進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0906202011052300
論文名稱(中文) 經由圖神經網路增強序列學習及其應用於時間序列與社群媒體預測
論文名稱(英文) Graph Neural Network-enhanced Sequential Learning for Time Series and Social Media Prediction
校院名稱 成功大學
系所名稱(中) 統計學系
系所名稱(英) Department of Statistics
學年度 108
學期 2
出版年 109
研究生(中文) 呂易儒
研究生(英文) Yi-Ju Lu
學號 R26074056
學位類別 碩士
語文別 中文
論文頁數 45頁
口試委員 指導教授-李政德
口試委員-高宏宇
口試委員-李家岩
口試委員-莊坤達
中文關鍵字 圖卷積網路  時間序列  假新聞偵測  深度學習 
英文關鍵字 Graph Convolution Network  time series  fake news detection  deeping learning 
學科別分類
中文摘要 近幾年,由於圖卷積網路(Graph Convolution Network,GCN) 的出現,被大量應用在圖形(graph) 資料上,能夠不單使用本身的資訊,也能同時考慮在圖形中與自己相連點資訊,對於模型的學習提供更多的訊息,例如社群網路、通訊網路和蛋白質網路,在過去的研究都有突出的模型表現。然而,圖卷積網路(GCN) 卻較少運用在序列資料的處理上。關於序列資料,一般常見的為時間序列,而由於科技的進步,使得感測(sensors) 廣泛運用在城市中,例如空氣品質監控、腳踏車流量管理、交通流量控管,同時也獲取許多感測器的序列型態紀錄,因此,對於利用時間序列資料的預測更為受到重視且可行。又由於網際網路的盛行,網路使用者在社群媒體平台頻繁的互動,資訊不斷的在網路上散布,同時也就產生了社群媒體的序列,例如轉傳文章貼文的序列,而近幾年來在社群網路上,假新聞的議題受到極大的關注,文章貼文文字序列以及轉傳使用者序列或許隱含著假新聞的資訊。因此,本研究將結合圖卷積網路(GCN) 的優點和深度學習的架構,針對兩種不同序列型態的資訊: 時間序列與社群媒體序列,分別根據其形態建立兩種模型,Attention-adjusted Graph Spatio-Temporal Network(AGSTN) 與Graph-aware Co-Attention Network(GCAN)模型來進行序列表示學習以及預測。
針對AGSTN 模型,利用多層圖卷積網路(Multi-Graph Convolutional Network,MGCN) 來學習感測器間隨著時間變化的空間與時間相關性,以及利用注意力(attention) 機制來進行調整,使得預測值在隨著時間變動幅度不定的情況下,能夠更趨於合適的範圍預測數值。模型應用在三種資料集上,分別為空氣品質序列、腳踏車需求序列、交通序列,皆有顯著的預測表現且優於過去的模型;針對GCAN模型,將社群媒體序列應用於假新聞偵測問題上,利用短篇文章貼文的文字序列和轉傳使用者序列,以較貼近真實的情況下進行假新聞的預測,利用圖卷積網路(GCN)學習轉傳使用者間的相互關係,結合深度學習(deep learning) 的序列模型進行預測,且藉由雙重共同注意力(dual co-attention)機制針對預測為假新聞的原因進行解釋,實驗於兩個真實的推(Twitter) 資料集上,模型表現皆優於過去的模型。
英文摘要 In recent years, due to the emergence of the Graph Convolution Network (GCN), it had been widely used in graph data, and can not only use its own information, but also consider the nodes connected to itself in the graph to provide more information for model learning. However, GCN is rarely used in the sequential data. We hope that we can utilize the advantage of GCN to imply on two types of sequential data, time series data of sensor and retweet sequence in social media to improve the forecasting performance.For time series data of sensor, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving spatio-temporal correlation between sensors. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods. For retweet sequence in social media, we focus on dealing with the fake news detection problem. We develop a novel GNN-based model, Graph-aware Co-Attention Network (GCAN) to achieve the goal. Given the source short-text tweet and its retweet users sequence without text comment, we aim at predicting whether it is fake or not, and generating explanation by
highlighting the evidences on suspicious retweeters and the words they concern. Experiments on real tweet datasets exhibit that GCAN can significantly outperform the state-of-the-art methods by 16% in accuracy on average, and produce reasonable explanation.
