News event prediction by trigger evolution graph and event segment

doi:10.23919/JSEE.2023.000083

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (3): 615-626.doi: 10.23919/JSEE.2023.000083

• COMPLEX SYSTEMS THEORY AND PRACTICE • Previous Articles

News event prediction by trigger evolution graph and event segment

Yaru ZHANG¹^,²(), Xijin TANG¹^,²^,*()

¹ Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China
² University of Chinese Academy of Sciences, Beijing 100049, China

Received:2022-08-31 Online:2023-06-15 Published:2023-06-30
Contact: Xijin TANG E-mail:zhangyaru@amss.ac.cn;xjtang@iss.ac.cn
About author:
ZHANG Yaru was born in 1994. She is currently working towards her Ph.D. degree in Academy of Mathematics and Systems Science, Chinese Academy of Sciences. Her research interests include natural language processing, social network analysis and knowledge management. E-mail: zhangyaru@amss.ac.cn

TANG Xijin was born in 1967. She is a full professor in Academy of Mathematics and Systems Science, Chinese Academy of Sciences (CAS). She received her B.E. degree in computer science and engineering from Zhejiang University, M.E. degree in management science and engineering from University of Science and Technology of China and Ph.D. degree from Institute of Systems Science, CAS. During her early system research and practice, she developed several decision support systems for water resources management, weapon system evaluation, e-commerce evaluation, etc. Now she is the secretary general of Systems Engineering Society of China. She also serves as vice president and secretary general of International Society for Knowledge and Systems Sciences. Her recent interests are meta-synthesis and advanced modeling, social network analysis and knowledge management, opinion mining and opinion dynamics, opinion big data and societal risk perception. E-mail: xjtang@iss.ac.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (71731002; 71971190)

Abstract

Abstract:

Event prediction aims to predict the most possible following event given a chain of closely related context events. Previous methods based on event pairs or the entire event chain may ignore much structural and semantic information. Current datasets for event prediction, naturally, can be used for supervised learning. Event chains are either from document-level procedural action flow, or from news sequences under the same column. This paper leverages graph structure knowledge of event triggers and event segment information for event prediction with general news corpus, and adopts the standard multiple choice narrative cloze task evaluation. The topic model is utilized to extract event chains from the news corpus to deal with training data bottleneck. Based on trigger-guided structural relations in the event chains, we construct trigger evolution graph, and trigger representations are learned through graph convolutional neural network and the novel neighbor selection strategy. Then there are features of two levels for each event, namely, text level semantic feature and trigger level structural feature. We design the attention mechanism to learn the features of event segments derived in term of event major subjects, and integrate relevance between event segments and the candidate event. The most possible next event is picked by the relevance. Experimental results on the real-world news corpus verify the effectiveness of the proposed model.

Key words: event prediction, trigger evolution graph, event segment

Yaru ZHANG, Xijin TANG. News event prediction by trigger evolution graph and event segment[J]. Journal of Systems Engineering and Electronics, 2023, 34(3): 615-626.

