基于深度学习的社交媒体情感信息抽取及其在灾情分析中的应用研究

Extracting Sentiment Information from Social Media Based on Deep Learning and the Research on Disaster Reduction

社交媒体具有强实效性、广传播性和低成本等优点,在减灾救援中发挥了重要作用,但较少有人抽取其中隐含的公众细粒度情感信息进行灾情分析。该文基于深度学习算法抽取社交媒体中蕴含的细粒度情感信息,同时结合社交媒体中包含的时空信息构建涉灾地理信息数据,在此基础上利用GIS空间分析方法研究灾害进展特征,分析结果可为减灾救援提供有效的信息参考,并以2017年8月8日九寨沟地震事件为案例,验证了该方法在减灾中的应用效果。

Social media has played an important role in disaster reduction in recent years due to its strong real-time,wide dissemination and low cost.Based on its rich content and spatio-temporal information,many scholars have carried out a lot of researches in disaster reduction.But few people extract the fine-grained public sentiment information contained in it for disaster analysis.So,in this paper,we proposed a method of extracting fine-grained metaphorical sentiment information contained in social media based on deep learning model.At the same time,we constructed disaster-related geographic information data by combining spatio-temporal features contained in social media.Based on this,the GIS spatial analysis methods were used to study the characteristics of disaster progress,and the analysis results can provide effective information for disaster reduction and rescue.This paper took the Jiuzhaigou earthquake on August 8,2017 as an example to verify the efficiency of the method in disaster reduction.