Table 1.
Example of different sentiments from the citation sentiment corpus.
Table 2.
Hyperparameter details of all machine learning models.
Table 3.
Strength and weakness of feature representation technique.
Fig 1.
Proposed architectural diagram.
Fig 2.
Architecture of the proposed voting classifier (LR+SGD) model.
Table 4.
Classification result of classifiers models using TF without SMOTE.
Table 5.
Classification result classifiers using TF with SMOTE.
Table 6.
Classification result of classifiers using TF-IDF without SMOTE.
Table 7.
Classification result classifiers using TF-IDF with SMOTE.
Table 8.
Classification results of machine learning models using CNN features with.
Table 9.
Significance of proposed methodology using k-fold validation.
Fig 3.
Accuracy comparison of classifiers.
Table 10.
Training testing accuracy result of TF and TF-IDF features with SMOTE.
Table 11.
Classification results of classifiers using fastText.