indonesian Consumers: A Multidimensional Segmentation Approach Suryaneta Suryaneta; Andhyka Tyaz Nugraha; Tri Noviantoro; Nisa Novia Avien Christy; M.Raihan Huzhaifi Muslim
Media Ekonomi dan Manajemen Vol 41, No 1 (2026): January 2026
Publisher : Fakultas Ekonomika dan Bisnis UNTAG Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56444/mem.v41i1.6609

Abstract

This study assesses whether a multidimensional psychographic base that joins values, life visions, aesthetic styles, and media preferences can explain skincare consumer behavior in Indonesia and translate directly into brand decisions. A cross sectional online survey of two hundred seventy consumers employed seven-point scales for twelve value items, ten life vision items, nine aesthetic style items, and nine media preference items. The instrument showed satisfactory internal consistency with Cronbach’s alpha of 0.81 for values, 0.78 for life visions, 0.85 for aesthetic styles, and 0.78 for media preferences. Dimensionality was examined with principal components at the block level and audience segments were identified with Gaussian mixture models, with the number of classes selected by the Bayesian Information Criterion. The analysis yielded six interpretable segments. Values place holistic health, emotional balance, and environmental or ethical responsibility at the center of decision making. Aesthetic attraction is strongest for modern minimalism followed by classic and sporty codes, while luxury and futuristic codes are less salient. Media use concentrates on Instagram and TikTok with e-commerce and YouTube as important complements. These findings establish a direct bridge from latent motives to actionable levers by pairing claims and design languages with the media habitats in which persuasion occurs. Brand teams can emphasize health and calm narratives with credible testing, employ transparent and minimalist clinical visual systems, and activate creator led short video content with seamless handoff to e-commerce, while using longer instructional content for audiences that prefer YouTube and Facebook. Limitations include a youthful and digital first sample, self-report measures, and a cross sectional design. The study offers an empirically grounded baseline for psychographic profiling in skincare and a practical roadmap for audience in culture strategy that is both differentiated and repeatable.
Comparative Study of Machine Learning Models for Sentiment Analysis of Amazon Product Reviews Tri Noviantoro; Suryaneta Suryaneta
Formosa Journal of Computer and Information Science Vol. 5 No. 1 (2026): March 2026
Publisher : PT FORMOSA CENDEKIA GLOBAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55927/fjcis.v5i1.16389

Abstract

This research presents a comparative analysis of four popular sentiment classification models: Naive Bayes, Support Vector Machine (SVM), Long Short-Term Memory (LSTM) networks, and Bidirectional Encoder Representations from Transformers (BERT). The models are evaluated using the Amazon Product Reviews dataset based on their ability to classify sentiments into positive or negative categories. The results show that BERT outperforms the other models in accuracy, precision, recall, and F1-score, demonstrating its superior ability to capture complex contextual relationships in text. LSTM performed well, particularly in recalling positive sentiments, but was outperformed by BERT overall. Conversely, Naive Bayes and SVM exhibited lower accuracy and higher false positive rates, highlighting their limitations in handling nuanced, context-dependent text. This study emphasizes the trade-offs between traditional machine learning models and advanced deep learning techniques.
Co-Authors Andhyka Tyaz Nugraha M.Raihan Huzhaifi Muslim Nisa Novia Avien Christy Suryaneta