计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (8): 268-276.doi: 10.11896/jsjkx.240600146

• 人工智能 • 上一篇    下一篇

基于持续事件知识网络的持续社会事件分类研究

张袁1, 张胜杰1, 刘利龙1, 钱胜胜2   

  1. 1 郑州大学河南先进技术研究院 郑州 450000
    2 中国科学院自动化研究所多模态人工智能系统全国重点实验室 北京 100190
  • 收稿日期:2024-06-24 修回日期:2024-10-16 出版日期:2025-08-15 发布日期:2025-08-08
  • 通讯作者: 钱胜胜(shengsheng.qian@nlpr.ia.ac.cn)
  • 作者简介:(1584462772@qq.com)
  • 基金资助:
    国家重点研发计划(2023YFC3310700);国家自然科学基金(62276257)

Research on Continual Social Event Classification Based on Continual Event Knowledge Network

ZHANG Yuan1, ZHANG Shengjie1, LIU Lilong1, QIAN Shengsheng2   

  1. 1 Henan Institute of Advanced Technology,Zhengzhou University,Zhengzhou 450000,China
    2 State Key Laboratory of Multimodal Artificial Intelligence Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China
  • Received:2024-06-24 Revised:2024-10-16 Online:2025-08-15 Published:2025-08-08
  • About author:ZHANG Yuan,born in 2001, postgra-duate.His main research interests include natural language processing and continual learning.
    QIAN Shengsheng,born in 1991,Ph.D,professor.His main research interests include data mining and multimedia content analysis.
  • Supported by:
    National Key Research and Development Program of China(2023YFC3310700) and National Natural Science Foundation of China(62276257).

PDF (PC)

17

摘要： 随着互联网的快速发展和社交媒体规模的不断扩大,社会事件分类(Social Event Classification,SEC)越来越受到人们的关注。现有的社会事件分类研究侧重于识别一组固定的社会事件。然而,在现实世界中,社交媒体上会不断出现新的社会事件,这就需要一种实用的SEC模型能够迅速适应社会事件不断发展的环境。因此,研究了一个新的关键问题,即持续社会事件分类(C-SEC),在持续收集的社会数据中会不断出现新事件;提出了一种新颖的持续事件知识网络(Continual Event Knowledge Network,CEKNet),用于持续学习持续事件知识,以实现具有持续增量事件的C-SEC分类。所提出的持续学习框架由两个部分组成:当前事件知识学习和过去事件知识重放。首先,进行当前事件知识学习,学习当前输入数据中新出现事件的分类。其次,设计了具有知识自蒸馏功能的过去事件知识重放,以巩固所学到的过去事件知识,防止灾难性遗忘。在真实世界的社会事件数据集上进行的综合实验表明,与先进的方法相比,为C-SEC而提出的CEKNet更具优势。

关键词: 社会事件分类, 类递增持续学习, 持续事件知识

Abstract: With the rapid development of the Internet and the burgeoning scale of social media,social event classification(SEC) has garnered increasing attention.The existing study of SEC focuses on recognizing a fixed set of social events.However,in real-world scenarios,new social events continually emerge on social media,which suggests the necessity for a practical SEC model that can swiftly adapt to the evolving environment with incremental social events.Therefore,this paper studies a new yet crucial pro-blem defined as continual social event classification(C-SEC),where new events continually emerge in the sequentially collected social data.Accordingly,this paper proposes a novel continual event knowledge network(CEKNet) to continually learn continual event knowledge for C-SEC with continually incremental events.The proposed continual learning framework consists of two components:present event knowledge learning and past event knowledge replay.Firstly,it conducts present event knowledge learning to learn the classification of newly emerging events in the presently incoming data.Secondly,it designs past event knowledge replay with self-knowledge distillation to consolidate the learned knowledge of past events and prevent catastrophic forgetting.Comprehensive experiments on real-world social event datasets demonstrate the superiority of the proposed CEKNet for C-SEC compared with state-of-the-art methods.

