ABSTRACT
Spatial event forecasting from social media is an important problem but encounters critical challenges, such as dynamic patterns of features (keywords) and geographic heterogeneity (e.g., spatial correlations, imbalanced samples, and different populations in different locations). Most existing approaches (e.g., LASSO regression, dynamic query expansion, and burst detection) are designed to address some of these challenges, but not all of them. This paper proposes a novel multi-task learning framework which aims to concurrently address all the challenges. Specifically, given a collection of locations (e.g., cities), we propose to build forecasting models for all locations simultaneously by extracting and utilizing appropriate shared information that effectively increases the sample size for each location, thus improving the forecasting performance. We combine both static features derived from a predefined vocabulary by domain experts and dynamic features generated from dynamic query expansion in a multi-task feature learning framework; we investigate different strategies to balance homogeneity and diversity between static and dynamic terms. Efficient algorithms based on Iterative Group Hard Thresholding are developed to achieve efficient and effective model training and prediction. Extensive experimental evaluations on Twitter data from four different countries in Latin America demonstrated the effectiveness of our proposed approach.
Supplemental Material
- J. Abernethy, F. Bach, T. Evgeniou, and J.-P. Vert. A new approach to collaborative filtering: Operator estimation with spectral regularization. The Journal of Machine Learning Research, 10:803--826, 2009. Google ScholarDigital Library
- H. Achrekar, A. Gandhe, R. Lazarus, S.-H. Yu, and B. Liu. Predicting flu trends using Twitter data. In IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pages 702--707, 2011.Google ScholarCross Ref
- C. C. Aggarwal and K. Subbian. Event detection in social streams. In SDM, pages 624--635, 2012.Google ScholarCross Ref
- R. Ando and T. Zhang. A framework for learning predictive structures from multiple tasks and unlabeled data. Journal of Machine Learning Research, 6:1817--1853, 2005. Google ScholarDigital Library
- A. Argyriou, T. Evgeniou, and M. Pontil. Multi-task feature learning. Advances in neural information processing systems, 19:41, 2007.Google Scholar
- M. Arias, A. Arratia, and R. Xuriguera. Forecasting with Twitter data. ACM Transactions on Intelligent Systems and Technology (TIST), 5(1):8, 2013. Google ScholarDigital Library
- A. Beck and M. Teboulle. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, 2(1):183--202, 2009. Google ScholarDigital Library
- T. Blumensath and M. E. Davies. Iterative hard thresholding for compressed sensing. Applied and Computational Harmonic Analysis, 27(3):265--274, 2009.Google ScholarCross Ref
- J. Bollen, H. Mao, and X. Zeng. Twitter mood predicts the stock market. Journal of Computational Science, 2(1):1--8, 2011.Google ScholarCross Ref
- R. Caruana. Multitask learning. Machine Learning, 28(1):41--75, 1997. Google ScholarDigital Library
- J. Chen, J. Liu, and J. Ye. Learning incoherent sparse and low-rank patterns from multiple tasks. ACM Transactions on Knowledge Discovery from Data (TKDD), 5(4):22, 2012. Google ScholarDigital Library
- T. Evgeniou and M. Pontil. Regularized multi-task learning. In KDD 2004, pages 109--117. ACM, 2004. Google ScholarDigital Library
- M. S. Gerber. Predicting crime using Twitter and kernel density estimation. Decision Support Systems, 61:115--125, 2014.Google ScholarCross Ref
- P. Gong, C. Zhang, Z. Lu, J. Z. Huang, and J. Ye. A general iterative shrinkage and thresholding algorithm for non-convex regularized optimization problems. In ICML, volume 28, page 37. NIH Public Access, 2013.Google Scholar
- J. He, W. Shen, P. Divakaruni, L. Wynter, and R. Lawrence. Improving traffic prediction with tweet semantics. In IJCAI, pages 1387--1393, 2013. Google ScholarDigital Library
- S. Ji and J. Ye. An accelerated gradient method for trace norm minimization. In ICML 2009, pages 457--464. ACM, 2009. Google ScholarDigital Library
- F. Jin, R. P. Khandpur, N. Self, E. Dougherty, S. Guo, F. Chen, B. A. Prakash, and N. Ramakrishnan. Modeling mass protest adoption in social network communities using geometric brownian motion. In KDD 2014, pages 1660--1669. ACM, 2014. Google ScholarDigital Library
