A deep learning-based social media text analysis framework for disaster resource management
- PDF / 955,974 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 75 Downloads / 175 Views
ORIGINAL ARTICLE
A deep learning‑based social media text analysis framework for disaster resource management Ashutosh Bhoi1 · Sthita Pragyan Pujari1 · Rakesh Chandra Balabantaray1 Received: 15 April 2020 / Revised: 22 August 2020 / Accepted: 27 August 2020 © Springer-Verlag GmbH Austria, part of Springer Nature 2020
Abstract Social media has evolved itself as a significant tool used by people for information spread during emergencies like natural or man-made disasters. Real-time analysis of this huge collected data can play a vital role in crisis estimation, response and assistance exercises. We propose a novel prototype system that analyzes the emergency-related tweets to classify them as need or available tweets. The presented system also takes care of non-English tweets as there is no boundary of language for social media users. Several classifiers along with different learning methodologies are used to show their usefulness for an efficient solution. Here, a new supervised learning technique based on word embedding is incorporated in the novel hybrid model that comprises of LSTM and CNN. The system will further give a ranked list of tweets, along with a relevance score for each tweet with respect to the topic. Finally for each of the identified need tweets, its corresponding availability tweets are mapped. For the mapping task, a novel two-word sliding window approach is proposed to generate the combine embedding of two adjacent words. The experimental results show significant improvement in the performance. We evaluate our proposed system with FIRE-2016 and CrisisLex datasets to illustrate its effectiveness during mobilization of needful resources. Keywords Resource management · Tweets analysis · Deep learning · Classification · Ranking · Mapping
1 Introduction With the wide use of the Internet, social media has become a prime means of communication in the twenty-first century. The social media applications such as Twitter, Facebook, YouTube, Instagram, WhatsApp, and many more are the main sources of online real-time data. The large volume of microblog texts are getting used for many applications such as sentiment analysis (Nagamanjula and Pethalakshmi 2020), question answering system (Sultana and Badugu 2020), recommender system (Aivazoglou et al. 2020), event detection (Goswami and Kumar 2016), named entity recognition (Bhoi and Balabantaray 2017), education (Froehlich et al. 2020) and many more. Recently,
* Rakesh Chandra Balabantaray rakesh@iiit‑bh.ac.in Ashutosh Bhoi c115001@iiit‑bh.ac.in Sthita Pragyan Pujari b116053@iiit‑bh.ac.in 1
IIIT Bhubaneswar, Bhubaneswar, India
the usage of social media has increased tremendously during natural or human-made hazards due to wide usage of handheld devices. Natural emergencies such as earthquake, typhoon, volcanic breakout, tsunami, avalanche, and disease epidemic or man-made emergencies like a terrorist attack, train accident, and nuclear power plant explosion trigger crisis. Further, in last few years information and communication technology (ICT) is bei
Data Loading...
