Sentiment Analysis of Digital Banking Reviews Using Machine Learning and Large Language Models DOI Open Access
Raghad Alawaji, Abdulrahman Aloraini

Electronics, Journal Year: 2025, Volume and Issue: 14(11), P. 2125 - 2125

Published: May 23, 2025

Sentiment analysis, in the context of digital banking reviews, aims to assess customer satisfaction and support service enhancement. Despite increasing attention sentiment analysis across domains, Arabic reviews remain underexplored. To bridge this gap, we introduce a dataset 4922 from three major Saudi banks with categories positive, negative, or conflict—providing actionable insights for banks. We evaluate using several machine learning models four large language (LLMs)—GPT 3.5, GPT 4, Llama-3-8B-Instruct, SILMA—using zero-shot (no labeled examples) few-shot (a few strategies. Our results show that 4 performs best among LLMs settings, while traditional still outperform LLMs, Voting Classifier achieving 90.24% accuracy. This study contributes domain-specific comparative research practical improvements services.

Language: Английский

Using Virtual Reality During Chemotherapy to Support Emotional Regulation in Patients: Adding an Olfactory Reinforcement or Not? DOI Creative Commons
Hélène Buche, Aude Michel, Nathalie Blanc

et al.

Virtual Worlds, Journal Year: 2025, Volume and Issue: 4(2), P. 16 - 16

Published: April 16, 2025

Introduction: In line with previous research conducted during chemotherapy to explore whether virtual reality (VR) can support patients’ emotional regulation, this study examines the relevance of adding olfactory reinforcement VR sessions breast cancer treatment. Methods: An experimental protocol assessed impact sensoriality in 50 patients over three sessions. Each patient experienced a 10-min immersion natural environment under randomized conditions: Contemplative VR, Participatory reinforcement. The sense presence measured immersion, while anxiety, depression, and state were evaluated using within-subject design compare effects each modality. Results: A reduction anxiety depression was observed regardless type experienced. interactive multimodal nature may their regulation. Conclusions: This provides preliminary evidence for usefulness enhancement patients. potential contributes by inducing positive experience soothing environment. reported results highlight value sensorimotor which also stimulates smell, improving supportive care.

Language: Английский

Citations

0
Sentiment Analysis of Digital Banking Reviews Using Machine Learning and Large Language Models DOI Open Access
Raghad Alawaji, Abdulrahman Aloraini

Electronics, Journal Year: 2025, Volume and Issue: 14(11), P. 2125 - 2125

Published: May 23, 2025

Sentiment analysis, in the context of digital banking reviews, aims to assess customer satisfaction and support service enhancement. Despite increasing attention sentiment analysis across domains, Arabic reviews remain underexplored. To bridge this gap, we introduce a dataset 4922 from three major Saudi banks with categories positive, negative, or conflict—providing actionable insights for banks. We evaluate using several machine learning models four large language (LLMs)—GPT 3.5, GPT 4, Llama-3-8B-Instruct, SILMA—using zero-shot (no labeled examples) few-shot (a few strategies. Our results show that 4 performs best among LLMs settings, while traditional still outperform LLMs, Voting Classifier achieving 90.24% accuracy. This study contributes domain-specific comparative research practical improvements services.

Language: Английский

Citations

0