Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Framework of the proposed E-GAT + Bi-LSTM pipeline.

1) Feature extraction from text/audio/vision/biomedical signals; 2) E-GAT module: Constructs a semantic graph where nodes represent emotional modalities and edges represent modality interactions; 3) Bi-LSTM module: Captures bidirectional temporal dynamics; 4) Fully-connected layer + softmax: Outputs emotion class probabilities.

More »

Fig 1 Expand

Fig 2.

Overarching structure of the proposed graph model (E-GAT).

Interpretability details: 1) Nodes: Represent emotional states (text, audio), with attributes encoding feature vectors (red dashed lines link nodes to feature vectors); 2) Edges: Blue solid lines represent dynamic relationships between emotional states; 3) Weights: Edge weights indicate relationship strength—higher weights mean stronger correlation; 4) Temporal Adaptability: Black dashed lines denote feedback loops, illustrating that emotional states evolve over time.

More »

Fig 2 Expand

Fig 3.

The architecture of the introduced Bi-LSTM model.

This component consists of LSTM models, fully-connected layer, and softmax layer.

More »

Fig 3 Expand

Table 1.

The outcome of the proposed model on SemEval-2018 dataset (%).

More »

Table 1 Expand

Table 2.

Performance on SemEval-2018 with statistical validation. 95% CI is calculated via 10-fold cross-validation to reflect result variability.

More »

Table 2 Expand

Fig 4.

Confusion matrix of the proposed model on SemEval-2018.

Interpretability and decision process insights: 1) Color intensity corresponds to the number of samples (darker shades = more samples); 2) Diagonal elements: Correct classifications; 3) Off-diagonal elements: Misclassifications; 4) Overall balance: for all categories confirm the model’s ability to distinguish nuanced emotions, with confusion patterns ‌‌aligning with human emotional perception.

More »

Fig 4 Expand

Table 3.

Performance of the competing methos on the RAVDESS dataset with statistical validation.

More »

Table 3 Expand

Table 4.

Performance of the proposed approach on realistic scenario datasets (RAVDESS with noisy data).

More »

Table 4 Expand

Table 5.

Performance of the competing method on the CMU-MOSEI datast with statistical validation.

More »

Table 5 Expand

Table 6.

Performance of semi-supervised vs. supervised learning on SemEval-2018.

More »

Table 6 Expand

Table 7.

Macro-averaged AUC-ROC scores of the competing methods on three datasets.

More »

Table 7 Expand

Table 8.

Ablation experiment results (%).

More »

Table 8 Expand

Table 9.

Real-World Robustness Evaluation Results (%).

More »

Table 9 Expand