基于社交媒体数据的知识增强多任务学习交通事件检测模型

周正; 汪玫; 杨林瑶; 李莉芳; 王晓

doi:10.11959/j.issn.2096-6652.202541

您当前的位置：

首页 >

文章列表页 >

基于社交媒体数据的知识增强多任务学习交通事件检测模型

专题：社会计算与韧性社会 | 更新时间：2026-03-18

- 基于社交媒体数据的知识增强多任务学习交通事件检测模型
- Knowledge-enhanced multi-task learning traffic incident detection model based on social media data
- 智能科学与技术学报 2025年7卷第4期页码：493-504
- 作者机构：
  
  1.安徽大学人工智能学院，安徽合肥 230031
  2.之江实验室，浙江杭州 311121
  3.中山大学新闻传播学院，广东广州 510006
  4.光电信息获取与防护技术全国重点实验室，安徽合肥 230031
- 作者简介：
  
  [ "周正（2000- ），男，安徽大学人工智能学院硕士生，主要研究方向为智能交通系统、自然语言处理、深度学习。" ]
  [ "汪玫（2005- ），女，安徽大学人工智能学院本科生，主要研究方向为交通事件预测、机器学习。" ]
  [ "杨林瑶（1995- ），男，之江实验室副研究员，主要研究方向为知识图谱、知识增强大模型等。" ]
  [ "李莉芳（1989- ），女，中山大学新闻传播学院副教授，主要研究方向为应急信息传播、应急管理、谣言治理。" ]
  [ "王晓（1988- ），女，安徽大学人工智能学院教授，主要研究方向为社会计算、群体行为建模、无人自主系统及其平行测试。" ]
- 基金信息：
  
  国家自然科学基金项目(62173329)
- DOI：10.11959/j.issn.2096-6652.202541
  中图分类号： TP39
- 收稿：2025-09-18，
  
  修回：2025-11-25，
  
  录用：2025-11-26，
  
  纸质出版：2025-12-15
- 稿件说明：
移动端阅览
周正,汪玫,杨林瑶等.基于社交媒体数据的知识增强多任务学习交通事件检测模型[J].智能科学与技术学报,2025,07(04):493-504.

ZHOU Zheng,WANG Mei,YANG Linyao,et al.Knowledge-enhanced multi-task learning traffic incident detection model based on social media data[J].Chinese Journal of Intelligent Science and Technology,2025,07(04):493-504.
周正,汪玫,杨林瑶等.基于社交媒体数据的知识增强多任务学习交通事件检测模型[J].智能科学与技术学报,2025,07(04):493-504. DOI： 10.11959/j.issn.2096-6652.202541.

ZHOU Zheng,WANG Mei,YANG Linyao,et al.Knowledge-enhanced multi-task learning traffic incident detection model based on social media data[J].Chinese Journal of Intelligent Science and Technology,2025,07(04):493-504. DOI： 10.11959/j.issn.2096-6652.202541.

摘要

交通事件检测是智能交通系统（ITS）的核心环节，现有方法在处理社交媒体非结构化文本、关联地理信息及协同多任务学习方面存在局限。为此，提出融合地理知识增强与多任务学习的交通事件检测（GeoKE-MTL）模型，以提升事件检测的准确性与鲁棒性，该模型主要由知识增强模块和多任务学习模块两个部分组成。实验结果表明，在自建的社交媒体文本数据集上，GeoKE-MTL在事发地点识别任务和交通事件识别任务中的F1分数分别达到79.42%和79.75%，在事发地点识别任务中均优于主流基线模型。研究验证了融合地理知识增强与多任务学习对提升检测性能的有效性，为智能交通系统的实时事件感知提供了新方案。

Abstract

Traffic incident detection is a core component of intelligent transportation systems (ITS)

but existing methods are limited in processing unstructured social media text

associated geographic information

and collaborative multi-task learning. To address this

a traffic incident detection model based on integrated geographical knowledge enhancement and multi-task learning (GeoKE-MTL) was proposed to improve the accuracy and robustness of incident detection. The model consists of two main components: a knowledge enhancement module and a multi-task learning module. Experimental results show that on a self-built social media text dataset

GeoKE-MTL achieves F1 scores of 79.42% and 79.75% in incident location identification and traffic event identification tasks

respectively

outperforming mainstream baseline models in the incident location identification task. This study validates the effectiveness of integrating geographic knowledge enhancement with multi-task learning in improving detection performance

providing a new solution for real-time event perception in intelligent transportation systems.

