ABSTRACT This work introduces a novel Tolerance‐Based Clustering Framework (MMLTC) framework for affective analytics of multimodal/multilingual content in social media. A key feature of the MMLTC framework is its ability to overcome limitations of prior tolerance‐based classifiers through the construction of label specific pure tolerance classes. Unlike traditional global partitioning methods, the proposed MMLTC employs a local, label aware grouping strategy that captures fine grained intra class variations while reducing the risk of label impurity. The proposed framework was tested on diverse multimodal datasets consisting of four English and three Bengali languages, using accuracy and weighted F1 metrics complemented by statistical significance testing via the Wilcoxon signed rank test and effect size analysis using Cohen's d measure. MMLTC demonstrates strong performance across the seven diverse benchmark datasets, each involving classification tasks such as sentiment analysis, hate speech detection, offensive language identification, and multilingual content categorization. MMLTC outperforms state‐of‐the‐art deep neural classifiers in six out of seven datasets with the weighted F1 score. Additionally, MMLTC consistently achieves performance that is either superior to or on par with five baseline classifiers: Random Forest, Support Vector Machines, Logistic Regression, K‐Nearest Neighbors, and XGBoost. To assess the tolerance class clustering ability of MMLTC, t‐SNE interpretability technique was applied. The Source code for MMLTC Classifier is available at: https://github.com/jaherchowdhury/MMLTC‐A‐novel‐Tolerance‐Based‐Clustering‐Framework .
Chowdhury et al. (Mon,) studied this question.