Filters








21,286 Hits in 4.4 sec

Cross-Context News Corpus for Protest Event-Related Knowledge Base Construction

Ali Hürriyetoğlu, Erdem Yörük, Osman Mutlu, Fırat Duruşan, Çağrı Yoltar, Deniz Yüret, Burak Gürel
2021 Data Intelligence  
We describe a gold standard corpus of protest events that comprise various local and international English language sources from various countries.  ...  This corpus and the reported results will establish a common foundation in automated protest event collection studies, which is currently lacking in the literature.  ...  Erdem Yörük for his project Emerging Welfare. Çagrı Yoltar is a post-doctoral fellow and the project leader of the "Emerging Welfare" project at Koç University, Turkey.  ... 
doi:10.1162/dint_a_00092 fatcat:zgylu5yjmjev7jqasvi27isnmq

Cross-context News Corpus for Protest Events related Knowledge Base Construction [article]

Ali Hürriyetoğlu, Erdem Yörük, Deniz Yüret, Osman Mutlu, Çağrı Yoltar, Fırat Duruşan, Burak Gürel
2020 arXiv   pre-print
We describe a gold standard corpus of protest events that comprise of various local and international sources from various countries in English.  ...  This corpus and the reported results will set the currently lacking common ground in automated protest event collection studies.  ...  Erdem Yörük for his project Emerging Welfare.  ... 
arXiv:2008.00351v1 fatcat:degmsyk5hfeetir25yddqezvbm

STAPLE: Spatio-Temporal Precursor Learning for Event Forecasting [chapter]

Yue Ning, Rongrong Tao, Chandan K. Reddy, Huzefa Rangwala, James C. Starz, Naren Ramakrishnan
2018 Proceedings of the 2018 SIAM International Conference on Data Mining  
Through studies on civil unrest movements in numerous countries, we demonstrate the effectiveness of the proposed method for precursor discovery and event forecasting.  ...  In this paper, we develop a novel multi-task model with dynamic graph constraints within a multiinstance learning framework.  ...  In this paper, we propose STAPLE, a multi-task Spatio-TemporAl Precursor Learning and Event forecasting framework for multiple cities, specifically designed to discover precursors across geolocations with  ... 
doi:10.1137/1.9781611975321.17 dblp:conf/sdm/NingTRRSR18 fatcat:hypmzotmqnax5dh2vomhmghkaa

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning [article]

Yue Ning and Sathappan Muthiah and Huzefa Rangwala and Naren Ramakrishnan
2016 arXiv   pre-print
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  ...  Our algorithm is able to identify news articles considered as precursors for a protest.  ...  Acknowledgments Supported by the Intelligence Advanced Research Projects Activity (IARPA) via DoI/NBC contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints of this work for  ... 
arXiv:1602.08033v2 fatcat:6p6gyf4ukzf47jahkpuwhd6kp4

Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning

Yue Ning, Sathappan Muthiah, Huzefa Rangwala, Naren Ramakrishnan
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
Specifically, given a collection of streaming news articles from multiple sources we develop a nested multiple instance learning approach to forecast significant societal events such as protests.  ...  Using data from three countries in Latin America, we demonstrate how our approach is able to consistently identify news articles considered as precursors for protests.  ...  Acknowledgments Supported by the Intelligence Advanced Research Projects Activity (IARPA) via DoI/NBC contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints of this work for  ... 
doi:10.1145/2939672.2939802 dblp:conf/kdd/NingMRR16 fatcat:miqo6jstk5ag5ftlwukufn3aki

Protest Activity Detection and Perceived Violence Estimation from Social Media Images [article]

Donghyeon Won, Zachary C. Steinert-Threlkeld, Jungseock Joo
2017 arXiv   pre-print
A multi-task convolutional neural network is employed in order to automatically classify the presence of protesters in an image and predict its visual attributes, perceived violence and exhibited emotions  ...  Our system characterizes protests along these dimensions. We have collected geotagged tweets and their images from 2013-2017 and analyzed multiple major protest events in that period.  ...  ACKNOWLEDGEMENTS This research is supported by UCLA TSG Program, "Visual Big Data: Using Images to Understand Protests. " We also acknowledge the support of NVIDIA Corporation for their donation of hardware  ... 
arXiv:1709.06204v1 fatcat:nflyezzpnfb5loqw6decbb64le

Protest Activity Detection and Perceived Violence Estimation from Social Media Images

Donghyeon Won, Zachary C. Steinert-Threlkeld, Jungseock Joo
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
A multi-task convolutional neural network is employed in order to automatically classify the presence of protesters in an image and predict its visual attributes, perceived violence and exhibited emotions  ...  Our system characterizes protests along these dimensions. We have collected geotagged tweets and their images from 2013-2017 and analyzed multiple major protest events in that period.  ...  ACKNOWLEDGEMENTS This research is supported by UCLA TSG Program, "Visual Big Data: Using Images to Understand Protests. " We also acknowledge the support of NVIDIA Corporation for their donation of hardware  ... 
doi:10.1145/3123266.3123282 dblp:conf/mm/WonSJ17 fatcat:nhcyrbdmsbblzph322a45zhoy4

CLEF ProtestNews Lab 2019: Contextualized Word Embeddings for Event Sentence Detection and Event Extraction

