Towards Sentic-Aware Multimodal Models for Cyberbullying Detection in Thai Memes
| dc.contributor.author | Weradechtaweewon, Nattawat | |
| dc.contributor.author | Boondamnoen, Mongkol | |
| dc.contributor.author | Pasupa, Kitsuchart | |
| dc.date.accessioned | 2026-08-06T10:54:19Z | |
| dc.date.available | 2026-08-06T10:54:19Z | |
| dc.date.issued | 2026-01-01 | |
| dc.description.abstract | Cyberbullying has become an increasingly urgent issue in online communities. Memes, a popular form of online expression, often blend text and imagery in emotionally charged, sarcastic, or offensive ways–posing unique challenges for automatic harmful content detection. This work explores sentic-aware multimodal models for cyberbullying detection in Thai memes, with a focus on integrating affective commonsense knowledge through SenticNet-based features that emphasize conceptual reasoning and structured emotion representation. To enable this, we propose ThaiSenticNet 7, a resource adapted for the Thai language by translating from SenticNet 7, which supports the generation of sentic features. We investigate three representations–sentic vectors, sentic spectrograms, and sentic mel-spectrograms–and their integration with various sequential models to form sentic embeddings. These embeddings are fused with textual and visual information, extracted via a fine-tuned WangchanBERTa and a Swin Transformer, respectively, forming a unified multimodal pipeline. Experiments on a curated Thai meme dataset show that incorporating sentic features significantly enhances classification performance, with the best configuration–combining all three modalities–achieving an F<inf>1</inf>-score of 0.8044. Notably, the mel-spectrogram transformation proves particularly effective, suggesting that frequency-domain encoding helps capture subtle affective transitions in text-derived emotional signals. Our findings highlight the value of affective knowledge and multimodal modeling in tackling harmful content in memes. | |
| dc.identifier.citation | Lecture Notes in Computer Science, 16309 LNCS, 228-242, 2026 | |
| dc.identifier.doi | 10.1007/978-981-95-4367-0_16 | |
| dc.identifier.issn | 03029743 | |
| dc.identifier.other | 2-s2.0-105023590152 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/17789 | |
| dc.source | Lecture Notes in Computer Science | |
| dc.subject | Cyberbully Detection | |
| dc.subject | Meme | |
| dc.subject | Multimodal | |
| dc.subject | SenticNet | |
| dc.title | Towards Sentic-Aware Multimodal Models for Cyberbullying Detection in Thai Memes | |
| dc.type | Conference Paper |