Multimodal Interaction and Fused Graph Convolution Network for Sentiment Classification of Online Reviews

Article Computer Science, Information Systems

Multimodal Sentiment Analysis With Image-Text Interaction Network

Tong Zhu et al.

Summary: More and more users are sharing their emotions or opinions on social networks through posting images and text. This has led to an increasing interest in multimodal sentiment analysis. The relationship between affective image regions and associated text is crucial for effective multimodal sentiment analysis. However, existing approaches fail to fully explore this interaction, resulting in suboptimal results. Therefore, we propose a new image-text interaction network (ITIN) that captures the relationship between affective image regions and text, outperforming state-of-the-art methods.

IEEE TRANSACTIONS ON MULTIMEDIA (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Gated attention fusion network for multimodal sentiment classification

Yongping Du et al.

Summary: Sentiment classification is important for helping people make better decisions by exploring their expressed opinions. This paper introduces a novel multimodal sentiment classification model based on a gated attention mechanism. The model emphasizes text segments by using image features and focuses on the text that affects sentiment polarity. Experimental results demonstrate the effectiveness of the proposed model in outperforming previous state-of-the-art models.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Mathematics

Triplet Contrastive Learning for Aspect Level Sentiment Classification

Haoliang Xiong et al.

Summary: A Triplet Contrastive Learning Network is introduced to coordinate syntactic and semantic information in sentiment classification tasks, achieving state-of-the-art results in Aspect Level Sentiment Classification as demonstrated by experiments on benchmark datasets.

MATHEMATICS (2022)

添加到收藏夹

Article Computer Science, Software Engineering

Hierarchical Hybrid Neural Networks With Multi-Head Attention for Document Classification

Weihao Huang et al.

Summary: This paper proposes a hierarchical hybrid neural network with multi-head attention (HHNN-MHA) model for document classification. Experimental results demonstrate the effectiveness and competitiveness of the proposed method.

INTERNATIONAL JOURNAL OF DATA WAREHOUSING AND MINING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Hierarchical self-adaptation network for multimodal named entity recognition in social media

Yu Tian et al.

Summary: Multimodal Named Entity Recognition aims to identify named entities in user-generated posts with both images and texts. Previous methods benefit from visual features when text and image are aligned, but may fail when the image is missing or mismatched. To address these issues, a novel model HSN is proposed, which achieved state-of-the-art results on Real-world multimodal NER dataset and Twitter multimodal NER dataset.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Mathematical & Computational Biology

Text Semantic Classification of Long Discourses Based on Neural Networks with Improved Focal Loss

Dan Jiang et al.

Summary: The study proposes a novel end-to-end model called CRAFL for semantic classification of Chinese long discourses, which addresses the issue of high-dimensional and sparse data distribution imbalance through convolutional layer with attention mechanism, recurrent neural networks, and improved focal loss function.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Hierarchical multi-attention networks for document classification

Yingren Huang et al.

Summary: This paper introduces a novel method for document classification, applying different attention strategies at multiple levels to achieve high accuracy. Research indicates that this method is more effective compared to other approaches.

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

LD-MAN: Layout-Driven Multimodal Attention Network for Online News Sentiment Recognition

Wenya Guo et al.

Summary: The prevailing use of both images and text on the web necessitates multimodal sentiment recognition. It is challenging to predict readers' sentiment after reading online news articles due to their complex structures. A layout-driven multimodal attention network is proposed to address this issue effectively.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence