Spatiotemporal Event Forecasting in Social Media

Zhao, Liang; Chen, Feng; Lu, Chang-Tien; Ramakrishnan, Naren

doi:10.1137/1.9781611974010.108

Cited by 58 publications

(34 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al [27] combine multi-task learning and dynamic features from social networks for spatial-temporal event forecasting. Generative models have also been used in [26] to jointly model the temporal evolution in semantics and geographical burstiness within social media content. Laxman et al [13] designed a generative model for categorical event prediction in event streams using frequent episodes.…”

Section: Related Workmentioning

confidence: 99%

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning

Ning

Muthiah

Rangwala

et al. 2016

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Self Cite

View full text Add to dashboard Cite

Forecasting events like civil unrest movements, disease outbreaks, financial market movements and government elections from open source indicators such as news feeds and social media streams is an important and challenging problem. From the perspective of human analysts and policy makers, forecasting algorithms need to provide supporting evidence and identify the causes related to the event of interest. We develop a novel multiple instance learning based approach that jointly tackles the problem of identifying evidence-based precursors and forecasts events into the future. Specifically, given a collection of streaming news articles from multiple sources we develop a nested multiple instance learning approach to forecast significant societal events across three countries in Latin America. Our algorithm is able to identify news articles considered as precursors for a protest. Our empirical evaluation shows the strengths of our proposed approaches in filtering candidate precursors, forecasting the occurrence of events with a lead time and predicting the characteristics of different events in comparison to several other formulations. We demonstrate through case studies the effectiveness of our proposed model in filtering the candidate precursors for inspection by a human analyst.

show abstract

Section: Related Workmentioning

confidence: 99%

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning

Ning

Muthiah

Rangwala

et al. 2016

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…Event forecasting: Most research in this area focuses on temporal events and ignores the underlying geographical information, such as the forecasting of elections [21,29], stock market movements [9], disease outbreaks [2,23], box office ticket sales [6,35], and crimes [31]. These works can be grouped into three categorizes: 1) Linear regression models: Simple features, such as tweet volumes, are utilized to predict the occurrence time of future events [6,9,15,21]; 2) Nonlinear models: More sophisticated features such as topicrelated keywords are used as the input to build forecasting models using existing methods such as support vector machines or LASSO [23,31]; 3) Time series-based methods: Methods like autoregressive models are used to model the temporal evolution of event-related indicators (e.g., tweet volume) [2].…”

Section: Related Workmentioning

confidence: 99%

“…Zhao et al [34,22,18] designed a new query expansion method to expand both keywords and key tweets by considering both semantic and social network relationships, and used the burstiness of key tweets to predict civil unrest events. Zhao et al [35] designed a new predictive model based on topic model that jointly characterizes the temporal evolution in both semantics and geographical burstiness of social media content.…”

Section: Related Workmentioning

confidence: 99%

Multi-Task Learning for Spatio-Temporal Event Forecasting

Zhao

Sun

et al. 2015

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Self Cite

118

View full text Add to dashboard Cite

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.

show abstract

“…For example, Krieck et al [18] suggested that self-reported symptoms are the most reliable signal in detecting whether a tweet is relevant to an outbreak or not and then went on to demonstrate that this is because even though people generally do not identify their specific problem until diagnosed by an expert, they readily write about how they feel. Using a similar approach to identify flu-related tweets, researchers generally concentrated on tracking the overall trend of a particular disease outbreak, typically influenza, by monitoring social media [2], [14], [17], [28]. …”

Section: Related Workmentioning

confidence: 99%

SimNest: Social Media Nested Epidemic Simulation via Online Semi-Supervised Deep Learning

Zhao

Chen

et al. 2015

2015 IEEE International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

Infectious disease epidemics such as influenza and Ebola pose a serious threat to global public health. It is crucial to characterize the disease and the evolution of the ongoing epidemic efficiently and accurately. Computational epidemiology can model the disease progress and underlying contact network, but suffers from the lack of real-time and fine-grained surveillance data. Social media, on the other hand, provides timely and detailed disease surveillance, but is insensible to the underlying contact network and disease model. This paper proposes a novel semi-supervised deep learning framework that integrates the strengths of computational epidemiology and social media mining techniques. Specifically, this framework learns the social media users’ health states and intervention actions in real time, which are regularized by the underlying disease model and contact network. Conversely, the learned knowledge from social media can be fed into computational epidemic model to improve the efficiency and accuracy of disease diffusion modeling. We propose an online optimization algorithm to substantialize the above interactive learning process iteratively to achieve a consistent stage of the integration. The extensive experimental results demonstrated that our approach can effectively characterize the spatio-temporal disease diffusion, outperforming competing methods by a substantial margin on multiple metrics.

show abstract

Spatiotemporal Event Forecasting in Social Media

Cited by 58 publications

References 18 publications

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning

Multi-Task Learning for Spatio-Temporal Event Forecasting

SimNest: Social Media Nested Epidemic Simulation via Online Semi-Supervised Deep Learning

Contact Info

Product

Resources

About