Aditi Seetha;Satyendra Singh Chouhan;Emmanuel S. Pilli;Vaskar Raychoudhury;Snehanshu Saha
{"title":"DiEvD-SF:利用选择性遗忘的持续机器学习进行破坏性事件检测","authors":"Aditi Seetha;Satyendra Singh Chouhan;Emmanuel S. Pilli;Vaskar Raychoudhury;Snehanshu Saha","doi":"10.1109/TCSS.2024.3364544","DOIUrl":null,"url":null,"abstract":"Detecting disruptive events (DEs), such as riots, protests, and natural calamities, from social media is essential for studying geopolitical dynamics. To automate the process, existing methods rely on classical machine learning (ML) models applied to static datasets, which is counterproductive. To detect DEs from dynamic data streams, this article introduces a novel \n<italic>DiEvD-SF</i>\n framework, which uses continual machine learning (CML) with selective forgetting. Twitter (currently “X”) is used as a real-time and dynamic data source for validation. \n<italic>DiEvD-SF</i>\n considers the temporal nature of DEs and “selectively forgets” outdated DEs through machine unlearning. To the best of our knowledge, this article is the first to apply CML with selective forgetting to discard outdated DEs and to continue learning about the new DEs. Extensive evaluation using a painstakingly collected Twitter dataset shows that the proposed framework continually identifies new DEs with an average incremental accuracy of 78.942% and successfully forgets old DEs with an average forgetting time of 118.498 seconds, which is better than the state-of-the-art. Additionally, computational analysis is performed to establish the effectiveness of the \n<italic>DiEvD-SF</i>\n framework by applying various candidate selection strategies.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5000,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DiEvD-SF: Disruptive Event Detection Using Continual Machine Learning With Selective Forgetting\",\"authors\":\"Aditi Seetha;Satyendra Singh Chouhan;Emmanuel S. Pilli;Vaskar Raychoudhury;Snehanshu Saha\",\"doi\":\"10.1109/TCSS.2024.3364544\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Detecting disruptive events (DEs), such as riots, protests, and natural calamities, from social media is essential for studying geopolitical dynamics. To automate the process, existing methods rely on classical machine learning (ML) models applied to static datasets, which is counterproductive. To detect DEs from dynamic data streams, this article introduces a novel \\n<italic>DiEvD-SF</i>\\n framework, which uses continual machine learning (CML) with selective forgetting. Twitter (currently “X”) is used as a real-time and dynamic data source for validation. \\n<italic>DiEvD-SF</i>\\n considers the temporal nature of DEs and “selectively forgets” outdated DEs through machine unlearning. To the best of our knowledge, this article is the first to apply CML with selective forgetting to discard outdated DEs and to continue learning about the new DEs. Extensive evaluation using a painstakingly collected Twitter dataset shows that the proposed framework continually identifies new DEs with an average incremental accuracy of 78.942% and successfully forgets old DEs with an average forgetting time of 118.498 seconds, which is better than the state-of-the-art. Additionally, computational analysis is performed to establish the effectiveness of the \\n<italic>DiEvD-SF</i>\\n framework by applying various candidate selection strategies.\",\"PeriodicalId\":13044,\"journal\":{\"name\":\"IEEE Transactions on Computational Social Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2024-03-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Computational Social Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10462483/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, CYBERNETICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Computational Social Systems","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10462483/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, CYBERNETICS","Score":null,"Total":0}
引用次数: 0
摘要
从社交媒体中检测骚乱、抗议和自然灾害等破坏性事件(DE)对于研究地缘政治动态至关重要。要实现这一过程的自动化,现有的方法依赖于应用于静态数据集的经典机器学习(ML)模型,这只会适得其反。为了从动态数据流中检测 DE,本文介绍了一种新颖的 DiEvD-SF 框架,该框架采用了带有选择性遗忘的持续机器学习 (CML)。Twitter(目前为 "X")被用作验证的实时动态数据源。DiEvD-SF 考虑了 DE 的时间性,并通过机器非学习 "有选择地遗忘 "过时的 DE。据我们所知,这篇文章是第一篇应用选择性遗忘的 CML 来摒弃过时的 DE 并继续学习新 DE 的文章。使用精心收集的 Twitter 数据集进行的广泛评估表明,所提出的框架能持续识别新的 DE,平均增量准确率为 78.942%,并能成功遗忘旧的 DE,平均遗忘时间为 118.498 秒,优于最先进的技术。此外,我们还进行了计算分析,通过应用各种候选选择策略来确定 DiEvD-SF 框架的有效性。
DiEvD-SF: Disruptive Event Detection Using Continual Machine Learning With Selective Forgetting
Detecting disruptive events (DEs), such as riots, protests, and natural calamities, from social media is essential for studying geopolitical dynamics. To automate the process, existing methods rely on classical machine learning (ML) models applied to static datasets, which is counterproductive. To detect DEs from dynamic data streams, this article introduces a novel
DiEvD-SF
framework, which uses continual machine learning (CML) with selective forgetting. Twitter (currently “X”) is used as a real-time and dynamic data source for validation.
DiEvD-SF
considers the temporal nature of DEs and “selectively forgets” outdated DEs through machine unlearning. To the best of our knowledge, this article is the first to apply CML with selective forgetting to discard outdated DEs and to continue learning about the new DEs. Extensive evaluation using a painstakingly collected Twitter dataset shows that the proposed framework continually identifies new DEs with an average incremental accuracy of 78.942% and successfully forgets old DEs with an average forgetting time of 118.498 seconds, which is better than the state-of-the-art. Additionally, computational analysis is performed to establish the effectiveness of the
DiEvD-SF
framework by applying various candidate selection strategies.
期刊介绍:
IEEE Transactions on Computational Social Systems focuses on such topics as modeling, simulation, analysis and understanding of social systems from the quantitative and/or computational perspective. "Systems" include man-man, man-machine and machine-machine organizations and adversarial situations as well as social media structures and their dynamics. More specifically, the proposed transactions publishes articles on modeling the dynamics of social systems, methodologies for incorporating and representing socio-cultural and behavioral aspects in computational modeling, analysis of social system behavior and structure, and paradigms for social systems modeling and simulation. The journal also features articles on social network dynamics, social intelligence and cognition, social systems design and architectures, socio-cultural modeling and representation, and computational behavior modeling, and their applications.