Figures/Tables 6

Fig 1

Fig 2

Fig 3

Table 1

Table 2

Table 3

References 41

1	ALLAN J, PAPKA R, LAVRENKO V On-line new event detection and tracking. Proc. of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1998, 37- 45.
2	TONG M H, XU B, WANG S, et al Improving event detection via open-domain trigger knowledge. Proc. of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, 5887- 5897.
3	LV J W, ZHANG Z Q, JIN L, et al HGEED: hierarchical graph enhanced event detection. Neurocomputing, 2021, 453, 141- 150. doi: 10.1016/j.neucom.2021.04.087
4	YANG S, FENG D W, QIAO L B, et al Exploring pre-trained language models for event extraction and generation. Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, 5284- 5294.
5	LIU X, HUANG H Y, ZHANG Y Open domain event extraction using neural latent variable models. Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, 2860- 2871.
6	WANG R, ZHOU D Y, HE Y L Open event extraction from online text using a generative adversarial network. Proc. of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019, 282- 291.
7	SUN W J, WANG Y H, GAO Y Q, et al Comprehensive event storyline generation from microblogs. Proc. of the ACM Multimedia Asia, 2019, 1- 7.
8	XU N, TANG X J Evolution analysis of societal risk events by risk maps. Journal of Systems Science and Systems Engineering, 2020, 29 (4): 454- 467. doi: 10.1007/s11518-020-5458-0
9	AMMANABROLU P, CHEUNG W, BRONIEC W, et al Automated storytelling via causal, commonsense plot ordering. Proc. of the AAAI Conference on Artificial Intelligence, 2021, 35 (7): 5859- 5867. doi: 10.1609/aaai.v35i7.16733
10	NING Q, SUBRAMANIAN S, ROTH D An improved neural baseline for temporal relation extraction. Proc. of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019, 6203- 6209.
11	LEI L, REN X G, FRANCISCUS N, et al Event prediction based on causality reasoning. Proc. of the Asian Conference on Intelligent Information and Database Systems, 2019, 165- 176.
12	ZHAO L Event prediction in the big data era: a systematic survey. ACM Computing Surveys, 2021, 54 (5): 1- 37.
13	WANG J, RAO C J, GOH M, et al Risk assessment of coronary heart disease based on cloud-random forest. Artificial Intelligence Review, 2022, 56, 203- 232.
14	GRANROTH-WILDING M, CLARK S What happens next? Event prediction using a compositional neural network model. Proc. of the 30th AAAI Conference on Artificial Intelligence, 2016, 2727- 2733.
15	DENG S G J, NING Y. A survey on societal event forecasting with deep learning. DOI: 10.48550/arXiv.2112.06345.
16	TAYMOURI F, LA ROSA M, ERFANI S, et al Predictive business process monitoring via generative adversarial nets: the case of next event prediction. Proc. of the International Conference on Business Process Management, 2020, 237- 256.
17	AGGARWAL K, THEOCHAROUS G, RAO A B Dynamic clustering with discrete time event prediction. Proc. of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020, 1501- 1504.
18	LUO W J, ZHANG H, YANG X D, et al Dynamic heterogeneous graph neural network for real-time event prediction. Proc. of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, 3213- 3223.
19	DENG S G J, RANGWALA H Z F, NING Y Dynamic knowledge graph based multi-event forecasting. Proc. of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, 1585- 1595.
20	HEINRICH K, ZSCHECH P, JANIESCH C, et al Process data properties matter: introducing gated convolutional neural networks (GCNN) and key-value-predict attention networks (KVP) for next event prediction with deep learning. Decision Support Systems, 2021, 143, 113494. doi: 10.1016/j.dss.2021.113494
21	DENG S G J, RANGWALA H Z F, NING Y Understanding event predictions via contextualized multilevel feature learning. Proc. of the 30th ACM International Conference on Information & Knowledge Management, 2021, 342- 351.
22	HU L M, LI J Z, NIE L Q, et al What happens next? Future subevent prediction using contextual hierarchical LSTM. Proc. of the 31st AAAI Conference on Artificial Intelligence, 2017, 3450- 3456.
23	SU Z C, JIANG J L Hierarchical gated recurrent unit with semantic attention for event prediction. Future Internet, 2020, 12 (2): 39. doi: 10.3390/fi12020039
24	HU L M, YU S Q, WU B, et al A neural model for joint event detection and prediction. Neurocomputing, 2020, 407, 376- 384. doi: 10.1016/j.neucom.2020.05.023
25	WANG Z Q, ZHANG Y, CHANG C Y Integrating order information and event relation for script event prediction. Proc. of the Conference on Empirical Methods in Natural Language Processing, 2017, 57- 67.
26	LI Z Y, DING X L, LIU T Constructing narrative event evolutionary graph for script event prediction. Proc. of the 27th International Joint Conference on Artificial Intelligence, 2018, 4201- 4207.
27	YANG Y Y, WEI Z Y, CHEN Q, et al Using external knowledge for financial event prediction based on graph neural networks. Proc. of the 28th ACM International Conference on Information and Knowledge Management, 2019, 2161- 2164.
28	MAO Q R, LI X, PENG H, et al Event prediction based on evolutionary event ontology knowledge. Future Generation Computer Systems, 2021, 115, 76- 89. doi: 10.1016/j.future.2020.07.041
29	LV S W, QIAN W H, HUANG L T, et al SAM-net: integrating event-level and chain-level attentions to predict what happens next. Proc. of the AAAI Conference on Artificial Intelligence, 2019, 6802- 6809. doi: 10.1609/aaai.v33i01.33016802
30	ZHOU B, CHEN Y B, LIU K, et al Multi-task self-supervised learning for script event prediction. Proc. of the 30th ACM International Conference on Information & Knowledge Management, 2021, 3662- 3666.
31	WANG L H, YUE J W, GUO S, et al Multi-level connection enhanced representation learning for script event prediction. Proc. of the Web Conference, 2021, 3524- 3533.
32	XU J, WANG H F, NIU Z Y, et al Conversational graph grounded policy learning for open-domain conversation generation. Proc. of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, 1835- 1845.
33	WU S W, SUN F, ZHANG W T, et al Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 2022, 55 (5): 1- 37.
34	YASUNAGA M, REN H Y, BOSSELUT A, et al QA-GNN: reasoning with language models and knowledge graphs for question answering. Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, 535- 546.
35	LIU Y, AO X, QIN Z D, et al Pick and choose: a GNN-based imbalanced learning approach for fraud detection. Proc. of the Web Conference, 2021, 3168- 3177.
36	JIANG W W, LUO J Y Graph neural network for traffic forecasting: a survey. Expert Systems with Applications, 2022, 117921.
37	PENG H, LI J X, GONG Q R, et al Fine-grained event categorization with heterogeneous graph convolutional networks. Proc. of the 28th International Joint Conference on Artificial Intelligence, 2019, 3238- 3245.
38	LI M L, LI S, WANG Z H L, et al. Future is not one-dimensional: graph modeling based complex event schema induction for event prediction. https://doi.org/10.48550/arXiv:2104.06344,2021.
39	RADINSKY K, DAVIDOVICH S, MARKOVITCH S Learning causality for news events prediction. Proc. of the 21st International Conference on World Wide Web, 2012, 909- 918.
40	RADINSKY K, HORVITZ E Mining the web to predict future events. Proc. of the 6th ACM International Conference on Web Search and Data Mining, 2013, 255- 264.
41	CHAMBERS N, JURAFSKY D Unsupervised learning of narrative event chains. Proc. of the 46th Annual Meeting of the Association for Computational Linguistics, 2008, 789- 797.

Name	Number
News item	37 160
$ n $	9
$ k $	5
Event chain	3 281
Node	2 721
Edge	21 298

Model	Accuracy
Random	20.00
GGNN model	48.62
PairLSTM	49.23
Event pair based model+Attention_1	50.77
Event pair based model+Attention	50.77
Event pair based model+Attention+trigger representation	52.92
Event segment based model	54.77
Event segment based model+trigger representation	55.38
Event segment based model+trigger representation with general update way	52.62
Event segment based model+trigger representation-weighted loss	54.46

Model	Accuracy
PMI*	30.52
Event-Comp*	49.57
PairLSTM*	50.83
PairLSTM+trigger representation with general update way	51.13
PairLSTM+trigger representation	51.52

News event prediction by trigger evolution graph and event segment

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 6

References 41

Related Articles 0

Recommended Articles

Metrics

Comments