[HTML][HTML] CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts

R Lamsal, MR Read, S Karunasekera - Knowledge-Based Systems, 2024 - Elsevier
Social media platforms play an essential role in crisis communication, but analysing crisis-
related social media texts is challenging due to their informal nature. Transformer-based pre …

AI-driven social media text analysis during crisis: A review for natural disasters and pandemics

JA Wahid, M Xu, M Ayoub, X Jiang, S Lei, Y Gao… - Applied Soft …, 2025 - Elsevier
During crises such as disasters and pandemics, people share diverse data on social media,
providing actionable information crucial for real-time crisis response. Such valuable …

[HTML][HTML] Leveraging sensory knowledge into Text-to-Text Transfer Transformer for enhanced emotion analysis

Q Zhao, Y **a, Y Long, G Xu, J Wang - Information Processing & …, 2025 - Elsevier
This study proposes an innovative model (ie, SensoryT5), which integrates sensory
knowledge into the T5 (Text-to-Text Transfer Transformer) framework for emotion …

[HTML][HTML] An Enhanced IDBO-CNN-BiLSTM Model for Sentiment Analysis of Natural Disaster Tweets

G Mu, J Li, X Li, C Chen, X Ju, J Dai - Biomimetics, 2024 - mdpi.com
The Internet's development has prompted social media to become an essential channel for
disseminating disaster-related information. Increasing the accuracy of emotional polarity …

Deltran15: A deep lightweight transformer-based framework for multiclass classification of disaster posts on x

S Saleem, N Hasan, A Khattar, PR Jain, TK Gupta… - IEEE …, 2024 - ieeexplore.ieee.org
During disasters, timely and accurate information is paramount for effective decision-making
and resource allocation. Social media (SM) platforms, particularly X platform (formerly …

[HTML][HTML] An integrated approach to Bayesian weight regulations and multitasking learning methods for generating emotion-based content in the metaverse

WH Park, DR Shin, H Mutahira - Expert Systems with Applications, 2025 - Elsevier
This paper introduces an integrated model designed to analyze topics and sentiments in
textual data simultaneously, recognizing their interdependence. By tackling challenges such …

Upper bound on the predictability of rating prediction in recommender systems

E Xu, K Zhao, Z Yu, H Wang, S Ren, H Cui… - Information Processing …, 2025 - Elsevier
The task of rating prediction has undergone extensive scrutiny, employing diverse modeling
approaches to enhance accuracy. However, it remains uncertain whether a maximum …

Panic emotional contagion in emergencies: The role of safety and hazard information diffusion

Z Tian, G Zhang, X Hong, D Lu - International Journal of Disaster Risk …, 2025 - Elsevier
In the event of a public safety incident, information diffusion plays a crucial role in the crowd
evacuation process. The diffusion of safety information inhibits the spread of panic and aids …

[HTML][HTML] MSBKA: A Multi-Strategy Improved Black-Winged Kite Algorithm for Feature Selection of Natural Disaster Tweets Classification

G Mu, J Li, Z Liu, J Dai, J Qu, X Li - Biomimetics, 2025 - mdpi.com
With the advancement of the Internet, social media platforms have gradually become
powerful in spreading crisis-related content. Identifying informative tweets associated with …