Table 1.
Lists of abbreviations and definitions.
Table 2.
Summary of the related works on feature engineering aspect for sarcasm detection.
Table 3.
The summary of dataset description.
Fig 1.
Multi-feature fusion framework for sarcasm identification.
Fig 2.
The flowchart of the proposed methodology.
Table 4.
The summary of proposed features for sarcasm identification.
Table 5.
Lists of the experimental environment.
Table 6.
Parameter optimization and tuning values of classifiers.
Table 7.
Confusion matrix.
Fig 3.
Performance results of different classification algorithms on the lexical feature only.
Table 8.
Performance results obtained by considering lexical feature only.
Fig 4.
Performance results of different classification algorithms on the fused features.
Table 9.
Performance results obtained by considering fused features.
Table 10.
Performance results attained on fused features using Pearson correlation.
Table 11.
Performance results attained on fused features using information gain.
Fig 5.
Results comparison of our proposed framework with the baseline approaches.
Table 12.
Comparison of the proposed framework with baselines.