Storyline extraction method from Weibo news based on graph convolutional network

doi:10.11772/j.issn.1001-9081.2021030451

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (11): 3139-3144.DOI: 10.11772/j.issn.1001-9081.2021030451

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Storyline extraction method from Weibo news based on graph convolutional network

Xujian ZHAO(), Chongwei WANG

School of Computer Science and Technology，Southwest University of Science and Technology，Mianyang Sichuan 621010，China

Received:2021-03-24 Revised:2021-06-03 Accepted:2021-06-03 Online:2021-11-29 Published:2021-11-10
Contact: Xujian ZHAO
About author:ZHAO Xujian，born in 1984，Ph. D.，associate professor. His research interests include text mining，natural language processing，Web information processing
WANG Chongwei，born in 1995，M. S. candidate. His research interests include information extraction，machine learning.
Supported by:
the Humanities and Social Sciences Foundation of the Ministry of Education(17YJCZH260);the Key Project of Science and Technology Department of Sichuan Province(2020YFS0057);the CERNET Innovation Project(NGII20180403)

基于图卷积网络的微博新闻故事线抽取方法

赵旭剑(), 王崇伟

西南科技大学计算机科学与技术学院，四川绵阳 621010

通讯作者: 赵旭剑
作者简介:赵旭剑（1984—），男，四川绵阳人，副教授，博士，CCF 会员，主要研究方向：文本挖掘、自然语言处理、Web 信息处理
王崇伟（1995—），男，四川泸州人，硕士研究生，主要研究方向：信息抽取、机器学习。
基金资助:
教育部人文社会科学基金资助项目(17YJCZH260);四川省科学技术厅重点项目(2020YFS0057);赛尔网络下一代互联网技术创新项目(NGII20180403)

Abstract

Abstract:

As a key platform for people to acquire and disseminate news events， Weibo hides rich event information. Extracting storylines from Weibo data provides users with an intuitive way to accurately understand event evolution. However， the data sparseness and lack of context make it difficult to extract storylines from Weibo data. Therefore， two consecutive tasks for extracting storylines automatically from Weibo data were introduced： 1） events were modeled by propagation impact of Weibo， and the primary events were extracted； 2） the heterogeneous event graph was built based on the event features， and an Event Graph Convolution Network （E-GCN） model was proposed to improve the learning ability of implicit relations between events， so as to predict story branches of the events and link the events. The proposed method was evaluated from the perspectives of story branch and storyline on real datasets. In story branch generation evaluation， the results show that compared with Bayesian model， Steiner tree and Story forest， the proposed method has the F1 value higher by 28 percentage points， 20 percentage points and 27 percentage points on Dataset1 respectively， and higher by 19 percentage points， 12 percentage points and 22 percentage points on Dataset2 respectively. In storyline extraction evaluation， the results show that compared with Story timeline， Steiner tree and Story forest， the proposed method has the correct edge accuracy higher by 33 percentage points， 23 percentage points and 17 percentage points on Dataset1 respectively， and higher by 12 percentage points， 3 percentage points and 9 percentage points on Dataset2 respectively.

Key words: social network, Weibo, primary event, storyline, Graph Convolutional Network (GCN)

摘要：

微博作为人们获取和传播新闻事件的主要平台，隐藏着丰富的事件信息。从微博数据中抽取故事线能为用户提供一种直观的方式来准确理解事件演化，然而微博数据稀疏和上下文缺乏的特点为故事线抽取带来了挑战。因此，通过两个连续的任务从微博数据中自动抽取故事线：1）基于微博传播影响力对事件进行建模，并提取出首要事件；2）基于事件特征建立异构事件图，提出事件图卷积网络（E-GCN）模型来提升对事件间隐式关系的学习能力，从而实现事件的故事分支预测并链接事件。在真实数据集上从故事分支和故事线两个角度进行评测，结果表明所提方法在故事分支生成测评中，相较于贝叶斯模型、斯坦纳树和故事森林在F1值上，在Dataset1上分别高出28个百分点、20个百分点和27个百分点，在Dataset2上分别高出19个百分点、12个百分点和22个百分点；而在故事线抽取评测中，相较于故事时间线、斯坦纳树和故事森林在正确的边准确率上，在Dataset1上分别高出33个百分点、23个百分点和17个百分点，在Dataset2上分别高出12个百分点、3个百分点和9个百分点。

关键词: 社交网络, 微博, 首要事件, 故事线, 图卷积网络

CLC Number:

TP391

Xujian ZHAO, Chongwei WANG. Storyline extraction method from Weibo news based on graph convolutional network[J]. Journal of Computer Applications, 2021, 41(11): 3139-3144.

赵旭剑, 王崇伟. 基于图卷积网络的微博新闻故事线抽取方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3139-3144.

