传播用户代表性特征学习的谣言检测方法

doi:10.3778/j.issn.1673-9418.2101030

计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (6): 1334-1342.DOI: 10.3778/j.issn.1673-9418.2101030

传播用户代表性特征学习的谣言检测方法

谢欣彤¹^,², 胡悦阳²^,⁵, 刘譞哲¹^,², 赵耀帅³^,⁴, 姜海鸥⁵^,⁶^,⁺()

1. 北京大学信息科学技术学院,北京 100871
2. 高可信软件技术教育部重点实验室（北京大学）,北京 100871
3. 中国民航信息网络股份有限公司,北京 101318
4. 中国民用航空局民航旅客服务智能化应用技术重点实验室,北京 101318
5. 北京大学软件与微电子学院,北京 102600
6. 北京大学（天津滨海）新一代信息技术研究院,天津 300452

收稿日期:2021-01-07 修回日期:2021-04-25 出版日期:2022-06-01 发布日期:2021-04-29
通讯作者: + E-mail: seagullwill@foxmail.com
作者简介:谢欣彤（1998—）,女,广东大埔人,硕士研究生,主要研究方向为数据分析。
胡悦阳（1997—）,男,安徽蚌埠人,硕士研究生,主要研究方向为大数据、区块链。
刘譞哲（1980—）,男,甘肃兰州人,博士,副教授,主要研究方向为服务计算、系统软件。
赵耀帅（1977—）,男,山东济宁人,硕士,高级软件工程师,主要研究方向为大数据、人工智能。
姜海鸥（1987—）,女,辽宁丹东人,博士,助理研究员,主要研究方向为云计算、大数据、机器学习。
基金资助:
国家重点研发计划(2018YFB1004400);北京高等学校卓越青年科学家项目(BJJWZYJH01201910001004)

Rumor Detection Based on Representative User Characteristics Learning Through Propagation

XIE Xintong¹^,², HU Yueyang²^,⁵, LIU Xuanzhe¹^,², ZHAO Yaoshuai³^,⁴, JIANG Hai’ou⁵^,⁶^,⁺()

1. School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
2. Key Laboratory of High Confidence Software Technologies of Ministry of Education (Peking University), Beijing 100871, China
3. TravelSky Technology Limited, Beijing 101318, China
4. Key Laboratory of Intelligent Passenger Service of Civil Aviation, Civil Aviation Administration of China, Beijing 101318, China
5. School of Software and Microelectronics, Peking University, Beijing 102600, China
6. Peking University Information Technology Institute (Tianjin Binhai), Tianjin 300452, China

Received:2021-01-07 Revised:2021-04-25 Online:2022-06-01 Published:2021-04-29
About author:XIE Xintong, born in 1998, M.S. candidate. Her research interest is data analysis.
HU Yueyang, born in 1997,M.S. candidate. His research interests include big data and block chain.
LIU Xuanzhe, born in 1980, Ph.D., associate professor. His research interests include services computing and system software.
ZHAO Yaoshuai, born in 1977, M.S., senior software engineer. His research interests include big data and artificial intelligence.
JIANG Hai’ou, born in 1987, Ph.D., assistant researcher. Her research interests include cloud computing, big data and machine learning.
Supported by:
National Key Research and Development Program of China(2018YFB1004400);Beijing Outstanding Young Scientist Program(BJJWZYJH01201910001004)

摘要/Abstract

摘要：

谣言的及时发现和有效管控,是互联网+政务服务中公共舆情治理的重要组成部分。互联网和移动互联网的发展,提高了民众沟通交流的便利度,同时也加速了谣言的传播速度和广度,极大地提高了谣言的影响力和危害力,给民众的生产生活带来干扰,也严重影响社会秩序。现有的网络平台辟谣工作大多依赖于人工举报筛查,往往耗费大量的时间和精力。而利用数据挖掘、机器学习技术实现的谣言检测算法大多基于文本信息,常用于追溯性谣言检测,不适用于谣言扩散早期数据量不足的情况。首先收集最新的网络平台数据进行标注构造数据集Weibo2020,对其中用户特征分布进行统计分析并选择具有代表性的用户特征,进而提出了基于传播用户代表性特征学习的早期谣言检测方法（RPPC）。经实验验证,RPPC与同样基于传播路径的算法在同等条件下,在输入数据规模减少50%的同时,将准确率提高了2.57个百分点。此外,该方法能对5 min内发布的消息进行检测,快速发现互联网内容中的疑似谣言且准确率达到近80%。因此可以认为提出的方法在现有的数据集中有较好的表现,能够在一定程度上辅助政府部门的舆情治理工作,从而提高政务服务的时效及质量。

