Citation

Srivastava H, Sankar R. IEEE Trans. Comput. Soc. Syst. 2020; 7(2): 319-328.

Copyright

(Copyright © 2020, Institute of Electrical and Electronics Engineers, Inc.)

DOI

10.1109/TCSS.2020.2964253

PMID

unavailable

Abstract

The recent trend of dependence on the social network for information abstraction and propagation has a cumulative effect on critical response. The content and reliability of data are substantiated by acquiring data from a network of social site users. It captures the engaged multiple user behavior to formulate and diffuse the connected information across the channel. The objective is to identify a bridge between different data sources for event anomalies. This article proposes a novel approach toward identifying the sublevel anomalies and predictive investigation toward the use of Twitter's social data during extreme weather scenarios. We performed qualitative analyses by gathering data from social media and weather data websites. Various analysis methods are proposed to aggregate the diffused information from the social network to generate influencing data. The analyses results further identify the connected user acknowledgment for dominant information in the public domain. This information is mapped by applying a convolutional neural network for a physical sensor data set to detect weather anomalies. Moreover, we exploited the reinforcement learning technique to determine smart policy on the influencing data. The results show that our proposed method can predict critical events with high precision during extreme weather emergency scenarios.

Language: en

Keywords

connected user acknowledgment; convolutional neural nets; convolutional neural network; Correlation; Data analysis; extreme weather; extreme weather emergency scenarios; geophysics computing; information abstraction; information dissemination; learning; learning (artificial intelligence); Meteorology; multiple user behavior; Real-time systems; Sensors; social data; social media; social network; social networking (online); social site; Twitter; weather anomalies; weather data Web sites