Big data analytics for disaster response and recovery through sentiment analysis

Name of the provider (company name or main contact name), or FIRE IN ID ? Ragini, J. Rexiline; Anand, P. M. Rubesh; Bhaskar, Vidhyacharan

CCC addressed

Scope, rationale, context: general description. Precise here if this technology is currently use (eg. company name or contact info) Big data created by social media and mobile networks provide an exceptional opportunity to mine valuable insights from them. This information is harnessed by business entities to measure the level of customer satisfaction but its application in disaster response is still in its inflection point. Social networks are increasingly used for emergency communications and help related requests. During disaster situations, such emergency requests need to be mined from the pool of big data for providing timely help. Though government organizations and emergency responders work together through their respective national disaster response framework, the sentiment of the affected people during and after the disaster determines the success of the disaster response and recovery process. In this paper, we propose a big data driven approach for disaster response through sentiment analysis. The proposed model collects disaster data from social networks and categorize them according to the needs of the affected people. The categorized disaster data are classified through machine learning algorithm for analyzing the sentiment of the people. Various features like, parts of speech and lexicon are analyzed to identify the best classification strategy for disaster data. The results show that lexicon based approach is suitable for analyzing the needs of the people during disaster. The practical implication of the proposed methodology is the real- time categorization and classification of social media big data for disaster response and recovery. This analysis helps the emergency responders and rescue personnel to develop better strategies for effective information management of the rapidly changing disaster environment.

If applicable, choose the relevant working group (Ctrl touch to select more than one)

Please select the relevant item

Short description of the solution. Technical details if relevant. Keywords.

Big data created by social media and mobile networks provide an exceptional opportunity to mine valuable insights from them. This information is harnessed by business entities to measure the level of customer satisfaction but its application in disaster response is still in its inflection point. Social networks are increasingly used for emergency communications and help related requests. During disaster situations, such emergency requests need to be mined from the pool of big data for providing timely help. Though government organizations and emergency responders work together through their respective national disaster response framework, the sentiment of the affected people during and after the disaster determines the success of the disaster response and recovery process. In this paper, we propose a big data driven approach for disaster response through sentiment analysis. The proposed model collects disaster data from social networks and categorize them according to the needs of the affected people. The categorized disaster data are classified through machine learning algorithm for analyzing the sentiment of the people. Various features like, parts of speech and lexicon are analyzed to identify the best classification strategy for disaster data. The results show that lexicon based approach is suitable for analyzing the needs of the people during disaster. The practical implication of the proposed methodology is the real- time categorization and classification of social media big data for disaster response and recovery. This analysis helps the emergency responders and rescue personnel to develop better strategies for effective information management of the rapidly changing disaster environment.

TRL of the proposed solution - Innovation stage (if applicable) Not applicable

Expected/scheduled future developments

published in 2018