A multi-view attention-based deep learning system for online deviant content detection
Liang, Yunji1; Guo, Bin1; Yu, Zhiwen1; Zheng, Xiaolong2; Wang, Zhu1; Tang, Lei3
Source PublicationWORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
ISSN1386-145X
2020-09-30
Pages24
Corresponding AuthorLiang, Yunji(liangyunji@nwpu.edu.cn)
AbstractWith 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%.
KeywordDeviant content Deep learning Ensemble learning View attention Social media
DOI10.1007/s11280-020-00840-9
WOS KeywordRANDOM SUBSPACE METHOD ; CLASSIFICATION
Indexed BySCI
Language英语
Funding Project2030 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]
Funding Organization2030 National Key AI Program of China ; natural science foundation of China ; fundamental research funds for the central universities
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering
WOS IDWOS:000574077000001
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/42048
Collection复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
Corresponding AuthorLiang, Yunji
Affiliation1.Northwestern Polytech Univ, Xian, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
3.Changan Univ, Xian, Peoples R China
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liang, Yunji]'s Articles
[Guo, Bin]'s Articles
[Yu, Zhiwen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liang, Yunji]'s Articles
[Guo, Bin]'s Articles
[Yu, Zhiwen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liang, Yunji]'s Articles
[Guo, Bin]'s Articles
[Yu, Zhiwen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.