关键词

Keywords

references

Global status report on road safety 2023[R]. 2023.

SUAT-ROJAS N, GUTIERREZ-OSORIO C, PEDRAZA C. Extraction and analysis of social networks data to detect traffic accidents[J]. Information, 2022, 13(1): 26.

陈苑文, 王晓, 李灵犀, 等. 基于社会媒体数据增强的交通态势感知研究及进展[J]. 智能科学与技术学报, 2022, 4(1): 1-13.

CHEN Y W, WANG X, LI L X, et al. Traffic situational awareness research and development enhanced by social media data: the state of the art and prospects[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(1): 1-13.

WU Y L, CHEN Y J, ZHANG R Y, et al. A spatial information extraction method based on multi-modal social media data: a case study on urban inundation[J]. ISPRS International Journal of Geo-Information, 2023, 12(9): 368.

ZHU R X, LIN D, JENDRYKE M, et al. Geo-tagged social media data-based analytical approach for perceiving impacts of social events[J]. ISPRS International Journal of Geo-Information, 2019, 8(1): 15.

DU Q C, XU L L, WU Q, et al. SafeCrossNet: multi-modal fusion with social-aware for pedestrian crossing intention prediction[J]. Information Fusion, 2026, 126: 103609.

ALI F, ALI A, IMRAN M, et al. Traffic accident detection and condition analysis based on social networking data[J]. Accident Analysis & Prevention, 2021, 151: 105973.

CHANG H L, LI L S, HUANG J X, et al. Tracking traffic congestion and accidents using social media data: a case study of Shanghai[J]. Accident Analysis & Prevention, 2022, 169: 106618.

WANG D, AL-RUBAIE A, CLARKE S S, et al. Real-time traffic event detection from social media[J]. ACM Transactions on Internet Technology, 2018, 18(1): 1-23.

MELHEM W, ABDI A, MEZIANE F. Traffic detection and forecasting from social media data using a deep learning-based model, linguistic knowledge, large language models, and knowledge graphs[C]//Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management. Setcibal: SCITEPRESS - Science and Technology Publications, 2024: 235-242.

BOK K, KIM I, LIM J, et al. Efficient graph-based event detection scheme on social media[J]. Information Sciences, 2023, 646: 119415.

SALAS A, GEORGAKIS P, NWAGBOSO C, et al. Traffic event detection framework using social media[C]//Proceedings of the 2017 IEEE International Conference on Smart Grid and Smart Cities (ICSGSC). Piscataway: IEEE Press, 2017: 303-307.

KOLAJO T, DARAMOLA O, ADEBIYI A A. Real-time event detection in social media streams through semantic analysis of noisy terms[J]. Journal of Big Data, 2022, 9(1): 90.

ZHANG Z H, HE Q, GAO J, et al. A deep learning approach for detecting traffic accidents from social media data[J]. Transportation Research Part C: Emerging Technologies, 2018, 86: 580-596.

HODOROG A, PETRI I, REZGUI Y. Machine learning and natural language processing of social media data for event detection in smart cities[J]. Sustainable Cities and Society, 2022, 85: 104026.

JONNALAGADDA J, HASHEMI M. A deep learning-based traffic event detection from social media[C]//Proceedings of the 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI). Piscataway: IEEE Press, 2021: 1-8.

AFYOUNI I, KHAN A, AL AGHBARI Z. Deep-Eware: spatio-temporal social event detection using a hybrid learning model[J]. Journal of Big Data, 2022, 9(1): 86.

YANG X Y, BEKOULIS G, DELIGIANNIS N. Traffic event detection as a slot filling problem[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106202.

YANG L, WANG Y, PAN Z, et al. Multi-task feature selection based anomaly detection[J]. arXiv preprint, 2014, arXiv:1403.4017.

DENG D X, SHAHABI C, DEMIRYUREK U, et al. Situation aware multi-task learning for traffic prediction[C]//Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM). Piscataway: IEEE Press, 2017: 81-90.

CHEN Q, WANG W, HUANG K Z, et al. Multi-modal generative adversarial networks for traffic event detection in smart cities[J]. Expert Systems with Applications, 2021, 177: 114939.

LI J, LI J, GONG Y J. Multi-task learning for sparse traffic forecasting[J]. arXiv preprint, 2022, arXiv:2211.09984.

