D.A. Devyatkin – Main Specialist, FRC «Computer Science and Control» of RAS (Moscow) E-mail: devyatkin@isa.ru

A.O. Shelmanov – Ph.D.(Eng.), Research Scientist, FRC «Computer Science and Control» of RAS (Moscow) E-mail: shelmanov@isa.ru

D.S. Larionov – Student, RUDN Univercity (Moscow)

E-mail: dslarionov@protonmail.com

The paper presents a prototype of a system for monitoring emergency events in a particular geographic region by analyzing social media data. We consider architecture, the main components of the system, as well as methods for crawling and processing emergency-related messages. The methods provide functionality for collecting emergency reports, information extraction, including the names of geographical locations and names of vessels, text classification, as well as new emergencies detection, and visualizing extracted events on a geographical map. As one of the possible future functions of the system, it is proposed to consider the evaluation of the informative nature of messages published in social networks and other sources. Evaluation of informativeness could be useful both in data collection and in the calculation of the relevance of answers when searching information in the system.

1. Sixto J., Pena O., Klein B., López-de Ipina D. Enable tweet-geolocation and don’t drive ERTs crazy! Improving situational awareness using Twitter // Proc. of SMERST. 2013. P. 27−31.
2. Devyatkin D.A., Shelmanov A.O. Unstructured data analysis to support rescue operations [Analiz nestructurirovannyh tekstovyh dannyh dlya podderzki poiskovo-spssatelnyh rabot] // High availability systems [Systemy vysokoi dostupnosti]. 2015. № 4. P. 45−60.
3. Devyatkin D. and Shelmanov A. Text processing framework for emergency event detection in the Arctic zone // Communications in Computer and Information Science. 2017. № 706. P. 74−88.
4. Devyatkin D., Shelmanov A. and Larionov D. Discovering Novel Emergency Events in Text Streams // Proc. of the XX International Conference «Data Analytics and Management in Data Intensive Domains» (DAMDID/RCDL’2018). Moscow, Russia. October 9−12, 2018. [V pechati].
5. Ashktorab Z. et al. Tweedr: Mining twitter to inform disaster response // ISCRAM. 2014.
6. Carreras X. et al. FreeLing: An Open-Source Suite of Language Analyzers // LREC. 2004. P. 239−242.
7. Nivre J., Hall J., Nilsson J. Maltparser: A data-driven parser-generator for dependency parsing // Proc. of LREC. 2006. Т. 6. P. 2216−2219.
8. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado and Jeff Dean Distributed representations of words and phrases and their compositionality // Advances in neural information processing systems. 2013. P. 3111−3119.
9. Alexandra Olteanu, Carlos Castillo, Fernando Diaz and Sarah Vieweg CrisisLex: A lexicon for collecting and filtering microblogged communications in crises // Proc. of ICWSM. 2014.
10. Al-Rfou R. et al. Polyglot-NER: Massive multilingual named entity recognition // Proc. of the 2015 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics. 2015. P. 586−594.
11. Osipov G., Smirnov I., Tikhomirov I., Sochenkov I. and Shelmanov A. Exactus expert search and analytical engine for research and development support // Novel Applications of Intelligent Systems. Springer. 2016. P. 269−285.
12. Ianina A., Golitsyn L. and Vorontsov K. Multi-objective topic modeling for exploratory search in tech news // Conference on Artificial Intelligence and Natural Language. Springer. 2017. P. 181−193.