Key words: Social event classification, Class-incremental continual learning, Continual event knowledge

中图分类号: 

  • TP391
[1]AFYOUNI I,AL AGHBARI Z,RAZACK R A.Multi-feature,multi-modal,and multi-source social event detection:A comprehensive survey[J].Information Fusion,2022,79:279-308.
[2]QIAN S,CHEN H,XUE D,et al.Open-world social event classification[C]//Proceedings of the ACM Web Conference 2023.2023:1562-1571.
[3]ZHOU H,YIN H,ZHENG H,et al.A survey on multi-modal social event detection[J].Knowledge-Based Systems,2020,195:105695.
[4]CHANDRASEKARAN G,NGUYEN T N,HEMANTH D J.Multimodal sentimental analysis for social media applications:A comprehensive review[J].Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery,2021,11(5):e1415.
[5]CHEN M,CHEN S C,SHYU M L,et al.Semantic event detection via multimodal data mining[J].IEEE Signal Processing Magazine,2006,23(2):38-46.
[6]HAN X,WANG J,ZHANG M,et al.Using social media to mine and analyze public opinion related to COVID-19 in China[J].International Journal of Environmental Research and Public Health,2020,17(8):2788.
[7]XIA H,AN W,LI J,et al.Outlier knowledge management for extreme public health events:Understanding public opinions about COVID-19 based on microblog data[J].Socio-Economic Planning Sciences,2022,80:100941.
[8]JIN Y,LIU B F,AUSTIN L L.Examining the role of social media in effective crisis management:The effects of crisis origin,information form,and source on publics' crisis responses[J].Communication Research,2014,41(1):74-94.
[9]ZADE H,SHAH K,RANGARAJAN V,et al.From situational awareness to actionability:Towards improving the utility of social media data for crisis response[J].Proceedings of the ACM on Human-Computer Interaction,2018,2(CSCW):1-18.
[10]CACCIA L,ALJUNDI R,ASADI N,et al.New insights on reducing abrupt representation change in online continual learning[J].arXiv:2104.05025,2021.
[11]MACEDO A Q,MARINHO L B,SANTOS R L T.Context-aware event recommendation in event-based social networks[C]//Proceedings of the 9th ACM Conference on Recommender Systems.2015:123-130.
[12]ABAVISANI M,WU L,HU S,et al.Multimodal categorization of crisis events in social media[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:14679-14689.
[13]KIELA D,BHOOSHAN S,FIROOZ H,et al.Supervised multimodal bitransformers for classifying images and text[J].arXiv:1909.02950,2019.
[14]OFLI F,ALAM F,IMRAN M.Analysis of social media data using multimodal deep learning for disaster response[J].arXiv:2004.11838,2020.
[15]DE LANGE M,ALJUNDI R,MASANA M,et al.A continual learning survey:Defying forgetting in classification tasks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(7):3366-3385.
[16]LESORT T,LOMONACO V,STOIAN A,et al.Continuallearning for robotics:Definition,framework,learning strategies,opportunities and challenges[J].Information Fusion,2020,58:52-68.
[17]MAI Z,LI R,JEONG J,et al.Online continual learning in image classification:An empirical survey[J].Neurocomputing,2022,469:28-51.
[18]BHAT P,ZONOOZ B,ARANI E.Task-aware information routing from common representation space in lifelong learning[J].arXiv:2302.11346,2023.
[19]JIN X,LIN B Y,ROSTAMI M,et al.Learn continually,genera-lize rapidly:Lifelong knowledge accumulation for few-shot lear-ning[J].arXiv:2104.08808,2021.
[20]SARFRAZ F,ARANI E,ZONOOZ B.Error sensitivity modulation based experience replay:Mitigating abrupt representation drift in continual learning[J].arXiv:2302.11344,2023.
[21]ROBINS A.Catastrophic forgetting,rehearsal and pseudore-hearsal[J].Connection Science,1995,7(2):123-146.
[22]BOSCHINI M,BONICELLI L,BUZZEGA P,et al.Class-incremental continual learning into the extended der-verse[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(5):5497-5512.
[23]LIN H,ZHANG B,FENG S,et al.PCR:Proxy-based contrastive replay for online class-incremental continual learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:24246-24255.
[24]ZHOU D W,WANG Q W,YE H J,et al.A model or 603 exemplars:Towards memory-efficient class-incremental learning[J].arXiv:2205.13218,2022.
[25]ALAM F,OFLI F,IMRAN M.Crisismmd:Multimodal twitter datasets from natural disasters[C]//Proceedings of the International AAAI Conference on Web and Social Media.2018.
[26]KOCHKINA E,LIAKATA M,ZUBIAGA A.All-in-one:Multi-task learning for rumour verification[J].arXiv:1806.03713,2018.
[27]LEE K,PALSETIA D,NARAYANAN R,et al.Twitter trending topic classification[C]//2011 IEEE 11th International Conference on Data Mining Workshops.IEEE,2011:251-258.
[28]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems.2013.
[29]PARILLA-FERRER B E,FERNANDEZ P L,BALLENA J T.Automatic classification of disaster-related tweets[C]//International Conference on Innovative Engineering Technologies(ICIET).2014.
