Claim Missing Document
Check
Articles

ANALYSIS OF MULTILINGUAL OPINION POLARIZATION WITH CROSS-LINGUAL LANGUAGE MODEL-ROBUSTLY OPTIMIZED BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS APPROACH (XLM-ROBERTA) Kananta, Ghaitsa Shafa Cinta; Saputro, Dewi Retno Sari; Sutanto, Sutanto
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp1709-1718

Abstract

The rapid growth of digital communication has intensified opinion exchanges across languages and cultures on social media, enriching public discourse while also increasing the risk of polarization that deepens social divisions. Conventional sentiment analysis methods that rely on translation often distort meaning, overlook emotional nuances, and fail to capture rhetorical devices such as irony and sarcasm, thereby limiting their reliability in multilingual contexts. This study examines the capability of XLM-RoBERTa, a multilingual transformer model pretrained on more than 100 languages, to address these challenges by generating consistent semantic representations and accommodating linguistic and cultural diversity without translation. The research employs bibliometric analysis using VOSviewer on 357 Scopus-indexed publications from 2020 to 2025 to map research trends, combined with a literature review that evaluates XLM-RoBERTa in sentiment and opinion analysis. The findings reveal that although XLM-RoBERTa has been widely employed for sentiment classification, text categorization, and offensive language detection, research explicitly focused on multilingual opinion polarization remains limited. Benchmark evaluations further indicate that XLM-RoBERTa surpasses earlier multilingual models, achieving 79.6% accuracy on XNLI and an 81.2% F1-score on MLQA, confirming its robustness in capturing semantic nuances, cultural variations, and rhetorical complexity without translation. The novelty of this research lies in integrating trend-mapping with methodological evaluation, thereby establishing XLM-RoBERTa as a reliable framework for real-time monitoring of global public opinion, supporting evidence-based policymaking, and advancing scholarly understanding of multilingual communication dynamics in the digital era.
HYBRID INTEGRATION OF BERT AND BILSTM MODELS FOR SENTIMENT ANALYSIS Tambunan, Nicolas Ray Amarco; Saputro, Dewi Retno Sari; Widyaningsih, Purnami
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp1719-1730

Abstract

The rapid growth of sentiment analysis research has driven increasing interest in deep learning models, particularly transformer-based architectures such as BERT and recurrent neural networks like BiLSTM. While both approaches have shown substantial success in text classification tasks, each presents distinct strengths and limitations. This study aims to analyze the integration of BERT and BiLSTM models to enhance sentiment classification performance by combining contextual and sequential learning. A bibliometric analysis was conducted using VosViewer based on Scopus-indexed publications from 2020 to 2025, identifying four major thematic clusters related to transformer modeling, recurrent architectures, hybrid integration, and methodological advancements. Comparative findings from benchmark datasets, including SST-2, IMDb, and Yelp Reviews, indicate that hybrid BERT–BiLSTM models achieve superior accuracy compared to single models, reaching up to 97.67% on the IMDb dataset. However, this improvement is associated with increased computational complexity. The proposed framework reinforces the integration between BERT’s contextual embeddings and BiLSTM’s sequential modeling, offering a foundation for developing adaptive, and multilingual sentiment analysis systems. The results highlight future directions in optimizing hybrid architectures for efficiency, cross-lingual adaptability, and domain-specific sentiment understanding.
Co-Authors Ade Susanti Adhitama, Ria Puan Adzakie, Haabi Luckmanoor Agung Nugroho, Tri Wahyu Agung Nugroho, Tri Wahyu Ahmad Faqihi, Ahmad Aji Hamim Wigena Al Barra, Andre Fajry Alfa Lutfiananda, Immas Metika Anik Djuraidah Antoni Wibowo Antoni Wibowo Ariati, Lia Arif Rahman Arrazaq, Khamid Muhammad Astutiningsih, Tiyas ‘Aini, Addin Zuhrotul Baharum, Aslina Budi Usodo Budi Usodo BUDIYONO Budiyono Budiyono Budiyono Budiyono Budiyono, Budiyono Cahyono, Heri Christy, Alexander Yonathan Dewi, Noviana Sukma Doni Susanto dwi hidayati Gustiasih, Restuning Harun Al Rasyid Heri Cahyono Ikawati, Nur Ikhsan Abdul Latif Indriati, Sela Putri Joko Domas, Joko Kananta, Ghaitsa Shafa Cinta Khairina, Fadiah Khamsatul Faizati, Khamsatul Khayati, Fitrotul Khomariah, Nurul Kiki Riska Ayu Kurniawati, Kiki Riska Ayu Kusuma, Nunung Fajar Kusumo, Fahri Aimar M Mardiyana, M Maharani, Swasti Marchamah Ulfa, Marchamah Mardiyana Mardiyana Mardiyana Mardiyana Mardiyana Mardiyana Mardiyana, Mardiyana Mardiyana, Mardiyana Muhamad Safa’udin, Muhamad Muslikhah, Muslikhah Musmiratul Uyun Musta'in, Ghufron Nanang Nabhar Fakhri Auliya, Nanang Nabhar Nanda Noor Fadjrin, Nanda Noor Ningrum, Hanifah Listya Ni’am, Dafi’ Ichsani Aysar Nughthoh Arfawi Kurdhi, Nughthoh Arfawi Nugroho Arif Sudibyo Nurul Khairiatin Nida Pambudi, Pangesti Arum Paryatun, Suji Paryatun, Suji Pradipta Annurwanda, Pradipta Prasetyo, Heri Pratama, Rizcka Indah Hani Prihastini Oktasari Putri Primasari, Dessy Marlinda Purnami Widyaningsih Purwaningsih, Tri Purwaningsih, Tri Putera Khano, Muhammad Nazhif Abda Putri, Diah Purwaning Putri, Matin Enggar Rahman, Arif Ramadhanti, Fajhria Budi Ririn Setyowati Riyadi Riyadi Riyansyah, Husnun Nur Ghiffari Putri Rizky Anggar Kusuma Wardani Safa’udin, Muhamad Santika, Putri Aura Sena, Arya Bima Setiyowati, Ririn Sidiq, Krisna Sujadi, Imam Sulistyaningsih Sulistyaningsih Suprapto, Suprapto Suryani, S Susanti, Ika Sutanto Sutanto Sutanto sutanto sutanto Tambunan, Nicolas Ray Amarco Tanjung, Andjani Ayu Cahaya Ummu Salamah Utami, Dwi Sari Utin Desy Susiaty Wahyu, Nugroho Lambang Wibowo, Gusti Ngurah Adhi Widiyaningsih, Purnami Winarno, Bowo YAFITA ARFINA MUTI Yekti Widyaningsih Yumaroh, Siti Roqhilu Zaidah Nurul Hasanah