論文目次 摘要i
英文延伸摘要ii
誌謝vii
目錄viii
表格x
圖片xi
第一章. 緒論1
1.1 研究背景與動機1
1.2 研究問題2
1.3 潛在應用2
1.4 研究挑戰3
1.5 論文貢獻4
第二章. 相關研究5
2.1 感測器時間序列預測任務5
2.2 社群媒體序列預測任務7
第三章. 感測器時間序列預測9
3.1 問題定義9
3.2 研究架構與方法流程10
3.3 特徵萃取11
3.4 特徵表示學習12
3.4.1 圖形建構與特徵表示學習12
3.4.2 時間序列特徵表示學習13
3.5 預測模型14
3.6 實驗評估15
3.6.1 資料集與實驗設15
3.6.2 實驗結果17
第四章. 社群媒體序列預測26
4.1 問題定義26
4.2 研究架構與方法流程27
4.3 特徵萃取27
4.4 特徵表示學習28
4.4.1 文章貼文特徵表示學習29
4.4.2 使用者轉傳序列特徵表示學習29
4.4.3 序列圖形化特徵表示學習30
4.5 預測模型31
4.6 實驗評估33
4.6.1 資料集與實驗設置33
4.6.2 實驗結果35
第五章. 結論與未來展望40
參考文獻42
參考文獻 [1] Ricardo A. BaezaYates and Berthier RibeiroNeto.
Modern Information Retrieval.AddisonWesley Longman Publishing Co., Inc., USA, 1999.
[2] Carlos Castillo, Marcelo Mendoza, and Barbara Poblete. Information credibility on twitter. In Proceedings of the 20th International Conference on World Wide Web, WWW ’11, pages 675–684, 2011.
[3] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling, 2014.
[4] Zulong Diao, Xin Wang, Dafang Zhang, Yingru Liu, Kun Xie, and Shaoyao He. Dynamic spatialtemporal graph convolutional neural networks for traffic forecasting. In
Proceedings of The ThirtyThird AAAI Conference on Artificial Intelligence, AAAI ’19,pages 890–897, 2019.
[5] Xu Geng, Yaguang Li, Leye Wang, Lingyu Zhang, Qiang Yang, Jieping Ye, and Yan Liu.Spatiotemporal multigraph
convolution network for ridehailing demand forecasting.
In Proceedings of the AAAI Conference on Artificial Intelligence, pages 3656–3663,2019.
[6] Chuan Guo, Juan Cao, Xueyao Zhang, Kai Shu, and Miao Yu. Exploiting emotions for fake news detection on social media. CoRR, abs/1903.01728, 2019.
[7] Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. Attention based spatialtemporal graph convolutional networks for traffic flow forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 33:922–929, 07 2019.
[8] Sepp Hochreiter and Jürgen Schmidhuber. Long shortterm
memory. Neural Comput.,9(8):1735–1780, 1997.
[9] Benjamin Horne and Sibel Adali. This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news. In Proceedings of AAAI International Conference on Web and Social Media, pages 759–766,2017.
[10] Norden E. Huang, Zheng Shen, Steven R. Long, Manli C. Wu, Hsing H. Shih, Quanan Zheng, NaiChyuan Yen, Chi Chao Tung, and Henry H. Liu. The empirical mode decomposition and the hilbert spectrum for nonlinear and nonstationary
time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971):903–995, 1998.
[11] Pierre Hulot, Daniel Aloise, and Sanjay Dominik Jena. Towards stationlevel demand prediction for effective rebalancing in bikesharing systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '18, pages 378–386, 2018.
[12] Thomas N. Kipf and Max Welling. Semisupervised classification with graph convolutional networks. CoRR, abs/1609.02907, 2016.
[13] Haewoon Kwak, Changhyun Lee, Hosung Park, and Sue Moon. What is twitter, a social network or a news media? In Proceedings of the 19th International Conference on World Wide Web, WWW ’10, pages 591–600, 2010.
[14] Sejeong Kwon, Meeyoung Cha, and Kyomin Jung. Rumor detection over varying time windows. PLOS ONE, 12(1):1–19, 2017.
[15] Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. Diffusion convolutional recurrent neural network: Datadriven traffic forecasting,. In Proceedings of International Conference on Learning Representations, ICLR ’17, 2017.
[16] Youru Li, Zhenfeng Zhu, Deqiang Kong, Meixiang Xu, and Yao Zhao. Learning heterogeneous spatialtemporal representation for bikesharing demand prediction. In Proceedings of The ThirtyThird AAAI Conference on Artificial Intelligence, AAAI ’19, pages 1004–1011, 2019.
[17] Yuxuan Liang, Songyu Ke, Junbo Zhang, Xiuwen Yi, and Yu Zheng. Geoman: Multilevel attention networks for geosensory time series prediction. In Proceedings of the
TwentySeventh International Joint Conference on Artificial Intelligence, IJCAI ’18, pages 3428–3434. International Joint Conferences on Artificial Intelligence Organization,
2018.
[18] Yang Liu and YiFang Wu. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks. In AAAI Conference on Artificial Intelligence, pages 254–261, 2018.
[19] Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. Hierarchical questionimage coattention for visual question answering. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16, pages 289–297, 2016.
