Intensity-Based Sentiment and Topic Analysis. The Case of the 2020 Aegean Earthquake

Diana Contreras,Matthieu Landès,Rémy Bossu,Sean Wilkinson,Yasemin Didem Aktas,Laure Fallou

doi:10.3389/fbuil.2022.839770

Abstract

After an earthquake, it is necessary to understand its impact to provide relief and plan recovery. Social media (SM) and crowdsourcing platforms have recently become valuable tools for quickly collecting large amounts of first-hand data after a disaster. Earthquake-related studies propose using data mining and natural language processing (NLP) for damage detection and emergency response assessment. Using tex-data provided by the Euro-Mediterranean Seismological Centre (EMSC) collected through the LastQuake app for the Aegean Earthquake, we undertake a sentiment and topic analysis according to the intensities reported by their users in the Modified Mercalli Intensity (MMI) scale. There were collected 2,518 comments, reporting intensities from I to X being the most frequent intensity reported III. We use supervised classification according to a rule-set defined by authors and a two-tailed Pearson correlation to find statistical relationships between intensities reported in the MMI by LastQuake app users, polarities, and topics addressed in their comments. The most frequent word among comments was: “Felt.” The sentiment analysis (SA) indicates that the positive polarity prevails in the comments associated with the lowest intensities reported: (I-II), while the negative polarity in the comments is associated with higher intensities (III–VIII and X). The correlation analysis identifies a negative correlation between the increase in the reported MMI intensity and the comments with positive polarity. The most addressed topic in the comments from LastQuake app users was intensity, followed by seismic information, solidarity messages, emergency response, unrelated topics, building damages, tsunami effects, preparedness, and geotechnical effects. Intensities reported in the MMI are significantly and negatively correlated with the number of topics addressed in comments. Positive polarity decreases with the soar in the reported intensity in MMI demonstrated the validity of our first hypothesis, despite not finding a correlation with negative polarity. Instead, we could not prove that building damage, geotechnical effects, lifelines affected, and tsunami effects were topis addressed only in comments reporting the highest intensities in the MMI.

Highlights

After an earthquake, it is necessary to understand its impact to provide relief and plan recovery
LastQuake is a crowdsourcebased earthquake information app developed by the Euro-Mediterranean Seismological Centre (EMSC), and Twitter data was purchased from TweetBinder, a third-party vendor; in this paper, we focused our analysis on text data collected through the LastQuake app
This research aimed to understand the relationship between the intensities reported by users and the polarities and topics addressed in the comments associated with these reports

Summary

Introduction

It is necessary to understand its impact to provide relief and plan recovery. The availability of state-of-the-art instrumentation, mobile data collection technologies, social media (SM), crowdsourcing platforms, training, and field support services has increased and eased the ability to capture perishable data during postdisaster phases (Wartman et al, 2020; Contreras et al, 2021a; Contreras et al, 2021c). Social media and crowdsourcing platforms collect first-hand data, observations, sentiments, and perspectives (Yan et al, 2020). Image and text data are contained in photos, videos, and comments posted in SM Correlation between the number of tweets and the intensity of an earthquake was observed for the first time in 2010. The recent increase in the number of crowdsourcing platforms used to source earthquake reconnaissance data demonstrates that it is likely to become an increasingly fundamental data source (Contreras et al, 2021d)

Objectives

Methods

Findings

Conclusion