TY - GEN
T1 - Snowball
T2 - 1st International Conference on Data Intelligence and Security, ICDIS 2018
AU - Alashri, Saud
AU - Tsai, Jiun Yi
AU - Koppela, Anvesh Reddy
AU - Davulcu, Hasan
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/25
Y1 - 2018/5/25
N2 - Unpacking causal relationships is essential for developing solutions for managing climate risks that threaten sociopolitical stability. However, the automatic discovery of complex causal chains among interlinked events and their participating actors within large corpora is not well studied. Previous studies on extracting causal relationships from text were based on laborious and incomplete hand developed lists of causal verbs, such as 'causes' and 'results in'. Such approaches result in limited recall because standard causal verbs may not generalize well to accommodate surface variations in texts when different keywords and phrases are used to express similar causal effects. This paper presents a Snowball system to generalize <Subject, Verb, Object> triplets extracted from corpora of online news articles, and cluster them into higher-level concepts without drift. We start with a seed set of causal verbs and apply a concept generalization technique to extract causal chains and their participating actors. Our novel algorithms overcome surface variations in written expressions of causal relationships and discover the domino effects between climate events and human security. Unlike prior studies, our semi-supervised approach alleviates the need for labor intensive keyword list development and annotated datasets. Experimental evaluations by domain experts achieve an average precision of 82%, a significant improvement from prior work. Qualitative assessments of causal chains show that results are consistent with the 2014 IPCC report illuminating causal mechanisms underlying the linkages between climatic stresses and social instability.
AB - Unpacking causal relationships is essential for developing solutions for managing climate risks that threaten sociopolitical stability. However, the automatic discovery of complex causal chains among interlinked events and their participating actors within large corpora is not well studied. Previous studies on extracting causal relationships from text were based on laborious and incomplete hand developed lists of causal verbs, such as 'causes' and 'results in'. Such approaches result in limited recall because standard causal verbs may not generalize well to accommodate surface variations in texts when different keywords and phrases are used to express similar causal effects. This paper presents a Snowball system to generalize <Subject, Verb, Object> triplets extracted from corpora of online news articles, and cluster them into higher-level concepts without drift. We start with a seed set of causal verbs and apply a concept generalization technique to extract causal chains and their participating actors. Our novel algorithms overcome surface variations in written expressions of causal relationships and discover the domino effects between climate events and human security. Unlike prior studies, our semi-supervised approach alleviates the need for labor intensive keyword list development and annotated datasets. Experimental evaluations by domain experts achieve an average precision of 82%, a significant improvement from prior work. Qualitative assessments of causal chains show that results are consistent with the 2014 IPCC report illuminating causal mechanisms underlying the linkages between climatic stresses and social instability.
KW - Causal Chains
KW - Causal Relations
KW - Climate Change
KW - Information Extraction
KW - Natural Language Processing
KW - Text Mining
UR - http://www.scopus.com/inward/record.url?scp=85048523770&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048523770&partnerID=8YFLogxK
U2 - 10.1109/ICDIS.2018.00045
DO - 10.1109/ICDIS.2018.00045
M3 - Conference contribution
AN - SCOPUS:85048523770
T3 - Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018
SP - 234
EP - 241
BT - Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 8 April 2018 through 10 April 2018
ER -