A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity
Abstract In recent years, advancements in deep learning and real-time data processing have significantly enhanced traffic management and accident prediction capabilities. Building on these developments, this study introduces an innovative approach ConvoseqNet to improve traffic accident prediction b...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-91484-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343946858168320 |
|---|---|
| author | Areeba Naseem Khan Yaser Ali Shah Wasiat Khan Amaad Khalil Jebran Khan |
| author_facet | Areeba Naseem Khan Yaser Ali Shah Wasiat Khan Amaad Khalil Jebran Khan |
| author_sort | Areeba Naseem Khan |
| collection | DOAJ |
| description | Abstract In recent years, advancements in deep learning and real-time data processing have significantly enhanced traffic management and accident prediction capabilities. Building on these developments, this study introduces an innovative approach ConvoseqNet to improve traffic accident prediction by integrating traditional traffic data with real-time social media insights, specifically using geographic data and Twitter sentiment analysis. ConvoseqNet combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks in a sequential architecture, enabling it to effectively capture complex spatiotemporal patterns in traffic data. To further enhance prediction accuracy, a meta-model called MetaFusionNetwork is proposed, which combines predictions from ConvoseqNet and a Random Forest Classifier. Results show that ConvoseqNet alone achieved the highest predictive accuracy, demonstrating its capacity to capture diverse accident-related patterns. Additionally, MetaFusionNetwork’s performance highlights the advantages of combining model outputs for better prediction. This research contributes to real-time data-driven traffic management by leveraging innovative data fusion techniques, improving prediction accuracy, and providing insights into model interpretability and computational efficiency. By addressing the challenges of integrating heterogeneous data sources, this approach presents a significant advancement in traffic accident prediction and safety enhancement. |
| format | Article |
| id | doaj-art-bf9ef690e0574fa19286c4e439151b43 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-bf9ef690e0574fa19286c4e439151b432025-08-20T03:42:48ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-91484-0A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severityAreeba Naseem Khan0Yaser Ali Shah1Wasiat Khan2Amaad Khalil3Jebran Khan4Department of Computer Science, COMSATS University Islamabad, Attock CampusDepartment of Computer Science, COMSATS University Islamabad, Attock CampusDepartment of Software Engineering, University of Science and TechnologyDepartment of Computer Systems Engineering, University of Engineering and TechnologyDepartment of Artificial Intelligence, Ajou UniversityAbstract In recent years, advancements in deep learning and real-time data processing have significantly enhanced traffic management and accident prediction capabilities. Building on these developments, this study introduces an innovative approach ConvoseqNet to improve traffic accident prediction by integrating traditional traffic data with real-time social media insights, specifically using geographic data and Twitter sentiment analysis. ConvoseqNet combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks in a sequential architecture, enabling it to effectively capture complex spatiotemporal patterns in traffic data. To further enhance prediction accuracy, a meta-model called MetaFusionNetwork is proposed, which combines predictions from ConvoseqNet and a Random Forest Classifier. Results show that ConvoseqNet alone achieved the highest predictive accuracy, demonstrating its capacity to capture diverse accident-related patterns. Additionally, MetaFusionNetwork’s performance highlights the advantages of combining model outputs for better prediction. This research contributes to real-time data-driven traffic management by leveraging innovative data fusion techniques, improving prediction accuracy, and providing insights into model interpretability and computational efficiency. By addressing the challenges of integrating heterogeneous data sources, this approach presents a significant advancement in traffic accident prediction and safety enhancement.https://doi.org/10.1038/s41598-025-91484-0 |
| spellingShingle | Areeba Naseem Khan Yaser Ali Shah Wasiat Khan Amaad Khalil Jebran Khan A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity Scientific Reports |
| title | A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| title_full | A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| title_fullStr | A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| title_full_unstemmed | A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| title_short | A meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| title_sort | meta fusion model combining geographic data and twitter sentiment analysis for predicting accident severity |
| url | https://doi.org/10.1038/s41598-025-91484-0 |
| work_keys_str_mv | AT areebanaseemkhan ametafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT yaseralishah ametafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT wasiatkhan ametafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT amaadkhalil ametafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT jebrankhan ametafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT areebanaseemkhan metafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT yaseralishah metafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT wasiatkhan metafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT amaadkhalil metafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity AT jebrankhan metafusionmodelcombininggeographicdataandtwittersentimentanalysisforpredictingaccidentseverity |