基于多任务学习的微博谣言检测方法

doi:10.3778/j.issn.1002-8331.2007-0152

摘要/Abstract

摘要：

微博谣言的广泛传播给当今社会造成了日益严峻的负面影响。基于深度神经网络的方法存在缺少大量带标签的数据。研究发现，谣言经常伴随负面情感，而非谣言则伴随正面情感，考虑到谣言与非谣言之间表现出的相反情感倾向性，提出一种将谣言检测和情感分析这两个高度相关的任务结合起来学习的多任务学习方法，为了尽可能多地挖掘不同任务之间的关联，全面分析谣言检测任务的特征，设计了一个由BERT和BiGRU联合的多任务学习框架（BERT-BiGRU-MTL，BBiGM）。利用权值共享的方法对两个任务进行联合训练，同时提取出任务之间的共同特征和针对谣言检测任务的特定特征，利用情感分析任务辅助谣言检测。研究结果表明，该方法在准确率、精确率、F1值评测指标上优于采用单任务学习的方法。

关键词: 多任务学习, 谣言检测, 情感分析, 微博

Abstract:

The widespread dissemination of Weibo rumors have caused an increasingly severe negative impact on today’s society. The method based on deep neural network has the problem of lack of a large amount of labeled data. The research has found that rumors are often accompanied by negative emotions, while non-rumors are accompanied by positive emotions. Taking into account the opposite emotional tendencies between rumors and non-rumors, a method is proposed to highly correlate rumors detection and sentiment analysis. The multi-task learning method that combines the tasks of BERT and BiGRU, in order to mine as many associations between different tasks as possible, and comprehensively analyze the characteristics of the rumor detection task, a multi-task learning framework（BERT-BiGRU-MTL, BBiGM）. The weight sharing method is used to jointly train the two tasks, and at the same time, the common features between the tasks and the specific features for the rumor detection task are extracted, and the sentiment analysis task is used to assist the rumor detection. The research results show that this method is better than the single-task learning method in terms of accuracy, precision and F1 value evaluation index.

Key words: multi-task learning, rumor detection, emotion analysis, Weibo

沈瑞琳，潘伟民，彭成，尹鹏博. 基于多任务学习的微博谣言检测方法[J]. 计算机工程与应用, 2021, 57(24): 192-197.

SHEN Ruilin, PAN Weimin, PENG Cheng, YIN Pengbo. Microblog Rumor Detection Method Based on Multi-task Learning[J]. Computer Engineering and Applications, 2021, 57(24): 192-197.

参考文献

[1] 陈帆.基于LSTM情感分析模型的微博谣言识别方法研究[D].武汉：华中师范大学，2018.
CHEN F.Research on recognition method of Weibo rumors based on LSTM sentiment analysis model[D].Wuhan：Central China Normal University，2018.
[2] ZIMBRA D，GHIASSI M，LEE S.Brand-related twitter sentiment analysis using feature engineering and the dynamic architecture for artificial neural networks[C]//Proceedings of the 49th Hawaii International Conference on System Sciences.Koloa：IEEE，2016：1930-1938.
[3] 首欢容，邓淑卿，徐健.基于情感分析的网络谣言识别方法[J].数据分析与知识发现，2017，7：44-51.
SHOU H R，DENG S Q，XU J.Network rumor recognition method based on sentiment analysis[J].Data Analysis and Knowledge Discovery，2017，7：44-51.
[4] 李巍胤.基于情感分析的微博谣言识别模式研究[D].重庆：重庆大学，2016.
LI W Y.Research on recognition pattern of Weibo rumors based on sentiment analysis[D].Chongqing：Chongqing University，2016.
[5] CASTILLO C，MENDOZA M，POBLETE B.Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web.Hyderabad：ACM Press，2011：675-684.
[6] YANG F，LIU Y，YU X H，et al.Automatic detection of rumor on Sina Weibo[C]//Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics.Beijing：ACM，2012：13-20.
[7] FRIGGERI A，ADAMIC L A，ECKLES D，et al.Rumor cascades[C]//Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media，2014：101-110.
[8] ZHAO Z，RESNICK P，MEI Q Z.Enquiring minds：early detection of rumors in social media from enquiry posts[C]//Proceedings of the 24th International Conference on World Wide Web.Florence：ACM Press，2015：1395-1405.
[9] KWON S，CHA M，JUNG K，et al.Prominent features of rumor propagation in online social media[C]//Proceedings of the 2013 IEEE 13th International Conference on Data Mining.Dallas：IEEE，2013.
[10] MA J，GAO W，WEI Z Y，et al.Detect rumors using time series of social context information on microblogging websites[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.Melbourne：ACM Press，2015：1751-1754.
[11] WU K，YANG S，ZHU K Q.False rumors detection on Sina Weibo by propagation structures[C]//2015 IEEE 31st International Conference on Data Engineering.Seoul：IEEE，2015：651-662.
[12] 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，2016：3818-3824.
[13] YU F，LIU Q，WU S，et al.A convolutional approach for misinformation identification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence，2017：3901-3907.
[14] 尹鹏博，潘伟民，彭成，等.基于用户特征分析的微博谣言早期检测研究[J].情报杂志，2020，39（7）：81-86.
YIN P B，PAN W M，PENG C，et al.Research on early detection of Weibo rumors based on user characteristics analysis[J].Journal of Intelligence，2020，39（7）：81-86.
[15] 李力钊，蔡国永，潘角.基于C-GRU的微博谣言事件检测方法[J].山东大学学报（工学版），2019，49（2）：102-106.
LI L Z，CAI G Y，PAN J.A microblog rumor events detection method based on C-GRU[J].Journal of Shandong University（Engineering Science Edition），2019，49（2）：102-106.
[16] ZHANG Y，CHEN W L，YEO C K.Detecting rumors on online social networks using multi-layer autoencoder[C]//Proceedings of the 2017 IEEE Technology & Engineering Management Conference，2017：437-441.
[17] CHEN W L，ZHANG Y，YEO C K，et al.Unsupervised rumor detection based on users’ behaviors using neural networks[J].Pattern Recognition Letters，2018，105：226-233.
[18] LIU P F，QIU X P，HUANG X J.Recurrent neural network for text classification with multi-task learning[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence，2016：2873-2879.
[19] MA J，GAO W，WONG K F.Detect rumor and stance jointly by neural multi-task learning[C]//Proceedings of the WWW’18 Companion.Lyon：ACM Press，2018：585-593.