ZHANG H W, QIAN S S, FANG Q, et al. Multi-modal meta multi-task learning for social media rumor detection[J]. IEEE Transactions on Multimedia, 2021, 24: 1449-1459.

LIU Y Q, GAO Y F, ZHANG Q C, et al. Multi-task safe reinforcement learning for navigating intersections in dense traffic[J]. Journal of the Franklin Institute, 2023, 360(17): 13737-13760.

ZHUANG L, FEI H, HU P. Knowledge-enhanced event relation extraction via event ontology prompt[J ] . Information Fusion, 2023, 100: 101919.

HU F F, ZHANG S T, LIN X B, et al. Network traffic classification model based on attention mechanism and spatiotemporal features[J]. EURASIP Journal on Information Security, 2023, 2023(1): 6.

覃缘琪, 季青原, 葛俊, 等. 城市交通路网动态短时推理与精准预测研究[J]. 智能科学与技术学报, 2022, 4(3): 380-395.

QIN Y Q, JI Q Y, GE J, et al. Short-term traffic state reasoning and precise prediction in urban networks[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(3): 380-395.

ADNAN K, AKBAR R. An analytical study of information extraction from unstructured and multidimensional big data[J]. Journal of Big Data, 2019, 6(1): 91.

LIU L, YU Y J, WU Y F, et al. Method for multi-task learning fusion network traffic classification to address small sample labels[J]. Scientific Reports, 2024, 14: 2518.

王晓, 杨林瑶, 胡斌, 等. 平行推理: 一种基于ACP方法的虚实互动的知识协同框架[J]. 智能科学与技术学报, 2023, 5(1): 69-82.

WANG X, YANG L Y, HU B, et al. Parallel reasoning: a virtual-real interactive knowledge collaboration framework based on ACP approach[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(1): 69-82.

MREDULA M S, DEY N, RAHMAN M S, et al. A review on the trends in event detection by analyzing social media platforms' data[J]. Sensors, 2022, 22(12): 4531.

PUTRA P K, MAHENDRA R, BUDI I. Traffic and road conditions monitoring system using extracted information from Twitter[J]. Journal of Big Data, 2022, 9(1): 65.

李炎英, 王新宇, 王晓, 等. 基于大语言模型的交通异常事件检测与辅助决策[J]. 智能科学与技术学报, 2024, 6(3): 347-355.

LI Y Y, WANG X Y, WANG X, et al. Traffic anomaly event detection and auxiliary decision-making based on large language models[J]. Chinese Journal of Intelligent Science and Technology, 2024, 6(3): 347-355.

TANG W, ZHANG Y, MAO X, et al. Enhanced named entity recognition and event extraction for power grid outage scheduling using a universal information extraction framework[J]. Energies, 2025, 18(14): 3617.

LIU Y, DU J, GOYAL N, et al. Roberta: a robustly optimized bert pretraining approach[J]. arXiv preprint, 2019, arXiv:1907.11692.

LIU X, HE P, CHEN W, et al. Multi-task deep neural networks for natural language understanding[J]. arXiv preprint, 2019, arXiv:1901.11504.

SANH V, WOLF T, RUDER S. A hierarchical multi-task approach for learning embeddings from semantic tasks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 6949-6956.

DU Q C, WANG X, YIN S G, et al. Social force embedded mixed graph convolutional network for multi-class trajectory prediction[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(9): 5571-5580.

XU S S, LI S N, HUANG W, et al. Detecting spatiotemporal traffic events using geosocial media data[J]. Computers, Environment and Urban Systems, 2022, 94: 101797.

WANG X, HUANG J, TIAN Y L, et al. Parallel driving with big models and foundation intelligence in cyber-physical-social spaces[J]. Research, 2024, 7: 349.

杜泉成, 王晓, 李灵犀, 等. 行人轨迹预测方法关键问题研究: 现状及展望[J]. 智能科学与技术学报, 2023, 5(2): 143-162.

DU Q C, WANG X, LI L X, et al. Key problems and progress of pedestrian trajectory prediction methods: the state of the art and prospects[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(2): 143-162.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合K-BERT与KG-BART的测井文本生成方法研究

可编程道路交通控制系统：概念、体系架构与关键技术

元宇宙下的平行交通系统

基于社会媒体数据增强的交通态势感知研究及进展

Cerberus：基于深度学习的跨站社交网络机器人检测系统