What question did this study set out to answer?

This research aims to analyze emotional reactions on Turkish social media following the February 2023 earthquake.

July 4, 2026ElectronicsOpen Access

Analyzing Post-Disaster Public Reactions in Turkish Social Media Through Topic Modeling and Hybrid Sentiment Classification

View Full Paper

Ask AI

Bookmark

Authors

AMAyşe Meydanoğlu SASerpil Aslan EDEmirhan Denizyol

Discussion

Member takes

Overview

Randomized trial analyzes emotional responses in Turkish social media, revealing significant sentiment patterns post-disaster, indicating varying public concerns.

Key Points

This research aims to analyze emotional reactions on Turkish social media following the February 2023 earthquake.
Data collected from 305,000 tweets on the X platform between February 10-28, 2023.
Employed Latent Dirichlet Allocation for topic modeling and a hybrid deep learning model for sentiment classification.
Achieved a classification accuracy of 94% using BERT, CNN, and BiLSTM.
Identified prevalent positive sentiments related to support and resilience, with 96% precision in sentiment classification.
Negative sentiments were primarily linked to aid delays and institutional shortcomings.
Framework provides insights for monitoring disaster response and public sentiment in real-time.

Cite This Study

Meydanoğlu et al. (2026) studied this question.

synapsesocial.com/papers/6a48a57289561a0c2d78e2ca https://doi.org/10.3390/electronics15132911

View Full Paper

Ask AI

Bookmark

July 4, 2026ElectronicsOpen Access

Analyzing Post-Disaster Public Reactions in Turkish Social Media Through Topic Modeling and Hybrid Sentiment Classification

View Full Paper

Ask AI

Bookmark

Authors

AMAyşe Meydanoğlu SASerpil Aslan EDEmirhan Denizyol

Discussion

Member takes

Overview

Randomized trial analyzes emotional responses in Turkish social media, revealing significant sentiment patterns post-disaster, indicating varying public concerns.

Key Points

This research aims to analyze emotional reactions on Turkish social media following the February 2023 earthquake.
Data collected from 305,000 tweets on the X platform between February 10-28, 2023.
Employed Latent Dirichlet Allocation for topic modeling and a hybrid deep learning model for sentiment classification.
Achieved a classification accuracy of 94% using BERT, CNN, and BiLSTM.
Identified prevalent positive sentiments related to support and resilience, with 96% precision in sentiment classification.
Negative sentiments were primarily linked to aid delays and institutional shortcomings.
Framework provides insights for monitoring disaster response and public sentiment in real-time.

Cite This Study

Meydanoğlu et al. (2026) studied this question.

synapsesocial.com/papers/6a48a57289561a0c2d78e2ca https://doi.org/10.3390/electronics15132911

Also Consider

Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark