Multi-source domain adaptation of social media data for disaster management

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

doi:10.1007/s11042-022-13456-0

Cited by 7 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An emerging paradigm by leveraging social networks and artificial intelligence (AI) capabilities helps emergency rescuers to gather situational information to provide better disaster management [1][2][3][4]. Contents uploaded during different crises such as biological pandemics (Ebola, Zika, COVID, etc.)…”

Section: Introductionmentioning

confidence: 99%

Let’s explain crisis: deep multi-scale hierarchical attention framework for crisis-task identification

Priya,

Joshi,

Chandra

2024

J Supercomput

View full text Add to dashboard Cite

Emergency services rely heavily on Twitter for early detection of crisis tasks to enhance crisis management systems. However, employing state-of-the-art models often face data sparsity as well as their inadequacy to handle long-range dependencies between tweet tokens. Additionally, the authorities need to gain confidence in the model's prediction so that the detected task information can be better believed and prioritized. In this study, we present a generalized framework named Explainable Attentive model for Crisis Task identification (ExACT) to handle the above mentioned challenges while identifying crisis task relevant tweets as well as provide the model explainability by utilizing a very small corpus of tweets. The novelty of ExACT is three-fold: (1) Data enrichment has been introduced by non-dynamic contextual attributes derived from tweets to overcome the sparsity. (2) Feature enrichment has been incorporated using hierarchical attention at both local and global levels using residual self-attention and correlation attention to capture long-range dependencies. (3) LIME based model explainability approach added to understand the task important tokens. Experiments reveal that ExACT has a competitive performance improvement over various state-of-the-art models in terms of F-measure (𝟐𝟎% and 𝟏𝟒% respectively) and accuracy (𝟏𝟒% and 𝟏𝟔% respectively) across two different crisis tasks infrastructure damage and support signal identification. Consistent performance improvement for two different tasks considered from publicly available crisis event datasets depicts the model's generalizability. While LIME supported explainable mechanism in ExACT can identify the important keywords but does not guarantee a high score in terms of plausibility and faithfulness metrics.

show abstract

Section: Introductionmentioning

confidence: 99%

Let’s explain crisis: deep multi-scale hierarchical attention framework for crisis-task identification

Priya,

Joshi,

Chandra

2024

J Supercomput

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Let’s Explain Crisis: Deep multi-scale Hierarchical Attention framework for Crisis-task Identification

Priya

Joshi

Chandra

2023

Preprint

View full text Add to dashboard Cite

Emergency services rely heavily on Twitter for early detection of crisis tasks to enhance crisis management systems. However, employing state-of-the-art models often face data sparsity as well as their inadequacy to handle long-range dependencies between tweet tokens. Additionally, the authorities need to gain confidence in the model's prediction so that the detected task information can be better believed and prioritized. In this study, we present a generalized framework named Explainable Attentive model for Crisis Task identification (ExACT) to handle the above mentioned challenges while identifying crisis task relevant tweets as well as provide the model explainability by utilizing a very small corpus of tweets. The novelty of ExACT is three-fold: (1) Data enrichment has been introduced by non-dynamic contextual attributes derived from tweets to overcome the sparsity. (2) Feature enrichment has been incorporated using hierarchical attention at both local and global levels using residual self-attention and correlation attention to capture long-range dependencies. (3) LIME based model explainability approach added to understand the task important tokens. Experiments reveal that ExACT has a competitive performance improvement over various state-of-the-art models in terms of F-measure (20% and 14% respectively) and accuracy (14% and 16% respectively) across two different crisis tasks infrastructure damage and support signal identification. Consistent performance improvement for two different tasks considered from publicly available crisis event datasets depicts the model's generalizability. While LIME supported explainable mechanism in ExACT can identify the important keywords but does not guarantee a high score in terms of plausibility and faithfulness metrics.

show abstract

Deep Neural Networks for Wild Fire Detection and Monitoring with UAV

Gewali

Panday

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Multi-source domain adaptation of social media data for disaster management

Cited by 7 publications

References 49 publications

Let’s explain crisis: deep multi-scale hierarchical attention framework for crisis-task identification

Let’s explain crisis: deep multi-scale hierarchical attention framework for crisis-task identification

Let’s Explain Crisis: Deep multi-scale Hierarchical Attention framework for Crisis-task Identification

Deep Neural Networks for Wild Fire Detection and Monitoring with UAV

Contact Info

Product

Resources

About