基于注意力机制的社交垃圾文本检测方法

doi:10.11959/j.issn.2096-109x.2020002

Abstract

Abstract:

In social networks,a large amount of spam has seriously threaten users' information security and the credit system of social websites.Aiming at the noise and sparsity problems,an attention-based CNN method was proposed to detect spam.On the basis of classical CNN,this method added a filter layer in which an attention mechanism based on Naive Bayesian weighting technology was designed to solve the noise issue.What’s more,instead of the original pooling strategy,it adapted an attention-based pooling policy to alleviate the sparsity problem.Compared with other methods,the results show that the accuracy has increased by 1.32%，2.15%，0.07%，1.63% on four different data sets.

Key words: social networks, information security, spam, attention system

CLC Number:

TP309

Qiang QU,Hongtao YU,Ruiyang HUANG. Attention-based approach of detecting spam in social networks[J]. Chinese Journal of Network and Information Security, 2020, 6(1): 54-61.

Figures/Tables 6

References 16

[1]	ZAFARANI , REZA , HUAN LIU , . 10 bits of surprise:detecting malicious users with minimum information[C]// The 24th ACM International on Conference on Information and Knowledge Management. 2015: 423-431.
[2]	RATKIEWICZ , JACOB , . Detecting and tracking political abuse in social media[C]// ICWSM. 2011: 297-304.
[3]	BENEVENUTO , FABRICIO , . Detecting spammers on twitter[C]// Collaboration,Electronic Messaging,Anti-abuse and Spam Conference. 2010:12.
[4]	SONG G E . Short text classification:a survey[J]. Journal of Multimedia, 2014,9(5):635.
[5]	YOON K . Convolutional neural networks for sentence classification[J]. arXiv preprint arXiv:1408.5882, 2014.
[6]	MIKOLOV , TOMAS , . Recurrent neural network based language model[C]// Eleventh Annual Conference of the International Speech Communication Association. 2010.
[7]	PASCANU R , MIKOLOV T , BENGIO Y . On the difficulty of training recurrent neural networks[C]// International Conference on Machine Learning. 2013: 1310-1318.
[8]	TANG D Y , QIN B , LIU T . Document modeling with gated recurrent neural network for sentiment classification[C]// The 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 1422-1432.
[9]	ZHANG X M , LI H , QU H . AHNN:an attention-based hybrid neural network for sentence modeling[C]// National CCF Conference on Natural Language Processing and Chinese Computing. 2017: 731-740.
[10]	ZHANG Y , ER M J , WANG N . Attention pooling-based convolutional neural network for sentence modelling[J]. Information Sciences 373, 2016: 388-403.
[11]	LI S , ZHAO Z , LIU T ,et al. Initializing convolutional filters with semantic features for text classification[C]// The 2017 Conference on Empirical Methods in Natural Language Processing. 2017: 1884-1889.
[12]	DU C S , HUANG L . Text classification research with attention-based recurrent neural networks[C]// International Journal of Computers Communications ＆ Control. 2018: 50-61.
[13]	ZHOU P , SHI W , TIAN J . Attention-based bidirectional long short-term memory networks for relation classification[C]// The 54th Annual Meeting of the Association for Computational Linguistics. 2016: 207-212.
[14]	WANG S D , MANNING C D . Manning.Baselines and bigrams:simple,good sentiment and topic classification[C]// The 50th Annual Meeting of the Association for Computational Linguistics. 2012: 90-94.
[15]	GOLDBERG Y , LEVY O . Word2vec explained:deriving Mikolov et al's negative-sampling word-embedding method[J]. arXiv preprint arXiv:1402.3722, 2014.
[16]	PENNINGTON J , SOCHER R , MANNING C . Glove:global vectors for word representation[C]// The 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014: 1532-1543.

Metrics

Recommended 0

No Suggested Reading articles found!

