A study on the epidemiology of COVID-19 in the Banias and Alkadmos areas of Syria during 2021.

Al-Tameemi, K.; Nassour, R.; Sleman, R. A.; Daoud, M. S.; Murad, L. S.

doi:10.21161/mjm.221505

Cited by 3 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high-level features are the third category [23]. Facial expressions or body movements are considered high-level semantic features.…”

Section: ) Visual Feature Extractionmentioning

confidence: 99%

“…Facial expressions are the essential signals for comprehending emotions and feelings. These features are mostly extracted using Convolutional Neural Networks (CNN)-based models, according to [20] These features can be generated using pre-trained classifiers or semantic embedding [23]. Pre-trained Convolutional Neural Network models, such as VGG16, VGG19 [24], Xception [25], Inception V3 [26], and Resnet [27], are advanced image classification methods that extract high-level semantic information from images.…”

Section: ) Visual Feature Extractionmentioning

confidence: 99%

“…Visual sentiment classification techniques may be classified as Machine learning, Deep Learning, and transfer learning methods. Although the predominant method employed is machine learning, which relies heavily on manually created features to extract and classify visual data [23], performing sentiment analysis on visual data has become a deep learning-based task.…”

Section: ) Visual Sentiment Classificationmentioning

confidence: 99%

“…Convolutional Neural Network-based models have been used to extract visual information [29]. as well as the transfer learning technique, which enabled the use of powerful pre-trained models (VGG, ResNet, Inception) that were created for other purposes, and adapted to specific tasks like sentiment analysis [22], [23].…”

Section: ) Visual Sentiment Classificationmentioning

confidence: 99%

“…The second approach intends to explore the inner linkages and correlation between the modalities by modelling the properties of multiple sources together. it enables flexible data combining Researchers develop models tailored to their specific research requirements and the context of the problem we denote it as model-based fusion ( [23], [35], [39]).…”

Section: A Fusion Approaches In Msamentioning

confidence: 99%

See 4 more Smart Citations

Textual-Visual multimodal sentiment analysis: A Review of Approaches and Challenges

Fatimi,

Sabbar,

Bekkhoucha

2023

2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)

View full text Add to dashboard Cite

Multimodal analysis is the discipline that mines and analyses data from datasets where inputs comprise more than one type of data. While traditional sentiment analysis primarily uses textual data, the rise of the available visual data has caused the appearance of visual sentiment analysis. Later on, the idea of combining multiple types of data for sentiment analyses seems to be more prominent. Multimodal sentiment analysis integrates text, acoustics, and visuals to enrich insights from individual modalities and eliminate ambiguities. This paper reviews textimage multimodal sentiment analysis; it discusses the unimodal sentiment analysis of both visual and textual data separately; then introduces the multimodal sentiment analysis approach with an emphasis on textual-visual methods, examines its different stages, and fusion techniques and concludes by addressing associated challenges and perspectives.

show abstract

“…The high-level features are the third category [23]. Facial expressions or body movements are considered high-level semantic features.…”

Section: ) Visual Feature Extractionmentioning

confidence: 99%

Section: ) Visual Feature Extractionmentioning

confidence: 99%

Section: ) Visual Sentiment Classificationmentioning

confidence: 99%

Section: ) Visual Sentiment Classificationmentioning

confidence: 99%

Section: A Fusion Approaches In Msamentioning

confidence: 99%

See 3 more Smart Citations

Textual-Visual multimodal sentiment analysis: A Review of Approaches and Challenges

Fatimi,

Sabbar,

Bekkhoucha

2023

2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)

View full text Add to dashboard Cite

show abstract

Interpretable Multimodal Sentiment Classification Using Deep Multi-View Attentive Network of Image and Text Data

Al-Tameemi,

Feizi-Derakhshi,

Pashazadeh

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Multimodal data can convey user emotions and feelings more effectively and interactively than unimodal content. Thus, multimodal sentiment analysis (MSA) research has recently acquired great significance as a field of study. However, most current approaches either acquire sentimental features independently for each modality or simply combine multiple modal features. Thus, semantic details pertinent to sentiment analysis and the relationship between visual and textual content have been neglected. Furthermore, most available multimodal datasets are sentiment-annotated, although user emotions are usually rich and unlimited. Motivated by these observations, this paper proposes a novel deep multi-view attentive network (DMVAN) for robust multimodal sentiment and emotion classification. The DMVAN model has three phases: feature learning, attentive interaction learning, and cross-modal fusion learning. During the feature learning phase, visual features from a multi-view perspective (region and scene) and textual features from various levels of analysis (word, sentence, and document) are extracted to capture information effectively for accurate classification. In the attentive interaction learning phase, we employed the image-text interaction learning mechanism to enhance visual and textual information interaction by extracting sentimental and discriminative visual features and utilizing the textual information to guide the learning process of image features. Moreover, a cross-modal fusion learning module has been developed to integrate the various features into a comprehensive framework that leverages the complementary nature of multiple modalities, followed by a multi-head attention mechanism that is intended to extract sufficient information from the intermediate features, thereby enabling the creation of a robust joint representation. Finally, a multi-layer perceptron with multiple stacking-fully connected layers is used to deeply fuse the modal features, thereby enhancing sentiment classification performance. An interpretable multimodal sentiment classification model is further developed utilizing the local interpretable model-agnostic explanation model (LIME) to ensure the model's explainability and strength. To perform a multimodal emotion classification, an image-text emotion dataset named emotion-Getty (EMO-G) was constructed from Getty Images and labeled by distinct emotions. The proposed model was tested on three real-world datasets, attaining 99.801% accuracy on binary_Getty (BG), 96.867% on Twitter, and 96.174% on the EMO-G dataset. These results show that the suggested model outperforms single-model techniques and current stateof-the-art methodologies based on model evaluation criteria. INDEX TERMS Multimodal sentiment analysis, attention mechanism, deep learning, deep multi-view attentive network, interpretability

show abstract

Enhancing Multimodal Tourism Review Sentiment Analysis Through Advanced Feature Association Techniques

Chen,

2024

International Journal of Information Systems in the Service Sector

View full text Add to dashboard Cite

The development of tourism services presents significant opportunities for extracting and analyzing customer sentiment. However, with the advent of multimodality, travel reviews have brought new challenges. Early methods for detecting such reviews merely combined text and image features, resulting in poor feature correlation. To address this issue, our study proposes a novel multimodal tourism review sentiment analysis method enhanced by relevant features. Initially, we employ a fusion model that combines BERT and Text-CNN for text feature extraction. This approach strengthens semantic relationships and filters noise effectively. Subsequently, we utilize ResNet-51 for image feature extraction, leveraging its ability to learn complex visual representations. Additionally, integrating an attention mechanism further enhances modality correlation, thereby improving fusion effectiveness. On the Multi-ZOL dataset, our method achieves an accuracy of 90.7% and an F1 score of 90.8%. Similarly, on the Ctrip dataset, it attains an accuracy of 83.6% and an F1 score of 84.1%.

show abstract

A study on the epidemiology of COVID-19 in the Banias and Alkadmos areas of Syria during 2021.

Cited by 3 publications

References 40 publications

Textual-Visual multimodal sentiment analysis: A Review of Approaches and Challenges

Textual-Visual multimodal sentiment analysis: A Review of Approaches and Challenges

Interpretable Multimodal Sentiment Classification Using Deep Multi-View Attentive Network of Image and Text Data

Enhancing Multimodal Tourism Review Sentiment Analysis Through Advanced Feature Association Techniques

Contact Info

Product

Resources

About