关键词: 谣言检测, 机器学习, 特征分析, 传播路径, 互联网+政务服务, 舆情治理

Abstract:

Effective rumor detection and management has become an essential part of Internet plus government services initiative. The Internet era brings great convenience to people’s communication as well as speeds up the propagation of rumors, which not only interferes people’s normal living but also does harm to the social confidence system. Existing work of rumor debunking on the Internet is mostly based on manual work of public tip-offs and screening, which is time consuming and demanding. Meanwhile, work on algorithm of rumor detection based on data mining and machine learning depends heavily on text content, which is deficient during the early stage of rumor propagation. This paper constructs latest dataset Weibo2020, composed of both rumors and normal information, and extracts representative user characteristics from the perspective of statistics, then proposes an algorithm of early-stage rumor detection based on brief propagation path, named RPPC (representative propagation path classification). The experimental results indicate that the proposed method can improve the prediction accuracy by 2.57 percentage points while reducing the input data scale by 50%. Meanwhile, the proposed method can predict the authenticity of news released in 5 minutes and achieve an accuracy of about 80%. Therefore, the proposed method achieves good results in a limited size of dataset and can to some degree help with network public opinion governance and improve the efficiency and quality of government service.

Key words: rumor detection, machine learning, characteristic analysis, propagation path, Internet plus government services initiative, public opinion management

中图分类号:

TP181

谢欣彤, 胡悦阳, 刘譞哲, 赵耀帅, 姜海鸥. 传播用户代表性特征学习的谣言检测方法[J]. 计算机科学与探索, 2022, 16(6): 1334-1342.

XIE Xintong, HU Yueyang, LIU Xuanzhe, ZHAO Yaoshuai, JIANG Hai’ou. Rumor Detection Based on Representative User Characteristics Learning Through Propagation[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(6): 1334-1342.

