Internet Public Opinion Event Detection Based on the Joint Model

Journal of Information Security Research ›› 2021, Vol. 7 ›› Issue (3): 207-214.

Previous Articles Next Articles

Internet Public Opinion Event Detection Based on the Joint Model

Received:2021-03-09 Online:2021-03-05 Published:2021-03-17

基于联合模型的网络舆情事件检测方法

冯科¹,阮树骅¹,陈兴蜀²,王海舟¹,王文贤³,蒋术语¹

1. 四川大学网络空间安全学院
2. 四川大学网络空间安全研究院成都610065
3. 四川大学网络空间安全研究院

通讯作者: 冯科
作者简介:冯科（1993-），男，四川大学硕士生，主要研究方向为云计算与大数据安全、事件检测、事件抽取。2676516772@qq.com 阮树骅（1966-），四川大学副教授、硕士生导师，主要研究方向为云计算与大数据安全、区块链安全。ruanshuhua@scu.edu.cn 陈兴蜀（1968-），四川大学教授、博士生导师，主要研究方向为云计算与大数据安全、可信计算与信息保障。chenxs@scu.edu.cn 王海舟（1986-），四川大学副教授，硕士生导师，主要研究方向为舆情监控，情报分析，社交网络分析。scu.haizhou@gmail.com 王文贤（1978-），四川大学讲师，博士，主要研究方向为开源情报采集、分析与挖掘，网络安全。catean2@qq.com 蒋术语（1996-），四川大学博士生，主要研究方向为舆情引导、文本生成、事件分析。530995919@qq.com

Abstract

Abstract: At present, the Internet has become an important place for public opinion, and major events of Internet public opinion have an increasingly serious impact on the stability of Internet public opinion. In order to detect major events of public opinion, a joint model detection method based on deep learning and the expert knowledge pattern base of the Internet public opinion events is proposed. Firstly, deep learning can identify the characteristics of deep hidden events and obtain the candidate event set of public opinion in the news text. Secondly, based on the news text keyword set extracted automatically, the expert mode intervention is adopted to establish the expert knowledge pattern base of public opinion events. Finally, on the basis of the event discovery of deep learning, the expert knowledge pattern base of Internet public opinion events is combined to match the pattern to identify major public opinion events, obtain the type and subtype of the event, and reduce the missed judgment and misjudgment of major public opinion events. At the same time, the event discovery and classification results of deep learning are integrated into the expert knowledge pattern base of Internet public opinion events through expert mode in-tervention as real-time feedback, which dynamically modifies and expands the major event pattern of public opinion and improves the ability to identify the new type of Internet public opinion events. The comparative experiments show that the joint model is superior to the single model and has a better ability to identify major events of Internet public opinion.

Key words: event detection, Internet public opinion event, pattern matching, deep learning, joint model

摘要： 当前网络成为了重要的舆论场所，网络舆情重大事件对网络舆情稳定的影响日益严重。为了检测网络舆情中的重大事件，提出了一种基于深度学习的事件发现与网络舆情事件专家知识模式库相结合的联合模型检测方法。首先，利用深度学习可识别深层隐性事件的特性，获取新闻文本中的网络舆情候选事件集；其次，基于自动提取的新闻文本关键词集，通过专家模式干预，建立网络舆情事件专家知识模式库；最后，在深度学习的事件发现基础上，联合网络舆情事件专家知识模式库模式匹配，识别网络舆情重大事件，并获得该事件的类型和子类型，降低了网络舆情重大事件的漏判和误判。同时，该联合模型将深度学习的事件发现和分类结果，通过专家模式干预，实时反馈融入网络舆情事件专家知识模式库，动态修正和扩充了网络舆情重大事件模式，提升了应对新型网络舆情事件的能力。对比实验表明，联合模型优于单模型，具有较好的网络舆情重大事件识别的能力。

关键词: 事件检测, 网络舆情事件, 模式匹配, 深度学习, 联合模型

冯科阮树骅陈兴蜀王海舟王文贤蒋术语. 基于联合模型的网络舆情事件检测方法 [J]. 信息安全研究, 2021, 7(3): 207-214.