[20] Zhipeng Luo, Jianqiang Huang, Ke Hu, Xue Li, and Peng Zhang. Accuair: Winning solution to air quality prediction for kdd cup 2018. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’19, pages 1842–1850, 2019.
[21] Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J. Jansen, Kam Fai Wong, and Meeyoung Cha. Detecting rumors from microblogs with recurrent neural networks. IJCAI International Joint Conference on Artificial Intelligence, pages 3818–3824, 2016.
[22] Jing Ma, Wei Gao, Zhongyu Wei, Yueming Lu, and KamFai
Wong. Detect rumors using time series of social context information on microblogging websites. In Proceedings
of the 24th ACM International on Conference on Information and Knowledge Management, CIKM ’15, pages 1751–1754, 2015.
[23] Jing Ma, Wei Gao, and Kam Fai Wong. Detect rumors in microblog posts using propagation structure via kernel learning. In ACL 2017 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, pages 708–717, 2017.
24] Jing Ma, Wei Gao, and KamFai Wong. Rumor detection on twitter with treestructured recursive neural networks. In Proceedings of the 56th Annual Meeting of the Association
for Computational Linguistics, pages 1980–1989, 2018.
[25] Kashyap Popat. Assessing the credibility of claims on the web. In Proceedings of the 26th International Conference on World Wide Web Companion, WWW ’17 Companion,
pages 735–739, 2017.
[26] Martin Potthast, Johannes Kiesel, Kevin Reinartz, Janek Bevendorff, and Benno Stein.A stylometric inquiry into hyperpartisan and fake news. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL ’18, pages 231–240, 2018.
[27] Hannah Rashkin, Eunsol Choi, Jin Yea Jang, Svitlana Volkova, and Yejin Choi. Truth of varying shades: Analyzing language in fake news and political factchecking. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2931–2937, 2017.
[28] Julio C. S. Reis, André Correia, Fabrício Murai, Adriano Veloso, and Fabrício Benevenuto.Explainable machine learning for fake news detection. In Proceedings of the
10th ACM Conference on Web Science, WebSci ’19, pages 17–26, 2019.
[29] Natali Ruchansky, Sungyong Seo, and Yan Liu. Csi: A hybrid deep model for fake news detection. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM ’17, pages 797–806, 2017.
[30] Justin Sampson, Fred Morstatter, Liang Wu, and Huan Liu. Leveraging the implicit structure within social media for emergent rumor detection. In Proceedings of the 25th
ACM International on Conference on Information and Knowledge Management, CIKM ’16, pages 2377–2382, 2016.
[31] Kai Shu, Limeng Cui, Suhang Wang, Dongwon Lee, and Huan Liu. defend: Explainable fake news detection. In Proceedings of the 25th ACM SIGKDD International Conference
on Knowledge Discovery & Data Mining, KDD ’19, pages 395–405, 2019.
[32] Kai Shu, Xinyi Zhou, Suhang Wang, Reza Zafarani, and Huan Liu. The role of user profile for fake news detection. CoRR, abs/1904.13355, 2019.
[33] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 27, pages 3104–3112, 2014.
[34] Yaqing Wang, Fenglong Ma, Zhiwei Jin, Ye Yuan, Guangxu Xun, Kishlay Jha, Lu Su, and Jing Gao. Eann: Event adversarial neural networks for multimodal fake news detection. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &; Data Mining, KDD ’18, pages 849–857, 2018.
[35] Yuankai Wu and Huachun Tan. Shortterm traffic flow forecasting with spatialtemporal correlation in a hybrid deep learning framework, 2016.
[36] Fan Yang, Yang Liu, Xiaohui Yu, and Min Yang. Automatic detection of rumor on sina weibo. In Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics, MDS ’12, 2012.
[37] Yang Yang, Lei Zheng, Jiawei Zhang, Qingcai Cui, Zhoujun Li, and Philip S. Yu. Ticnn:Convolutional neural networks for fake news detection, 2018.
[38] Xiuwen Yi, Junbo Zhang, Zhaoyuan Wang, Tianrui Li, and Yu Zheng. Deep distributed fusion network for air quality prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '18, pages 965–973, 2018.
[39] Bing Yu, Haoteng Yin, and Zhanxing Zhu. Spatiotemporal
graph convolutional neural network: A deep learning framework for traffic forecasting. In Proceedings of the
TwentySeventh International Joint Conference on Artificial Intelligence, IJCAI ’18,2018.
[40] Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, and Xiuwen Yi. Dnnbased prediction model for spatiotemporal
data. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPACIAL ' 16, 2016.
[41] Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi, and Tianrui Li. Predicting citywide crowd flows using deep spatiotemporal residual networks. Artificial Intelligence, 259:147 – 166, 2018.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-01-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw