Sentiment analysis is one of the most crucial tasks in Natural Language Processing (NLP), involving the training of machine learning models to classify text based on the polarity of opinions. Pre-trained Language Models (PLMs) can be applied to downstream tasks through fine-tuning, eliminating the need to train the model from scratch. Specifically, PLMs have been employed for Sentiment Analysis, a process that involves detecting, analyzing, and extracting the polarity of text sentiments. Numerous models have been proposed to address this task, with pre-trained PhoBERT-V2 models standing out as the state-of-the-art language models for Vietnamese. The PhoBERT-V2 pre-training approach is based on RoBERTa, optimizing the BERT pre-training method for more robust performance. In this paper, we introduce a novel approach that combines PhoBERT-V2 and SentiWordnet for Sentiment Analysis of Vietnamese reviews. Our proposed model utilizes PhoBERT-V2 for Vietnamese, offering a robust optimization for the prominent BERT model in the context of Vietnamese language, and leverages SentiWordNet, a lexical resource explicitly designed to support sentiment classification applications. Experimental results on the VLSP 2016 and AIVIVN 2019 datasets demonstrate that our sentiment analysis system has achieved excellent performance in comparison to other models.
The emergence of multimodal data on social media platforms presents new opportunities to better understand user sentiments toward a given aspect. However, existing multimodal datasets for Aspect-Category Sentiment Analysis (ACSA) often focus on textual annotations, neglecting fine-grained information in images. Consequently, these datasets fail to fully exploit the richness inherent in multimodal. To address this, we introduce a new Vietnamese multimodal dataset, named ViMACSA, which consists of 4,876 text-image pairs with 14,618 fine-grained annotations for both text and image in the hotel domain. Additionally, we propose a Fine-Grained Cross-Modal Fusion Framework (FCMF) that effectively learns both intra- and inter-modality interactions and then fuses these information to produce a unified multimodal representation. Experimental results show that our framework outperforms SOTA models on the ViMACSA dataset, achieving the highest F1 score of 79.73%. We also explore characteristics and challenges in Vietnamese multimodal sentiment analysis, including misspellings, abbreviations, and the complexities of the Vietnamese language. This work contributes both a benchmark dataset and a new framework that leverages fine-grained multimodal information to improve multimodal aspect-category sentiment analysis. Our dataset is available for research purposes: https://github.com/hoangquy18/Multimodal-Aspect-Category-Sentiment-Analysis.
In this paper, we present a process of building a social listening system based on aspect-based sentiment analysis in Vietnamese from creating a dataset to building a real application. Firstly, we create UIT-ViSFD, a Vietnamese Smartphone Feedback Dataset as a new benchmark corpus built based on a strict annotation schemes for evaluating aspect-based sentiment analysis, consisting of 11,122 human-annotated comments for mobile e-commerce, which is freely available for research purposes. We also present a proposed approach based on the Bi-LSTM architecture with the fastText word embeddings for the Vietnamese aspect based sentiment task. Our experiments show that our approach achieves the best performances with the F1-score of 84.48% for the aspect task and 63.06% for the sentiment task, which performs several conventional machine learning and deep learning systems. Last but not least, we build SA2SL, a social listening system based on the best performance model on our dataset, which will inspire more social listening systems in future.