Fig 1.
Steps of applied methodology.
Table 1.
Sample sentences from the dataset showing case categories.
Fig 2.
Most frequent words in dataset.
Fig 3.
Working of sentence transformer.
Fig 4.
Architecture of Applied LSTM Model with Sentence Embeddings, showing the process of legal text into semantic vectors using embeddings, processing the sequence with LSTM to capture contextual dependencies, and using a fully connected layer to classify cases.
Table 2.
Performance evaluation measures.
Table 3.
Experimental setup and hyperparameter configuration.
Table 4.
Machine learning results in percentage.
Fig 5.
Confusion matrix of SVC model.
Fig 6.
Confusion matrix of DT model.
Fig 7.
Confusion matrix of RF model.
Fig 8.
Confusion matrix of ETC model.
Fig 9.
Comparison of all applied ML models.
Table 5.
Results with deep model in percentage.
Fig 10.
Confusion matrix of LSTM model.
Fig 11.
Training graph of LSTM model.
Fig 12.
SHAP summary plot showing the impact of top textual features on the proposed model’s output.
Fig 13.
LIME explanation highlighting key words probabilities for classes.
Fig 14.
Combined LIME heatmap values illustrating feature contributions across all classes.
Table 6.
Comparison of ML models with the proposed model (%).
Table 7.
Comparison of proposed with existing studies’ results in %age accuracies.