2023 International Joint Conference on Neural Networks (IJCNN) 2023
DOI: 10.1109/ijcnn54540.2023.10191445
|View full text |Cite
|
Sign up to set email alerts
|

BIT: Improving Image-text Sentiment Analysis via Learning Bidirectional Image-text Interaction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 35 publications
0
1
0
Order By: Relevance
“…In summary, traditional single modal sentiment analysis methods for tourism reviews cannot fully capture emotional semantics and were prone to ignoring emotional information with important features (Das et al, 2023;Lu et al, 2022). Although some researchers began to study multimodal sentiment analysis tasks, they only simply concatenated image features and text features into the classifier, without fully considering the bidirectional correlation between image and text data (Xiao et al, 2023). In addition, the multimodal sentiment analysis methods for tourism reviews still faced many other unresolved problems and challenges, such as polysemy, contextual information extraction and important feature differentiation.…”
Section: Image and Text-based Sentiment Analysis Methodsmentioning
confidence: 99%
“…In summary, traditional single modal sentiment analysis methods for tourism reviews cannot fully capture emotional semantics and were prone to ignoring emotional information with important features (Das et al, 2023;Lu et al, 2022). Although some researchers began to study multimodal sentiment analysis tasks, they only simply concatenated image features and text features into the classifier, without fully considering the bidirectional correlation between image and text data (Xiao et al, 2023). In addition, the multimodal sentiment analysis methods for tourism reviews still faced many other unresolved problems and challenges, such as polysemy, contextual information extraction and important feature differentiation.…”
Section: Image and Text-based Sentiment Analysis Methodsmentioning
confidence: 99%