A multi-view attention-based deep learning system for online deviant content detection

doi:10.1007/s11280-020-00840-9

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 互联网大数据与安全信息学研究中心

	A multi-view attention-based deep learning system for online deviant content detection
	Liang, Yunji 1; Guo, Bin 1; Yu, Zhiwen 1; Zheng, Xiaolong 2; Wang, Zhu 1; Tang, Lei 3
刊名	WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
	2020-09-30
页码	24
关键词	Deviant content Deep learning Ensemble learning View attention Social media
ISSN号	1386-145X
DOI	10.1007/s11280-020-00840-9
通讯作者	Liang, Yunji(liangyunji@nwpu.edu.cn)
英文摘要	With the exponential growth of user-generated content, policies and guidelines are not always enforced in social media, resulting in the prevalence of deviant content violating policies and guidelines. The adverse effects of deviant content are devastating and far-reaching. However, the detection of deviant content from sparse and imbalanced textual data is challenging, as a large number of stakeholders are involved with different stands and the subtle linguistic cues are highly dependent on complex context. To address this problem, we propose a multi-view attention-based deep learning system, which combines random subspace and binary particle swarm optimization (RS-BPSO) to distill content of interest (candidates) from imbalanced data, and applies the context and view attention mechanisms in convolutional neural network (dubbed as SSCNN) for the extraction of structural and semantic features. We evaluate the proposed approach on a large-scale dataset collected from Facebook, and find that RS-BPSO is able to detect whether the content is associated with marijuana with an accuracy of 87.55%, and SSCNN outperforms baselines with an accuracy of 94.50%.
资助项目	2030 National Key AI Program of China[2018AAA0100500] ; natural science foundation of China[61902320] ; natural science foundation of China[71472175] ; natural science foundation of China[71602184] ; natural science foundation of China[71621002] ; fundamental research funds for the central universities[31020180QD140]
WOS关键词	RANDOM SUBSPACE METHOD ; CLASSIFICATION
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000574077000001
资助机构	2030 National Key AI Program of China ; natural science foundation of China ; fundamental research funds for the central universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42047]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心
通讯作者	Liang, Yunji
作者单位	1.Northwestern Polytech Univ, Xian, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Changan Univ, Xian, Peoples R China
推荐引用方式 GB/T 7714	Liang, Yunji,Guo, Bin,Yu, Zhiwen,et al. A multi-view attention-based deep learning system for online deviant content detection[J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,2020:24.
APA	Liang, Yunji,Guo, Bin,Yu, Zhiwen,Zheng, Xiaolong,Wang, Zhu,&Tang, Lei.(2020).A multi-view attention-based deep learning system for online deviant content detection.WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,24.
MLA	Liang, Yunji,et al."A multi-view attention-based deep learning system for online deviant content detection".WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS (2020):24.