arbiter
JournalsPricingAccount

Multimodal Sentiment and Emotional Analysis in Short Video Dissemination

Rong He

International Journal of Information Systems in the Service Sector2025https://doi.org/10.4018/ijisss.396225article
AJG 1
Weight
0.50

What the paper says

Short videos dominate online content, yet sentiment's role in virality is understudied. This research proposes a multimodal framework integrating visual, textual, and interactional data from 127,843 anonymized videos. It extracts emotional features—visual (color saturation, brightness), textual sentiment (FinBERT, -1 to 1), and interactional feedback—using deep learning for fusion and structural equation modeling for causal analysis. Results show positive text sentiment with high brightness boosts shares by 18%; dwell time mediates emotional resonance and sharing. Emotional drivers vary by content: entertainment relies on visual stimuli, education on positive text sentiment, news on comment signals. The multimodal model achieves 89.7% accuracy in predicting dissemination, outperforming unimodal models by 9–13%. Findings enhance service information systems by optimizing recommendations, user experience, and public opinion management, offering actionable insights for aligning content with user emotions to improve engagement sustainability.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.4018/ijisss.396225

Or copy a formatted citation

@article{rong2025,
  title        = {{Multimodal Sentiment and Emotional Analysis in Short Video Dissemination}},
  author       = {Rong He},
  journal      = {International Journal of Information Systems in the Service Sector},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.4018/ijisss.396225},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Multimodal Sentiment and Emotional Analysis in Short Video Dissemination

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.