数据集	垃圾文本的检测准确率	正常文本的检测准确率	文本总数
Youtube	1 005(51.25%)	956(48.75%)	1 961
Opinion	800(50%)	800(50%)	1 600
SMS	3 198(13.41%)	4 827(86.59%)	5 574
E-mail	1 813(39.40%)	2 788(60.60%)	4 601

检测方法	Youtube	Opinion	SMS	E-mail
CNN^[5]	92.86	86.26	99.64	87.17
RNN^[6]	87.24	70.62	98.74	85.65
LSTM^[7]	89.80	78.75	98.20	89.78
GRU^[8]	87.75	81.25	98.92	89.56
Semantic-CNN^[11]	95.11	90.30	99.82	87.14
AP-BiLSTM^[13]	91.35	91.16	99.75	88.61
本文方法(MA-CNN)	96.43	93.31	99.89	91.41

表示方法	Youtube	Opinion	SMS	E-mail
Random	92.86	86.26	99.64	87.17
SkipGram	93.37	87.39	99.28	86.52
CBOW	93.87	82.50	99.46	87.39
Glove	92.86	87.50	98.56	78.48

激活函数	Youtube	Opinion	SMS	E-mail
relu	92.86	86.26	99.64	87.17
sigmoid	89.80	75.63	98.75	85.87
tanh	89.28	74.37	99.10	86.96
softplus	93.37	85.63	99.46	87.39
softsign	89.29	74.38	98.56	86.73
leakly-relu	92.36	85.62	99.28	86.95

Attention-based approach of detecting spam in social networks

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 16

Related Articles 15

Metrics

Recommended 0

[1]	Ganqin LIU, Hui LI, Hui ZHU, Yukun HUANG, Xingdong LIU. Public key cryptographic algorithm SM2 optimized implementation on low power embedded platform [J]. Chinese Journal of Network and Information Security, 2022, 8(6): 29-38.
[2]	Jun LIU, Lin YUAN, Zhishang FENG. Survey of key management schemes for cluster networks [J]. Chinese Journal of Network and Information Security, 2022, 8(6): 52-69.
[3]	Yi XIA, Mingjng LAN, Xiaohui CHEN, Junyong LUO, Gang ZHOU, Peng HE. Survey on explainable knowledge graph reasoning methods [J]. Chinese Journal of Network and Information Security, 2022, 8(5): 1-25.
[4]	Rongna XIE, Xiaonan FAN, Lin YUAN, Zichen GUO, Jiayu ZHU, Guozhen SHI. Research on extended access control mechanism in online social network [J]. Chinese Journal of Network and Information Security, 2021, 7(5): 123-131.
[5]	Jin LI, Jin CAO, Yueyu ZHANG, Meiru ZHANG, Hui LI. Reverse teaching design of curriculum ideological and political in information security major—Take the wireless communication network security course of Xidian University as an example [J]. Chinese Journal of Network and Information Security, 2021, 7(3): 166-174.
[6]	Guojie LIU,Jianbiao ZHANG. TPCM-based trusted PXE boot method for servers [J]. Chinese Journal of Network and Information Security, 2020, 6(6): 105-111.
[7]	Qiao HU,Yupeng HU,Xin LIAO,Zheng QIN,Jianhua SUN,Jiliang ZHANG. Investigation,analysis and improvement mentality of the revision on information security’s training program to undergraduates in Hunan University [J]. Chinese Journal of Network and Information Security, 2020, 6(4): 153-158.
[8]	JIA Chunfu,LI Ruiqi,TIAN Meiqi,CHENG Xiaoyang. Discuss on cultivating mode of information security and law inter-disciplinary talents [J]. Chinese Journal of Network and Information Security, 2019, 5(3): 31-35.
[9]	Jinxin ZUO,Ziyu GUO,Jin LI,Jie ZHANG,Yueming LU. Security evaluation method for confidential and stable complex systems [J]. Chinese Journal of Network and Information Security, 2019, 5(2): 58-65.
[10]	Shudi CHEN,Youwen ZHU. Shoulder-surfing resistant PIN-entry method [J]. Chinese Journal of Network and Information Security, 2019, 5(1): 87-93.
[11]	Ying CHENG. Data protection impact assessment system in the mode of risk management [J]. Chinese Journal of Network and Information Security, 2018, 4(8): 63-70.
[12]	Qiang QU, Hongtao YU, Ruiyang HUANG. Spammer detection technology of social network based on graph convolution network [J]. Chinese Journal of Network and Information Security, 2018, 4(5): 39-46.
[13]	Zenan WU,Liqin TIAN,Zhigang WANG. Behavior authentication of Web users based on machine learning [J]. Chinese Journal of Network and Information Security, 2018, 4(1): 45-51.
[14]	Xin-min FAN. Practice and exploration of network information security course teaching innovation based on mobile learning and inverted classroom depth integration [J]. Chinese Journal of Network and Information Security, 2017, 3(9): 61-66.
[15]	Yuan MENG,Pei-qun WU. Research on professional learning margin of university information security teachers in China [J]. Chinese Journal of Network and Information Security, 2017, 3(7): 64-69.