MMLTC: A novel Tolerance-Based Clustering Framework for Multimodal Sentiment and Harmful Meme Classification in Multilingual Settings
Bibliographic record
Abstract
This thesis 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".