Figures/Tables 10

References 19

1	LIU B， HAN F X， NIU D， et al. Story forest： extracting events and telling stories from breaking news ［J］. ACM Transactions on Knowledge Discovery from Data， 2020， 14（3）： Article No.31. 10.1145/3377939
2	HUANG D P， HU S Y， CAI Y， et al. Discovering event evolution graphs based on news articles relationships ［C］// Proceedings of the 2014 IEEE 11th International Conference on e-Business Engineering. Piscataway： IEEE， 2014： 246-251. 10.1109/icebe.2014.49
3	ZHOU P P， WU B， CAO Z. EMMBTT： a novel event evolution model based on TFxIEF and TDC in tracking news streams ［C］// Proceedings of the 2017 IEEE 2nd International Conference on Data Science in Cyberspace. Piscataway： IEEE， 2017： 102-107. 10.1109/dsc.2017.53
4	李莹莹，马帅，蒋浩谊，等.一种基于社交事件关联的故事脉络生成方法［J］.计算机研究与发展，2018，55（9）：1972-1986. 10.7544/issn1000-1239.2018.20180155
	LI Y Y， MA S， JIANG H Y， et al. An approach for storytelling by correlating events from social networks ［J］. Journal of Computer Research and Development， 2018， 55（9）： 1972-1986. 10.7544/issn1000-1239.2018.20180155
5	YUAN R F， ZHOU Q F， ZHOU W B. dTexSL： a dynamic disaster textual storyline generating framework ［J］. World Wide Web， 2019， 22（5）： 1913-1933. 10.1007/s11280-018-0640-8
6	HAWWASH B， NASRAOUI O. From Tweets to Stories： using Stream-Dashboard to weave the Twitter data stream into dynamic cluster models ［C］// Proceedings of the 2014 3rd International Workshop on Big Data， Streams and Heterogeneous Source Mining： Algorithms， Systems， Programming Models and Applications. New York： ACM， 2014： 182-197. 10.18297/etd/587
7	HUA T， ZHANG X C， WANG W， et al. Automatical storyline generation with help from Twitter ［C］// Proceedings of the 25th ACM International Conference on Information and Knowledge Management. New York： ACM， 2016： 2383-2388. 10.1145/2983323.2983698
8	MAKKONEN J. Investigations on event evolution on TDT ［C］// Proceedings of the HLT-NAACL 2003 Student Research Workshop. Stroudsburg： ACL， 2003： 43-48. 10.3115/1073416.1073424
9	NALLAPATI R， FENG A， PENG F C， et al. Event threading within news topics ［C］// Proceedings of the 2004 13th ACM International Conference on Information and Knowledge Management. New York： ACM， 2004： 446-453. 10.1145/1031171.1031258
10	LABAN P， HEARST M A. newsLens： building and visualizing long-ranging news stories ［C］// Proceedings of the 2017 Events and Stories in the News Workshop. Stroudsburg： ACL， 2017： 1-9. 10.18653/v1/w17-2701
11	佘玉轩，熊赟.基于贝叶斯网络的故事线挖掘算法［J］.计算机工程，2018，44（3）：55-59.（SHE Y X， XIONG Y. Storyline mining algorithm based on Bayesian network ［J］. Computer Engineering， 2018， 2018， 44（3）： 55-59.）. 10.3969/j.issn.1000-3428.2018.03.009
12	ZHOU D Y， XU H Y， DAI X Y， et al. Unsupervised storyline extraction from news articles ［C］// Proceedings of the 2016 25th International Joint Conference on Artificial Intelligence. New York： ACM， 2016： 3014-3020.
13	WANG D D， LI T， OGIHARA M. Generating pictorial storylines via minimum-weight connected dominating set approximation in multi-view graphs ［C］// Proceedings of the 2012 26th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2012： 683-689. 5074
14	CAI H Y， HUANG Z， SRIVASTAVA D， et al. Indexing evolving events from tweet streams ［J］. IEEE Transactions on Knowledge and Data Engineering， 2015， 27（11）： 3001-3015. 10.1109/tkde.2015.2445773
15	LIN C， LIN C， LI J X， et al. Generating event storylines from microblogs ［C］// Proceedings of the 2012 21st ACM International Conference on Information and Knowledge Management. New York： ACM， 2012： 175-184. 10.1145/2396761.2396787
16	李培，翁伟，林琛.中文微博故事线生成方法［J］.中文信息学报，2016，30（3）：143-151. 10.1007/978-3-319-41003-6_9
	LI P， WENG W， LIN C. Method for generating microblogs storylines ［J］. Journal of Chinese Information Processing， 2016， 30（3）： 143-151. 10.1007/978-3-319-41003-6_9
17	WU Z H， PAN S R， CHEN F W， et al. A comprehensive survey on graph neural networks ［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021， 32（1）： 4-24. 10.1109/tnnls.2020.2978386
18	CHEN C C， CHEN Y T， CHEN M C. An aging theory for event life-cycle modeling ［J］. IEEE Transactions on Systems， Man， and Cybernetics — Part A： Systems and Humans， 2007， 37（2）： 237-248. 10.1109/tsmca.2006.886370
19	KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks ［EB/OL］. ［2020-10-10］. .

