On mining mobile emergency communication applications in Nordic countries
被引:0
|
作者:
Shaik, Fuzel Ahamed
论文数: 0引用数: 0
h-index: 0
机构:
Univ Oulu, Fac Informat Technol & Elect Engn, Ctr Machine Vis & Signal Proc, POB 4500, Oulu 90014, FinlandUniv Oulu, Fac Informat Technol & Elect Engn, Ctr Machine Vis & Signal Proc, POB 4500, Oulu 90014, Finland
Shaik, Fuzel Ahamed
[1
]
Oussalah, Mourad
论文数: 0引用数: 0
h-index: 0
机构:
Univ Oulu, Fac Informat Technol & Elect Engn, Ctr Machine Vis & Signal Proc, POB 4500, Oulu 90014, FinlandUniv Oulu, Fac Informat Technol & Elect Engn, Ctr Machine Vis & Signal Proc, POB 4500, Oulu 90014, Finland
Oussalah, Mourad
[1
]
机构:
[1] Univ Oulu, Fac Informat Technol & Elect Engn, Ctr Machine Vis & Signal Proc, POB 4500, Oulu 90014, Finland
Social media;
Emergency communication;
Aspect Based Sentiment Analysis;
BERT;
Ontological vocabulary;
Empath categorization;
MANAGEMENT;
ONTOLOGY;
MODEL;
D O I:
10.1016/j.ijdrr.2024.104566
中图分类号:
P [天文学、地球科学];
学科分类号:
07 ;
摘要:
Nowadays, the use of mobile devices has become ubiquitous, allowing users to access and share information in almost real-time through various social media platforms. This has provided an edge in emergency communication and disaster handling. Mobile emergency apps have emerged as key technologies in emergency communication. Mining the content of users' reviews of mobile emergency apps has the potential to learn about users' behavior and uncover unforeseen events in the emergency management process. This paper focused on emergency apps present in Nordic countries (Finland, Sweden, and Norway). User feedback was collected for every app from the Google/Apple store, and appropriate text mining techniques were employed to mine the discussion content for a given emergency communication ontology. Next, we investigated the contexts that generate either positive or negative sentiment, highlighting the main factors that impact user behavior most by leveraging the Empath Categorization technique. Finally, we constructed a word association by considering different ontological vocabularies related to mobile applications and emergency response and management systems. The study's findings can help develop early warning systems that trigger alarms whenever a critical event requiring special attention is identified. It also paves the way for developing a more tailored communication strategy that considers the identified community behavior concerning emergency apps.