Multi-Task Learning for Transit Service Disruption Detection

With the rapid growth in urban transit networks in recent years, detecting service disruptions in a timely manner is a problem of increased interest to service providers. Transit agencies are seeking to move beyond traditional customer questionnaires and manual service inspections to leveraging open source indicators like social media for deteting emerging transit events. In this paper, we leverage Twitter data for early detection of metro service disruptions. Inspired by the multi-task learning framework, we propose the Metro Disruption Detection Model, which captures the semantic similarity between transit lines in Twitter space. We propose novel constraints on feature semantic similarity exploiting prior knowledge about the spatial connectivity and shared tracks of the metro network. An algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed model. We run extensive experiments and comparisons to other models with real world Twitter data and transit disruption records from the Washington Metropolitan Area Transit Authority (WMATA) to justify the efficacy of our model.

[1]  Tong Zhang,et al.  A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , 2005, J. Mach. Learn. Res..

[2]  Matthew S. Gerber,et al.  Predicting crime using Twitter and kernel density estimation , 2014, Decis. Support Syst..

[3]  Saif Mohammad,et al.  NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets , 2013, *SEMEVAL.

[4]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[5]  Tianyi Ma,et al.  Delivering Real-Time Information Services on Public Transit: A Framework , 2017, IEEE Transactions on Intelligent Transportation Systems.

[6]  Jiejun Xu,et al.  Using publicly visible social media to build detailed forecasts of civil unrest , 2014, Security Informatics.

[7]  Michael J. Paul,et al.  Session Introduction , 2016, PSB.

[8]  Xuchao Zhang,et al.  Storytelling in heterogeneous Twitter entity network based on hierarchical cluster routing , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[9]  Ophir Frieder,et al.  A framework for detecting public health trends with Twitter , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[10]  Massimiliano Pontil,et al.  Convex multi-task feature learning , 2008, Machine Learning.

[11]  Mark Dredze,et al.  Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance , 2015, PLoS Comput. Biol..

[12]  Satish V. Ukkusuri,et al.  Urban activity pattern classification using topic models from online geo-location data , 2014 .

[13]  Zhaohui Wu,et al.  City-Scale Social Event Detection and Evaluation with Taxi Traces , 2015, ACM Trans. Intell. Syst. Technol..

[14]  Aggelos K. Katsaggelos,et al.  Anomalous video event detection using spatiotemporal context , 2011 .

[15]  Naren Ramakrishnan,et al.  Syndromic surveillance of Flu on Twitter using weakly supervised temporal topic models , 2016, Data Mining and Knowledge Discovery.

[16]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[17]  Nirajan Shiwakoti,et al.  Social Media Use during Unplanned Transit Network Disruptions: A Review of Literature , 2014 .

[18]  Wotao Yin,et al.  A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion , 2013, SIAM J. Imaging Sci..

[19]  J. Neff,et al.  2016 Public Transportation Fact Book , 2008 .

[20]  Jieping Ye,et al.  Multi-Task Learning for Spatio-Temporal Event Forecasting , 2015, KDD.

[21]  Aravind Srinivasan,et al.  'Beating the news' with EMBERS: forecasting civil unrest using open source indicators , 2014, KDD.