A Method of Constructing Marine Oil Spill Scenarios from Flat Text Based on Semantic Analysis

Kui Huang, Wen Nie and Nianxue Luo
Additional contact information
Kui Huang: School of Geodesy and Geomatics, Wuhan University, Wuhan 420100, China
Wen Nie: State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 420100, China
Nianxue Luo: School of Geodesy and Geomatics, Wuhan University, Wuhan 420100, China

IJERPH, 2020, vol. 17, issue 8, 1-17

Abstract: Constructed emergency response scenarios provide a basis for decision makers to make management decisions, and the development of such scenarios considers earlier historical cases. Over the decades, the development of emergency response scenarios has mainly implemented the elements of historic cases to describe the grade and influence of an accident. This paper focuses on scenario construction and proposes a corresponding framework based on natural language processing (NLP) using text reports of marine oil spill accidents. For each accident, the original textual reports are first divided into sentence sets corresponding to the temporal evolution. Each sentence set is regarded as a textual description of a marine oil spill scenario. A method is proposed in this paper, based on parsing, named entity recognition (NER) and open information extraction (OpenIE) to process the relation triples that are extracted from the sentence sets. Finally, the relation triples are semantically clustered into different marine oil spill domains to construct scenarios. The research results are validated and indicate that the proposed scenario construction framework can be effectively used in practical applications.

Keywords: scenario construction; marine oil spill; natural language processing; semantic clustering (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1660-4601/17/8/2659/pdf (application/pdf)
https://www.mdpi.com/1660-4601/17/8/2659/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:17:y:2020:i:8:p:2659-:d:344970

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().