- F. Jin, W. Wang, L. Zhao, E. Dougherty, Y. Cao, C.-T. Lu, and N. Ramakrishnan. Misinformation propagation in the age of twitter. Computer, (12):90--94, 2014. Google ScholarDigital Library
- T. Lappas, M. R. Vieira, D. Gunopulos, and V. J. Tsotras. On the spatiotemporal burstiness of terms. VLDB, 5(9):836--847, 2012. Google ScholarDigital Library
- MITRE. http://www.mitre.org/.Google Scholar
- B. O'Connor, R. Balasubramanyan, B. R. Routledge, and N. A. Smith. From tweets to polls: Linking text sentiment to public opinion time series. ICWSM, 11:122--129, 2010.Google ScholarCross Ref
- N. Ramakrishnan, P. Butler, S. Muthiah, N. Self, R. Khandpur, P. Saraf, W. Wang, J. Cadena, A. Vullikanti, G. Korkmaz, et al. 'beating the news' with embers: forecasting civil unrest using open source indicators.Google Scholar
- J. Ritterman, M. Osborne, and E. Klein. Using prediction markets and Twitter to predict a swine flu pandemic. In 1st international workshop on mining social media, volume 9, 2009.Google Scholar
- T. Sakaki, M. Okazaki, and Y. Matsuo. Earthquake shakes Twitter users: real-time event detection by social sensors. In WWW, pages 851--860, 2010. Google ScholarDigital Library
- E. Schubert, M. Weiler, and H.-P. Kriegel. Signitrend: scalable detection of emerging topics in textual streams by hashed significance thresholds. In KDD 2014, pages 871--880. ACM, 2014. Google ScholarDigital Library
- A. Signorini, A. M. Segre, and P. M. Polgreen. The use of Twitter to track levels of disease activity and public concern in the us during the influenza an H1N1 pandemic. PloS one, 6(5):e19467, 2011.Google ScholarCross Ref
- S. Thrun and J. O'Sullivan. Clustering learning tasks and the selective cross-task transfer of knowledge. Learning to learn, pages 181--209, 1998. Google ScholarDigital Library
- R. Tibshirani. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological), pages 267--288, 1996.Google Scholar
- A. Tumasjan, T. O. Sprenger, P. G. Sandner, and I. M. Welpe. Predicting elections with Twitter: What 140 characters reveal about political sentiment. ICWSM, 10:178--185, 2010.Google ScholarCross Ref
- X. Wang, D. E. Brown, and M. S. Gerber. Spatio-temporal modeling of criminal incidents using geographic, demographic, and Twitter-derived information. In ISI, pages 36--41, 2012.Google ScholarCross Ref
- X. Wang, M. S. Gerber, and D. E. Brown. Automatic crime prediction using events extracted from Twitter posts. In Social Computing, Behavioral-Cultural Modeling and Prediction, pages 231--238. Springer, 2012. Google ScholarDigital Library
- J. Weng and B.-S. Lee. Event detection in twitter. ICWSM, 11:401--408, 2011.Google Scholar
- S. Xiang, T. Yang, and J. Ye. Simultaneous feature and feature group selection through hard thresholding. In KDD 2014, pages 532--541. ACM, 2014. Google ScholarDigital Library
- L. Zhao, F. Chen, J. Dai, T. Hua, C.-T. Lu, and N. Ramakrishnan. Unsupervised spatial event detection in targeted domains with applications to civil unrest modeling. PloS one, 9(10):e110206, 2014.Google ScholarCross Ref
- L. Zhao, F. Chen, C.-T. Lu, and N. Ramakrishnan. Spatiotemporal event forecasting in social media. In SDM 15, pages 963--971. SIAM, 2015.Google ScholarCross Ref
- J. Zhou, J. Chen, and J. Ye. MALSAR: Multi-tAsk Learning via StructurAl Regularization. Arizona State University, 2011.Google Scholar
Index Terms
- Multi-Task Learning for Spatio-Temporal Event Forecasting
Recommendations
Event Prediction in the Big Data Era: A Systematic Survey
Events are occurrences in specific locations, time, and semantics that nontrivially impact either our society or the nature, such as earthquakes, civil unrest, system failures, pandemics, and crimes. It is highly desirable to be able to anticipate the ...
Spatio-temporal Event Forecasting and Precursor Identification
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningSpatio-temporal societal event forecasting, which has traditionally been prohibitively challenging, is now becoming possible and experiencing rapid growth thanks to the big data from Open Source Indicators (OSI) such as social media, news sources, blogs,...
Spatio-Temporal Data Mining: A Survey of Problems and Methods
Large volumes of spatio-temporal data are increasingly collected and studied in diverse domains, including climate science, social sciences, neuroscience, epidemiology, transportation, mobile health, and Earth sciences. Spatio-temporal data differ from ...
Comments