数据集	标题	起止日期	记录数
Dataset1	疫苗事件	2018.07.01—2019.09.01	73 614
Dataset2	中兴事件	2018.04.16—2018.07.14	45 113

数据集	标题	起止日期	记录数
Dataset1	疫苗事件	2018.07.01—2019.09.01	73 614
Dataset2	中兴事件	2018.04.16—2018.07.14	45 113

方法	Precision	Recall	F1	方法	Precision	Recall	F1
贝叶斯模型	0.75	0.45	0.55	故事森林	0.74	0.51	0.56
斯坦纳树	0.65	0.66	0.63	本文方法	0.86	0.84	0.83

方法	Precision	Recall	F1	方法	Precision	Recall	F1
贝叶斯模型	0.75	0.45	0.55	故事森林	0.74	0.51	0.56
斯坦纳树	0.65	0.66	0.63	本文方法	0.86	0.84	0.83

方法	Precision	Recall	F1	方法	Precision	Recall	F1
贝叶斯模型	0.46	0.57	0.51	故事森林	0.41	0.56	0.48
斯坦纳树	0.50	0.68	0.58	本文方法	0.85	0.60	0.70

Storyline extraction method from Weibo news based on graph convolutional network

基于图卷积网络的微博新闻故事线抽取方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 19

Related Articles 15

Recommended Articles

Metrics

方法	Dataset1	Dataset2	方法	Dataset1	Dataset2
故事时间线	0.31	0.30	故事森林	0.47	0.33
斯坦纳树	0.41	0.39	本文方法	0.64	0.42

[1]	Guixiang XUE, Hui WANG, Weifeng ZHOU, Yu LIU, Yan LI. Port traffic flow prediction based on knowledge graph and spatio-temporal diffusion graph convolutional network [J]. Journal of Computer Applications, 2024, 44(9): 2952-2957.
[2]	Chuanlin PANG, Rui TANG, Ruizhi ZHANG, Chuan LIU, Jia LIU, Shibo YUE. Distributed power allocation algorithm based on graph convolutional network for D2D communication systems [J]. Journal of Computer Applications, 2024, 44(9): 2855-2862.
[3]	Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072.
[4]	Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861.
[5]	Shibin LI, Jun GONG, Shengjun TANG. Semi-supervised heterophilic graph representation learning model based on Graph Transformer [J]. Journal of Computer Applications, 2024, 44(6): 1816-1823.
[6]	Longtao GAO, Nana LI. Aspect sentiment triplet extraction based on aspect-aware attention enhancement [J]. Journal of Computer Applications, 2024, 44(4): 1049-1057.
[7]	Xianfeng YANG, Yilei TANG, Ziqiang LI. Aspect-level sentiment analysis model based on alternating‑attention mechanism and graph convolutional network [J]. Journal of Computer Applications, 2024, 44(4): 1058-1064.
[8]	Tao SUN, Zhangtian DUAN, Haonan ZHU, Peihao GUO, Heli SUN. Social event recommendation method based on unexpectedness metric [J]. Journal of Computer Applications, 2024, 44(3): 760-766.
[9]	Yuanyuan MA, Leilei XIE, Nan DONG, Na LIU. Opinion propagation model considering user initiative and mobility [J]. Journal of Computer Applications, 2024, 44(2): 619-627.
[10]	Kaitian WANG, Qing YE, Chunlei CHENG. Classification method for traditional Chinese medicine electronic medical records based on heterogeneous graph representation [J]. Journal of Computer Applications, 2024, 44(2): 411-417.
[11]	Zucheng WU, Xiaojun WU, Tianyang XU. Image-text retrieval model based on intra-modal fine-grained feature relationship extraction [J]. Journal of Computer Applications, 2024, 44(12): 3776-3783.
[12]	Rui GAO, Xuebin CHEN, Zucuan ZHANG. Dynamic social network privacy publishing method for partial graph updating [J]. Journal of Computer Applications, 2024, 44(12): 3831-3838.
[13]	Xinrong HU, Jingxue CHEN, Zijian HUANG, Bangchao WANG, Xun YAO, Junping LIU, Qiang ZHU, Jie YANG. Graph convolution network-based masked data augmentation [J]. Journal of Computer Applications, 2024, 44(11): 3335-3344.
[14]	Shiliang LIU, Yi WANG, Yinglong MA. Non-overlapping community detection with imbalanced community sizes [J]. Journal of Computer Applications, 2024, 44(11): 3396-3402.
[15]	Nengqiang XIANG, Xiaofei ZHU, Zhaoze GAO. Information diffusion prediction model of prototype-aware dual-channel graph convolutional neural network [J]. Journal of Computer Applications, 2024, 44(10): 3260-3266.