图/表 12

参考文献 21

[1]	SCHRAVENDIJK J P V. Rumeurs, le plus vieux média du monde[M]. KAPFERER J N. Paris: Editions du Seuil, 1987.
[2]	陈燕方, 李志宇, 梁循, 等. 在线社会网络谣言检测综述[J]. 计算机学报, 2018, 41(7): 1648-1677.
	CHEN Y F, LI Z Y, LIANG X, et al. Review on rumor detection of online social networks[J]. Chinese Journal of Computers, 2018, 41(7): 1648-1677.
[3]	CASTILLO C, MENDOZA M, POBLETE B. Information credibility on Twitter[C]// Proceedings of the 20th International Conference on World Wide Web, Hyderabad, Mar 28-Apr 1, 2011. New York: ACM, 2011: 675-684.
[4]	ANDREEVSKAIA A, ANDREEVSKAIA A, BERGLER S, et al. Mining WordNet for fuzzy sentiment: sentiment tag extraction from WordNet glosses[C]// Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics, Trento, 2006. Stroudsburg: ACL, 2006: 209-216.
[5]	TAKAHASHI T, IGATA N. Rumor detection on Twitter[C]// Proceedings of the 6th International Conference on Soft Computing and Intelligent Systems, and the 13th International Symposium on Advanced Intelligent Systems, Kobe, Nov 20-24, 2012. Piscataway: IEEE, 2012: 452-457.
[6]	RATKIEWICZ J, CONOVER M, MEISS M, et al. Detecting and tracking the spread of astroturf memes in microblog streams[J]. arXiv:1011.3768, 2010.
[7]	QAZVINIAN V, ROSENGREN E, RADEV D R, et al. Rumor has it: identifying misinformation in microblogs[C]// Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Jul 27-31, 2011. Stroudsburg: ACL, 2011: 1589-1599.
[8]	MA J, GAO W, MITRA P, et al. Detecting rumors from microblogs with recurrent neural networks[C]// Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, Jul 9-15, 2016. Menlo Park: AAAI, 2016: 3818-3824.
[9]	毛二松, 陈刚, 刘欣, 等. 基于深层特征和集成分类器的微博谣言检测研究[J]. 计算机应用研究, 2016, 33(11): 3369-3373.
	MAO E S, CHEN G, LIU X, et al. Research on detecting micro-blog rumors based on deep features and ensemble classifier[J]. Application Research of Computers, 2016, 33(11): 3369-3373.
[10]	郭凯. 基于评论情感的微博谣言检测研究[D]. 大连: 大连理工大学, 2014.
	GUO K. The research of Microblog rumors detection based on comments sentiment[D]. Dalian: Dalian University of Technology, 2014.
[11]	ZHANG Q, ZHANG S Y, DONG J, et al. Automatic detection of rumor on social network[C]// LNCS 9362: Proceedings of the 4th Natural Language Processing and Chinese Computing, Nanchang, Oct 9-13, 2015. Cham: Springer, 2015: 113-122.
[12]	SUN S Y, LIU H Y, HE J, et al. Detecting event rumors on Sina Weibo automatically[C]// LNCS 7808:Proceedings of the 15th Asia-Pacific Web Conference on Web Technologies and Applications, Sydney, Apr 4-6, 2013. Berlin, Heidelberg: Springer, 2013: 120-131.
[13]	JIN Z, CAO J, ZHANG Y, et al. Novel visual and statistical image features for microblogs news verification[J]. IEEE Transactions on Multimedia, 2017, 19(3): 598-608. DOI URL
[14]	WANG Y Q, MA F L, JIN Z W, et al. EANN: event adversarial neural networks for multi-modal fake news detection[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, 2018. New York: ACM, 2018: 849-857.
[15]	KHATTAR D, GOUD J S, GUPTA M, et al. MVAE: multimodal variational autoencoder for fake news detection[C]// Proceedings of the 2019 World Wide Web Conference, San Francisco, May 13-17, 2019. New York: ACM, 2019: 2915-2921.
[16]	WU K, YANG S, ZHU K Q. False rumors detection on Sina weibo by propagation structures[C]// Proceedings of the 31st 2015 IEEE International Conference on Data Engineering, Seoul, Apr 13-17, 2015. Piscataway: IEEE, 2015: 651-662.
[17]	CAI G Y, WU H, LV R. Rumors detection in Chinese via crowd responses[C]// Proceedings of the 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Beijing, Aug 17-20, 2014. Washington: IEEE Computer Society, 2014: 912-917.
[18]	LIANG G, HE W, XU C, et al. Rumor identification in microblogging systems based on users’ behavior[J]. IEEE Transactions on Computational Social Systems, 2015, 2(3): 99-108. DOI URL
[19]	LI Q Z, ZHANG Q, SI L. Rumor detection by exploiting user credibility information, attention and multi-task learning[C]// Proceedings of the 57th Conference of the Association for Computational Linguistics, Florence, Jul 28-Aug 2, 2019. Stroudsburg: ACL, 2019: 1173-1179.
[20]	LIU Y, WU Y F. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 354-361.
[21]	CHUNG J, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv:1412.3555, 2014.

统计信息	真实消息	谣言消息
消息数量	3 460	3 688
发布用户	2 871	3 317
评论用户	206 518	74 192

统计信息	真实消息	谣言消息
消息数量	3 460	3 688
发布用户	2 871	3 317
评论用户	206 518	74 192

字段名称	含义
bi_followers_count	互相关注用户数
user_description	个人简介
user_avatar	头像图片链接
friends_count	关注数
followers_count	粉丝数
verified	是否为认证用户
statuses_count	动态数
user_created_at	注册时间
favourites_count	收藏数量
screen_name	用户名
gender	性别
user_geo_enabled	地理标识开启
urank	微博等级