References

[1] Andrew S, Amanda T, Ashish J, et al. Mining for Causal Rela-tionships: A Data-Driven Study of the Islamic State[C] //Proc of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: Association for Computing Machinery, 2015: 2137–2146 [2] Chinatsu A, Mila R. REES: a large-scale relation and event extraction system[C] //Proc of the sixth conference on Applied natural language processing. USA: Association for Computa-tional Linguistics, 2000: 76–83 [3] Yangarber R. Scenario Customization for Information Extrac-tion[D]. New York: New York University, 2001. [4] Karin V, Helen L, Chris R, et al. High-precision biological event extraction with a concept recognizer[C] //Proc of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task. USA: Association for Computational Linguistics, 2009: 50–58 [5] Hung S, Lin C, Hong J. Web Mining for Event-based Com-monsense Knowledge using Lexico-Syntactic Pattern Matching and Semantic Role Labeling[J]. Expert Systems with Applica-tions, 2010, 37(1): 341-347 [6] Grishman R, Westbrook D, Meyers A. NYU’s English ace 2005 system description[J]. Journal on Satisfiability, 2005, 51(11): 1927-1938 [7] David A. The stages of event extraction[C] //Proc of the Workshop on Annotating and Reasoning about Time and Events. USA: Association for Computational Linguistics, 2006: 1–8 [8] JI H, Grishman R. Refining event extraction through cross-document inference[C] //Proc of the 46th Annual Meet-ing of the Association for Computational Linguistics. USA: Association for Computational Linguistics, 2008: 254-162 [9] Liao S, Grishman R. Using document level cross-event infer-ence to improve event extraction[C] //Proc of the 48th Annual Meeting of the Association for Computational Linguistics. USA: Association for Computational Linguistics, 2010: 789-797 [10] Hong Yu, Zhang Jianfeng, Ma Bin, et al. Using cross-entity inference to improve event extraction[C] //Proc of the 49th Annual Meeting of the Association for Computational Linguis-tics. USA: Association for Computational Linguistics, 2011: 1127–1136 [11] Li Qi, Ji Heng, Huang Liang. Joint event extraction via struc-tured prediction with global features[C] //Proc of the 51th An-nual Meeting of the Association for Computational Linguistics. USA: Association for Computational Linguistics, 2013: 73-82 [12] Chen Yubo, Xu Liheng, Liu Kang, et al. Event extraction via dynamic multi-pooling convolutional neural networks[C] //Proc of the 53th Annual Meeting of the Association for Computational Linguistics. China: Association for Computa-tional Linguistics, 2015: 167-176 [13] Nguyen T, Cho K, Grishman R. Joint event extraction via re-current neural networks[C] //Proc of the 2016 Conference of the North American Chapter of the Association for Computa-tional Linguistics: Human Language Technologies. USA: Asso-ciation for Computational Linguistics, 2016: 300-309 [14] Feng Xiaocheng, Qin Bing, Liu Ting. A language-independent neural network for event detection[J]. Science China Infor-mation Sciences, 2018, 61(9): 92-106 [15] Liu Shulin, Chen Yubo, Liu Kang, et al. Exploiting argument information to improve event detection via supervised atten-tion mechanisms[C] //Proc of the 55th Annual Meeting of the Association for Computational Linguistics. Canada: Associa-tion for Computational Linguistics, 2017: 1789-1798 [16] 马晨曦, 陈兴蜀, 王海舟, 等. 基于递归神经网络的中文事件检测[J]. 信息网络安全, 2018, (5): 75-81 [17] Lin Hongyu, Lu Yaojie, Han Xianpei, et al. Nugget Proposal Networks for Chinese Event Detection[C] //Proc of the 56th Annual Meeting of the Association for Computational Lin-guistics. Australia: Association for Computational Linguistics, 2018: 1565-1574 [18] Ding Ning, Li Ziran, Liu Zhiyuan, et al. Event Detection with Trigger-Aware Lattice Neural Network[C] //Proc of the 2019 Conference on Empirical Methods in Natural Language Pro-cessing and the 9th International Joint Conference on Natural Language Processing. China: Association for Computational Linguistics, 2019: 347-356 [19] Xu Guixian, Meng Yueting, Zhou Xiaokai, et al. Chinese Event Detection Based on Multi-Feature Fusion and Bi LSTM[J]. IEEE Access, 2019, (7): 134992-135004 [20] 徐建忠, 朱骏, 赵瑞, 等. 基于新闻流的信息安全事件发现[J]. 信息安全研究, 2016, 2(12): 1105-1109 [21] 陈华钧, 耿玉霞, 叶志权, 等. “知识图谱+深度学习”赋能内容安全[J]. 信息安全研究, 2019, 5(11): 975-980

Internet Public Opinion Event Detection Based on the Joint Model

基于联合模型的网络舆情事件检测方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 13

Recommended Articles

Metrics

[1]	. Survey of Security Situation Prediction Technology Based on Artificial Intelligence [J]. Journal of Information Security Research, 2020, 6(6): 0-0.
[2]	. Design of Protocol Monitoring System Based on Cloud Computing and Deep Learning [J]. Journal of Information Security Research, 2020, 6(12): 1127-1132.
[3]	. The Review of Information Hiding Technology Based on GAN Image Generation [J]. Journal of Information Security Research, 2019, 5(9): 771-777.
[4]	. Study on People Flow Situation Awareness Based on Intelligent Video Analysis [J]. Journal of Information Security Research, 2019, 5(6): 488-494.
[5]	. Android Malware Detection Algorithm Based on CNN and Naive Bayesian Method [J]. Journal of Information Security Research, 2019, 5(6): 470-476.
[6]	. Image Steganography Methods from Traditional to Deep Learning [J]. Journal of Information Security Research, 2019, 5(3): 230-235.
[7]	. A Survey of Image Captioning Technology [J]. Journal of Information Security Research, 2019, 5(11): 988-992.
[8]	. Negative Sentiment Detection in Intelligent HumanMachine Dialogue [J]. Journal of Information Security Research, 2019, 5(11): 981-987.
[9]	. Knowledge Graph and Deep Learning Empowering Content Security [J]. Journal of Information Security Research, 2019, 5(11): 975-980.
[10]	. Design and Implementation of Android Malware Detection System Based on Deep Learning [J]. Journal of Information Security Research, 2018, 4(2): 140-144.
[11]	. Network intrusion detection model based on convolutional neural network [J]. Journal of Information Security Research, 2017, 3(11): 990-994.
[12]	. The Detecting Algorithm of Pornographic Image Based on Deep Learning and Model Cascade [J]. Journal of Information Security Research, 2016, 2(10): 903-908.
[13]	. The Comprehensive Technology Development of Face Recognition [J]. Journal of Information Security Research, 2016, 2(1): 33-39.