Cloud Enabled Social Media Analytics Framework for Crisis Management

Artificial Intelligence and Data Engineering (AIDE)Lab

39 followers.

This project aims to develop a cloud-based computing framework that will systematically monitor, collect and integrate disaster and crisis-related data streams from diverse social network channels, and turn them into actionable intelligence in a knowledge-base for intelligent inferencing, crisis handling, and decision making. The key components of the proposed framework are three: First, the collection of multilingual and multimodal data (text, audios, videos, images, and location information or other sensor-data) and their conversion into a unified machine-understandable dynamic knowledge-base. Second, the application of Natural Language Processing (NLP), Data Mining, Machine Learning, and Artificial Intelligence techniques for automatic identification, prediction, and detection of any type of crisis or disaster using the unified knowledge-base from the previous stage. 3) Third, the development of an interactive dashboard visualization to facilitate crisis monitoring and management.

check New check Scoping check Scoping QA check Staffing check In progress check Final QA done_all Completed
Volunteers are working on this project

Project scope (as of June 19, 2020, 6:43 a.m.)

Project goal(s)

• Develop a big data analytics framework for dynamic knowledge extraction from heterogeneous sources, and information from social media channels, in order to facilitate disaster related operations and activities. • Develop and deploy a Crisis Management Ontology and dynamic knowledge base to facilitate effective knowledge extraction and representation.
• Develop and deploy semantic data models to facilitate effective knowledge interpretation and integration into a unified data model, so that human experts can easily navigate through the knowledge repository. • Apply relevant artificial intelligence and machine learning algorithms for automatic reasoning, inference and effective visualization of data to facilitate the efforts of decision-making needed by human experts. • Demonstrate the effectiveness of automatically extracted knowledge from structured, semi-structured and unstructured data and information by applying such knowledge in creating values for the management of disaster-related activities.

Interventions and Actions

The research team will provide all the resources required to complete this project.

Data

Data will be collected from Twiter using keywords on COVID-19 and bounded box locations for Saudi Arabia. The main purpose is assessing what measures government is taking for COVID-19 risk mitigation and how the public is responding to those policies and observing whether such policies have any impact on disease prevention and transmission.

Analysis Needed

Identifying COVID-19 related themes and mapping those themes into location-based maps Classifying those themes into different humanitarian-based classes so that humanitarian organization map them into a specific need Identifying location hot spot identifying useful links, donation organizations for specific needs

Validation Methodology

AI-based prediction solution will be compared with ground truth data published by the Saudi Government

Implementation

After implementation, the solution would be deployed with humanitarian organizations such as the emergency response department in the ministry of civil defense.
An interface will be provided to the public, where the public notification will be posted by humanitarian organizations.

Scope version notes