%0 Book Section %1 noKey %A Xu, Jun-Ming %A Bhargava, Aniruddha %A Nowak, Robert %A Zhu, Xiaojin %B Machine Learning and Knowledge Discovery in Databases %D 2012 %E Flach, PeterA. %E Bie, Tijl %E Cristianini, Nello %I Springer Berlin Heidelberg %K signal social spatio-temporal todo %P 644-659 %R 10.1007/978-3-642-33486-3_41 %T Socioscope: Spatio-temporal Signal Recovery from Social Media %U http://dx.doi.org/10.1007/978-3-642-33486-3_41 %V 7524 %X Many real-world phenomena can be represented by a spatio-temporal signal: where, when, and how much. Social media is a tantalizing data source for those who wish to monitor such signals. Unlike most prior work, we assume that the target phenomenon is known and we are given a method to count its occurrences in social media. However, counting is plagued by sample bias, incomplete data, and, paradoxically, data scarcity – issues inadequately addressed by prior work. We formulate signal recovery as a Poisson point process estimation problem. We explicitly incorporate human population bias, time delays and spatial distortions, and spatio-temporal regularization into the model to address the noisy count issues. We present an efficient optimization algorithm and discuss its theoretical properties. We show that our model is more accurate than commonly-used baselines. Finally, we present a case study on wildlife roadkill monitoring, where our model produces qualitatively convincing results. %@ 978-3-642-33485-6

@incollection{noKey, abstract = {Many real-world phenomena can be represented by a spatio-temporal signal: where, when, and how much. Social media is a tantalizing data source for those who wish to monitor such signals. Unlike most prior work, we assume that the target phenomenon is known and we are given a method to count its occurrences in social media. However, counting is plagued by sample bias, incomplete data, and, paradoxically, data scarcity – issues inadequately addressed by prior work. We formulate signal recovery as a Poisson point process estimation problem. We explicitly incorporate human population bias, time delays and spatial distortions, and spatio-temporal regularization into the model to address the noisy count issues. We present an efficient optimization algorithm and discuss its theoretical properties. We show that our model is more accurate than commonly-used baselines. Finally, we present a case study on wildlife roadkill monitoring, where our model produces qualitatively convincing results.}, added-at = {2014-05-12T13:04:46.000+0200}, author = {Xu, Jun-Ming and Bhargava, Aniruddha and Nowak, Robert and Zhu, Xiaojin}, biburl = {https://www.bibsonomy.org/bibtex/260445437200780030b2ce08b8a30e63d/dallmann}, booktitle = {Machine Learning and Knowledge Discovery in Databases}, doi = {10.1007/978-3-642-33486-3_41}, editor = {Flach, PeterA. and Bie, Tijl and Cristianini, Nello}, interhash = {598a48c8e6854e92968ddba02d18df06}, intrahash = {60445437200780030b2ce08b8a30e63d}, isbn = {978-3-642-33485-6}, keywords = {signal social spatio-temporal todo}, pages = {644-659}, publisher = {Springer Berlin Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2014-05-12T13:04:46.000+0200}, title = {Socioscope: Spatio-temporal Signal Recovery from Social Media}, url = {http://dx.doi.org/10.1007/978-3-642-33486-3_41}, volume = 7524, year = 2012 }