字段名称	含义
bi_followers_count	互相关注用户数
user_description	个人简介
user_avatar	头像图片链接
friends_count	关注数
followers_count	粉丝数
verified	是否为认证用户
statuses_count	动态数
user_created_at	注册时间
favourites_count	收藏数量
screen_name	用户名
gender	性别
user_geo_enabled	地理标识开启
urank	微博等级

模型	类别	准确率	精确率	召回率	F1值
PPC_RNN+CNN	谣言真实消息	76.86	75.62 79.50	79.79 74.25	77.25 76.24
RPPC_RNN	谣言真实消息	60.11	55.95 97.88	99.58 19.63	71.65 32.71
RPPC_CNN	谣言真实消息	73.13	69.78 78.03	82.33 63.77	75.54 70.19
RPPC_RNN+CNN	谣言真实消息	79.43	77.51 81.81	82.30 76.73	79.74 79.09
RPPC_RNN+CNN_5	谣言真实消息	78.98	78.32 80.00	79.65 78.18	78.86 78.94
RPPC_RNN+CNN_6	谣言真实消息	79.69	78.79 80.76	80.96 78.35	79.82 79.48
RPPC_RNN+CNN_7	谣言真实消息	79.36	78.79 80.04	79.65 79.01	79.17 79.48

传播用户代表性特征学习的谣言检测方法

Rumor Detection Based on Representative User Characteristics Learning Through Propagation

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 15

编辑推荐

Metrics

[1]	许嘉, 韦婷婷, 于戈, 黄欣悦, 吕品. 题目难度评估方法研究综述[J]. 计算机科学与探索, 2022, 16(4): 734-759.
[2]	杨悦, 王士同. 随机特征映射的四层神经网络及其增量学习[J]. 计算机科学与探索, 2021, 15(7): 1265-1278.
[3]	赵雪莉, 卢光跃, 吕少卿, 张潘. 结合属性信息的二分网络表示学习[J]. 计算机科学与探索, 2021, 15(3): 495-505.
[4]	马永杰, 徐小冬, 张茹, 谢艺蓉, 陈宏. 生成式对抗网络及其在图像生成中的研究进展[J]. 计算机科学与探索, 2021, 15(10): 1795-1811.
[5]	宋雨萌，谷峪，李芳芳，于戈. 人工智能赋能的查询处理与优化新技术研究综述[J]. 计算机科学与探索, 2020, 14(7): 1081-1103.
[6]	马毓敏，王士同. 最大化AUC的正例未标注分类及其增量算法[J]. 计算机科学与探索, 2020, 14(11): 1879-1887.
[7]	梁俊杰，韦舰晶，蒋正锋. 生成对抗网络GAN综述[J]. 计算机科学与探索, 2020, 14(1): 1-17.
[8]	孙涛，周志华. 近似多元信息多样性[J]. 计算机科学与探索, 2019, 13(4): 639-646.
[9]	龙廷艳，万良，丁红卫. 自编码网络在JavaScript恶意代码检测中的应用研究[J]. 计算机科学与探索, 2019, 13(12): 2073-2084.
[10]	丁毅，王明亮，张道强. 差异性随机子空间集成[J]. 计算机科学与探索, 2018, 12(9): 1434-1443.
[11]	张贤贤，王浩宇，郭耀，徐国爱. 基于众包和机器学习的移动应用隐私评级研究[J]. 计算机科学与探索, 2018, 12(8): 1238-1251.
[12]	王建飞，亢良伊，刘杰，叶丹. 分布式随机方差消减梯度下降算法topkSVRG[J]. 计算机科学与探索, 2018, 12(7): 1047-1054.
[13]	李盼，赵文涛，刘强，崔建京，殷建平. 机器学习安全性问题及其防御技术研究综述[J]. 计算机科学与探索, 2018, 12(2): 171-184.
[14]	王蒙湘，李芳芳，谷峪，于戈. 交互式数据探索综述[J]. 计算机科学与探索, 2017, 11(2): 171-184.
[15]	陈茜，史殿习，杨若松. 多维数据特征融合的用户情绪识别[J]. 计算机科学与探索, 2016, 10(6): 751-760.