Gabriella Skitalinskaya, Jonas Klaff, Maximilian Spliethöver
2019 Conference and Labs of the Evaluation Forum  
The models were trained on a data corpus collected from Indian news sources, but evaluated on data obtained from news sources from other countries as well, such as China.  ...  Our models have obtained competitive results and have scored 3rd in the event sentence detection task and 1st in the event extraction task based on average F1-scores for different test datasets.  ...  Lab [19] tries to tackle this problem and has introduced three shared tasks aimed at identifying and extracting event information from news articles across multiple countries.  ... 
dblp:conf/clef/SkitalinskayaKS19 fatcat:oeehimezzvfvtkfg5jpdgcy7te

Improving the selection of news reports for event coding using ensemble classification

Mihai Croicu, Nils B Weidmann
2015 Research & Politics  
data collected.  ...  In this paper, we introduce an alternative strategy by establishing a semi-automatic pipeline, where an automatic classification system eliminates irrelevant source material before further coding is done  ...  Acknowledgements The authors would like to thank participants at the July 2015 workshop on "Automated Content Analysis in the Social Sciences" at the University of Zurich for comments.  ... 
doi:10.1177/2053168015615596 fatcat:iazbzfes7reypmigdkpnl632qe

Multi-Task Learning for Spatio-Temporal Event Forecasting

Liang Zhao, Qian Sun, Jieping Ye, Feng Chen, Chang-Tien Lu, Naren Ramakrishnan
2015 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15  
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  ...  This paper proposes a novel multi-task learning framework which aims to concurrently address all the challenges.  ...  Acknowledgement Supported by the Intelligence Advanced Research Projects Activity (IARPA) via DoI/NBC contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints of this work for  ... 
doi:10.1145/2783258.2783377 dblp:conf/kdd/ZhaoSYCLR15 fatcat:tcbej6wfcrfdjax6mn66amjeey

Automated Extraction of Socio-political Events from News (AESPEN): Workshop and Shared Task Report [article]

Ali Hürriyetoğlu, Vanni Zavarella, Hristo Tanev, Erdem Yörük, Ali Safaya, Osman Mutlu
2020 arXiv   pre-print
collection across sources, countries, and languages.  ...  socio-political event information collection.  ...  In the scope of the other event information collection study, Papanikolaou and Papageorgiou1 (2020) processed two news sources in Greek from Greece to create a database of protest events for the period  ... 
arXiv:2005.06070v1 fatcat:de3rtp7lergcngbansvnvl76ka

Using Computational Linguistics to Enhance Protest Event Analysis

Bruno Wueest, Klaus Rothenhäusler, Swen Hutter
2013 Social Science Research Network  
As a consequence, most of the scholarship still focuses on a narrow set of European countries or the United States and does not cover the period since the early 2000s.  ...  As a consequence, most of the scholarship still focuses on a narrow set of European countries or the United States and does not cover the period since the early 2000s.  ...  ., 2011) , we understand our task insofar as we try to establish semi-automatic procedures to collect a basic set of key indicators of protest events such as the protest form, the number of participants  ... 
doi:10.2139/ssrn.2286769 fatcat:hxrds6naobhn3c4hjyyw4bnsrm

Combining Heterogeneous Data Sources for Civil Unrest Forecasting

Gizem Korkmaz, Jose Cadena, Chris J. Kuhlman, Achla Marathe, Anil Vullikanti, Naren Ramakrishnan
2015 Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015 - ASONAM '15  
We analyze protest dynamics in six countries of Latin America on a daily level, from November 2012 through August 2014, using multiple data sources that capture social, political and economic contexts  ...  We use logistic regression models with Lasso to select a sparse feature set from our diverse datasets, in order to predict the probability of occurrence of civil unrest events in these countries.  ...  Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center (DoI/NBC) contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints for  ... 
doi:10.1145/2808797.2808847 dblp:conf/asunam/KorkmazCKMVR15 fatcat:ida6maithvfufjkcis5ye36dsm

Image as Data: Automated Visual Content Analysis for Political Science [article]

Jungseock Joo, Zachary C. Steinert-Threlkeld
2018 arXiv   pre-print
This article introduces a new class of automated methods based on computer vision and deep learning which can automatically analyze visual content data.  ...  We then discuss how these methods can contribute to the study of political communication, identity and politics, development, and conflict, by enabling a new set of research questions at scale.  ...  In training, all the model parameters (model weights) are optimized to minimize this loss function across the entire training set.  ... 
arXiv:1810.01544v1 fatcat:vboljkjbufhbvbsiuhisk3ucde

A topic-focused trust model for Twitter

Liang Zhao, Ting Hua, Chang-Tien Lu, Ing-Ray Chen
2016 Computer Communications  
Twitter is a crucial platform to get access to breaking news and timely information.  ...  In this paper, we propose a novel topic-focused trust model to assess trustworthiness of users and tweets in Twitter.  ...  For both datasets, we collected data across 10 countries in Latin America from July 2012 to May 2013, including: Argentina, Brazil, Chile, Colombia, Ecuador, El Salvador, Mexico, Paraguay, Uruguay, and  ... 
doi:10.1016/j.comcom.2015.08.001 fatcat:nff4lqlxqfezhozl4wgmw64xma
« Previous Showing results 1 — 15 out of 21,286 results