Metraipolis › archive › dc_85b0f7257ffd

Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis — arXiv:2608.16201

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16201
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:29.138Z
SHA-256 of the archived text
1854e0ca9525e5d73547d9272a68cc762ba24f676d242024adcb3f59f9d5867a
Stable URL of this page
https://metraipolis.com/documento/dc_85b0f7257ffd

How to cite

Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis — arXiv:2608.16201 — arXiv (en), https://arxiv.org/abs/2608.16201 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85b0f7257ffd (Metraipolis archive dc_85b0f7257ffd, sha256 1854e0ca9525e5d73547d9272a68cc762ba24f676d242024adcb3f59f9d5867a)
BibTeX
@misc{dc85b0f7257ffd,
  title = {Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis — arXiv:2608.16201},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16201},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85b0f7257ffd; sha256 1854e0ca9525e5d73547d9272a68cc762ba24f676d242024adcb3f59f9d5867a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16201. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal sentiment analysis (MSA) aims to predict sentiment polarity and intensity from heterogeneous inputs such as text, audio, and vision. While large language models (LLMs) offer strong semantic priors for MSA, effectively incorporating audio and visual signals effectively remains challenging. A key challenge is that audio and visual sentiment cues evolve over different temporal scales, yet many LLM-based methods compress these signals through shallow projection or coarse pooling before fusing them with text, which can weaken cross-modal alignment and erase fine-grained affective information. We propose MGSI, a multi-granularity sentiment integration framework for LLM-based MSA. MGSI first encodes audio and visual streams at short-, medium-, and long-range temporal scales, preserving both local variations and global affective trends. It then refines non-text features through text-guided alignment, and applies polarity- and intensity-aware enhancement to better handle ambiguous and near-neutral samples. The resulting multimodal representation is finally compressed into a small set of pseudo-tokens for efficient conditioning of a frozen LLM. Experiments on four public benchmarks show that MGSI substantially outperforms frozen-LLM baselines and remains competitive with strong multimodal methods. Further ablation and sensitivity analyses support the effectiveness of multi-granularity temporal modeling, text-guided refinement, and adaptive sentiment calibration.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16201 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T19:02:44.154Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).