[30]SRIRAM B,FUHRY D,DEMIR E,et al.Short text classification in twitter to improve information filtering[C]//Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2010:841-842.
[31]QIAO Z,ZHANG P,ZHOU C,et al.Event recommendation in event-based social networks[C]//Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence.AAAI,2014:3130-3131.
[32]TANG J,TANG J,LIU H.Recommendation in social media:recent advances and new frontiers[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.2014.
[33]TSOU M H,YANG J A,LUSHER D,et al.Mapping social activities and concepts with social media(Twitter) and web search engines(Yahoo and Bing):a case study in 2012 US Presidential Election[J].Cartography and Geographic Information Science,2013,40(4):337-348.
[34]ALSAEDI N,BURNAP P,RANA O.Can we predict a riot?Disruptive event detection using Twitter[J].ACM Transactions on Internet Technology,2017,17(2):1-26.
[35]ZHANG W,QI G,PAN G,et al.City-scale social event detection and evaluation with taxi traces[J].ACM Transactions on Intelligent Systems and Technology,2015,6(3):1-20.
[36]KELLY S,ZHANG X,AHMAD K.Mining multimodal information on social media for increased situational awareness[C]//Proceedings of the 14th International Conference on Information Systems for Crisis Response and Management.2017.
[37]LI X,DOINA C.Improving disaster-related tweet classification with a multimodal approach[C]//Proceedings of the 17th International Conference on Information Systems for Crisis Response and Management.2020.
[38]MOUZANNAR H,RIZK Y,AWAD M.Damage Identification in Social Media Posts using Multimodal Deep Learning[C]//The 15th International Conference on Information Systems for Crisis Response and Management(ISCRAM).2018.
[39]NGUYEN T H,RUDRA K.Towards an interpretable approach to classify and summarize crisis events from microblogs[C]//Proceedings of the ACM Web Conference.2022:3641-3650.
[40]HADSELL R,RAO D,RUSU A A,et al.Embracing change:Continual learning in deep neural networks[J].Trends in Cognitive Sciences,2020,24(12):1028-1040.
[41]REBUFFI S A,KOLESNIKOV A,SPERL G,et al.ICARL:Incremental classifier and representation learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2001-2010.
[42]LOPEZ-PAZ D,RANZATO M A.Gradient episodic memory for continual learning[C]//Advances in Neural Information Processing Systems.2017.
[43]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding.[J].arXiv:1810.04805,2018.
[44]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[45]HOU S,PAN X,LOY C C,et al.Learning a unified classifier incrementally via rebalancing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:831-839.
[46]LI Z,HOIEM D.Learning without forgetting[J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2017,40(12):2935-2947.
[47]CACCIA L,ALJUNDI R,ASADI N,et al.New insights on reducing abrupt representation change in online continual learning[J].arXiv:2104.05025,2021.
[48]MITTAL S,GALESSO S,BROX T.Essentials for class incre-mental learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:3513-3522.
[49]VITTER J S.Random sampling with a reservoir[J].ACMTransactions on Mathematical Software,1985,11(1):37-57.
[50]KOCHKINA E,LIAKATA M,ZUBIAGA A.All-in-one:Multi-task learning for rumour verification[J].arXiv:1806.03713,2018.
[51]ZUBIAGA A,LIAKATA M,PROCTER R,et al.Analysinghow people orient to and spread rumours in social media by looking at conversational threads[J].PLoS One,2016,11(3):e0150989.
[52]ALAM F,OFLI F,IMRAN M.Crisismmd:Multimodal twitter datasets from natural disasters[C]//Proceedings of the International AAAI Conference on Web and Social Media.2018.
[53]BONICELLI L,BOSCHINI M,PORRELLO A,et al.On the effectiveness of lipschitz-driven rehearsal in continual learning[J].Advances in Neural Information Processing Systems,2022,35:31886-31901.
[54]ARANI E,SARFRAZ F,ZONOOZ B.Learning fast,learningslow:A general continual learning method based on complementary learning system[J].arXiv:2201.12604,2022.
[55]CHA S,CHO S,HWANG D,et al.Rebalancing batch normalization for exemplar-based class-incremental learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:20127-20136.
[56]VILLA A,ALCÁZAR J L,ALFARRA M,et al.Pivot:Prompting for video continual learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:24214-24223.
[57]CHAUDHRY A,DOKANIA P K,AJANTHAN T,et al.Rie-mannian walk for incremental learning:Understanding forgetting and intransigence[C]//Proceedings of the European Conference on Computer vision(ECCV).2018:532-547.
[58]PASZKE A,GROSS S,MASSA F,et al.Pytorch:An imperative style,high-performance deep learning library[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc.,2019:8026-8037.
[59]KINGMA D P.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发