Emerging Role of Artificial Intelligence for Disaster Management Based on Microblogged Communication

Khattar, Anuradha; Quadri, S. M. K.

doi:10.2139/ssrn.3562973

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Those who are graduating this year are worried about their future as they would be entering the jobs at the beginning of a major g lobal recession. Social med ia plays an important role in disaster management [10]. Factual headlines more often than not come fro m authentic mainstream media sources.…”

Section: Emotions and Moods Of Studentsmentioning

confidence: 99%

Effects of the Disastrous Pandemic COVID 19 on Learning Styles, Activities and Mental Health of Young Indian Students - A Machine Learning Approach

Khattar

Jain

Quadri

2020

2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS)

Self Cite

View full text Add to dashboard Cite

Word Health Organization declared coronavirus disease 2019 (COVID-19) as pandemic on 11 M arch 2020. After that on 14 M arch 2020 the M inistry of Home Affairs, India decided to treat COVID-19 as a "notified disaster" due to the spurt in the cases related to coronavirus in the country, leading to a complete shut down from 24 M arch 2020. This has affected all sectors of the country including the education sector. The near-total closure of schools, colleges, and universities has disrupted academic activities at various levels. The objective of this online survey study is to understand the day to day living, activities, learning styles, and mental health of young students of India during this unprecedented crisis and assess how they are adapting to the new e-learning styles and how they are managing their social lives.

show abstract

Section: Emotions and Moods Of Studentsmentioning

confidence: 99%

Effects of the Disastrous Pandemic COVID 19 on Learning Styles, Activities and Mental Health of Young Indian Students - A Machine Learning Approach

Khattar

Jain

Quadri

2020

2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Karmegam et al [59] have developed a mapping model towards forecasting a flood event from data captured from twitter. The emergence of an Artificial Intelligencebased model towards the prediction of disaster is carried out by Khattar and Quadri [60] using content from microblogs in social networks. Mendoza et al [61] developed an early prediction model based on the Mercalli scale integrated with locally supported information for estimating real-life earthquake events.…”

Section:  Predictive Approachmentioning

confidence: 99%

“…Several dominant research-based approaches are used to analyze natural disasters viz. i) Interdisciplinary Research (Tavra et al [65], Khattar & Quadri [60], Ide & Nomura [58]), ii) Risk-Based Approaches ((Psaroudakis et al [30]), iii) Datadriven Analysis (Ghawana et al [38], Vavassori et al [52], Zhang et al [45]), iv) Resilience Frameworks (Maxant et al [51], Divjak and Lapaine [47], Du et al [49]). Under interdisciplinary research scheme, it is considered that natural disasters are complex events involving multiple factors, including physical, social, economic, and environmental dimensions.…”

Section: R2: What Is the Currently Dominant Research-based Approaches...mentioning

confidence: 99%

“…The adoption of social media for evaluating the criticality of natural disasters presents several complexities:i) Data Veracity (Han et al [39], Mitcham et al [40]), ii) Data Volume and Velocity (Durrant et al [50], Takenouchi and Choh [64], Kamiya et al [68], Karmegam et al [59], Wania et al [36], Asif et al [53], Ghawana et al [38], Vavassori et al [52]), iii) Bias and Algorithmic Fairness (Fan et al [55], Khattar and Quadri [60], Mendoza et al [61], Ng et al [62], Sayama et al [63], Takenouchi and Choh [64]). Under data veracity problem, the researchers have developed a model towards ensuring that model reliability without much considering the authenticity of the data from contextual viewpoint.…”

Section: R2: What Is the Currently Dominant Research-based Approaches...mentioning

confidence: 99%

See 1 more Smart Citation

Exhaustive Insights Towards Social-Media Driven Disaster Management Approaches

Krishnappa,

Saraswathi,

Chelliah

2024

ijacsa

View full text Add to dashboard Cite

The manuscript presents discussion about the disaster management approaches using social media. It is noted that rising popularity of social media has been witnessed to significantly contribute towards information propagation and community participation to deal with the event of disaster. Different from conventional disaster management policies, the scope of inclusion of social media-based approaches are quite novel and yet promising. However, the problem is towards unclear information about the effectivity of such schemes. Hence, this manuscript contributes towards bridging this information gap by carrying out an exhaustive and systematic review of existing methodology frequently adopted towards disaster management using social media viz. early warning methods, information dissemination methods, crisis mapping method, and predictive approach, where Artificial Intelligence was noted to be quite dominant scheme. The contributory findings of this review study contribute towards clear visualization of updated research trends, critical learning outcomes associated with identified research gap with illustrated discussion of the reviewed articles. A clear and informative study findings contributes towards future researchers. The result of review has also answered the formed research question to give potential insight towards existing system. The result of the review finds that existing approaches has both beneficial aspect and limitation associated with complex learning approaches, higher infrastructural cost, model complexities, security threats, higher resource dependencies.

show abstract

“…Analyzing these multimodal posts together for an event allows the government authorities and humanitarian organizations to assess the post-disaster situation from different angles and perspectives to take appropriate action. While these tweets provide crucial information during an emergency, filtering informative and actionable messages from a vast pool of these noisy messages is challenging [7], [8].…”

Section: Introductionmentioning

confidence: 99%

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

Khattar

Quadri

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

During the past decade, social media platforms have been extensively used during a disaster for information dissemination by the affected community and humanitarian agencies. Although many studies have been done recently to classify the informative and non-informative messages from social media posts, most are unimodal, i.e., have independently used textual or visual data to build the deep learning models. In the present study, we integrate the complementary information provided by the text and image messages about the same event posted by the affected community on the social media platform Twitter and build a multimodal deep learning model based on the concept of attention mechanism. The attention mechanism is a recent breakthrough that has revolutionized the field of deep learning. Just as humans pay more attention to a specific part of the text or image, ignoring the rest, neural networks can also be trained to concentrate on more relevant features through the attention mechanism. We propose a novel Cross-Attention Multi-Modal (CAMM) deep neural network for classifying multimodal disaster data, which uses the attention mask of the textual modality to highlight the features of the visual modality. We compare CAMM with unimodal models and the most popular bilinear multimodal models, MUTAN and BLOCK, generally used for visual question answering. CAMM achieves an average F1-score of 84.08%, better than the MUTAN and BLOCK methods by 6.31% and 5.91%, respectively. The proposed crossattention-based multimodal deep learning method outperforms the current state-of-the-art fusion methods on the benchmark multimodal disaster dataset by highlighting the more relevant cross-domain features of text and image tweets. This study affirms that social media platforms become a rich source of multimodal data during a disaster. This data can be utilized to build automated tools for quick filtration of informative messages to assess the post-disaster needs of the affected community and provide timely help.

show abstract

Emerging Role of Artificial Intelligence for Disaster Management Based on Microblogged Communication

Cited by 10 publications

References 0 publications

Effects of the Disastrous Pandemic COVID 19 on Learning Styles, Activities and Mental Health of Young Indian Students - A Machine Learning Approach

Effects of the Disastrous Pandemic COVID 19 on Learning Styles, Activities and Mental Health of Young Indian Students - A Machine Learning Approach

Exhaustive Insights Towards Social-Media Driven Disaster Management Approaches

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

Contact Info

Product

Resources

About