Automated Disaster Monitoring From Social Media Posts Using AI-Based Location Intelligence and Sentiment Analysis

Abstract

Worldwide disasters like bushfires, earthquakes, floods, cyclones, heatwaves etc. have affected the lives of social media users in an unprecedented manner. They are constantly posting their level of negativity over the disaster situations at their location of interest. Understanding location-oriented sentiments about disaster situation is of prime importance for political leaders, and strategic decision-makers. To this end, we present a new fully automated algorithm based on artificial intelligence (AI) and Natural Language Processing (NLP), for extraction of location-oriented public sentiments on global disaster situation.We designed the proposed system to obtain exhaustive knowledge and insights on social media feeds related to disaster in 110 languages through AI and NLP based sentiment analysis, named entity recognition (NER), anomaly detection, regression, and Getis Ord Gi * algorithms. We deployed and tested this algorithm on live Twitter feeds from 28 September 2021 till 6 October 2021. Tweets with 67,515 entities in 39 different languages were processed during this period. Our novel algorithm extracted 9727 location entities with greater than 70% confidence from live twitter feed and displayed the locations of possible disasters with disaster intelligence. The rates of average precision, recall and F1-Score were measured to be 0.93, 0.88 and 0.90 respectively. Overall, the fully automated disaster monitoring solution demonstrated 97% accuracy. According to the best of our knowledge, this study is the first to report location intelligence with NER, sentiment analysis, regression and anomaly detection on social media messages related to disasters and has covered the largest set of languages.

AI-Tornado: An AI-based Software for analyzing Tornadoes from disaster event dataset

“…For obtaining AI-based insights, AI-Tornado uses two different types of regression analysis (i.e., linear regression and logistic regression as depicted in [1,[8][9][10][11][12]) with MS Power BI's Key influencers visual. Using these automated regression algorithms, factors related to Tornado associated deaths are identified and explained as shown in Fig.…”

“…For identifying the key factors, their correlations, and NLP based explanations, Microsoft Power BI's Key Influencer visualization is used, where linear and logistic regressions are automatically performed (As seen from Table 1). Using Microsoft Power BI's Key Influencer for performing AI driven automatic regression was demonstrated in our previous studies [1,[8][9][10][11][12].…”

“…Policy makers and town planner can also benefit from such system on developing evidence-based guidance for disaster policy implementation [1,[7][8][9]. Based on the created scenario, data statistics could be shown (using Get Data Statistics feature) or Tornado events could be analyzed.…”

“…Hence, for their decision-making process they are heavily dependent on the advices from expert data scientists, who manually execute AI models and then summarize the results. These dependencies and delegations of tasks often cause significant delays in decision making [1,[8][9][10][11][12]. AI-Tornado allows the disaster strategists and planners to directly interact with the intuitive interface for obtaining AI driven Tornado insights in plain english language obviating the dependencies on the manual work of data scientists [1].…”

“…It should be noted that MS Power BI is freely available for download from https: //app.powerbi.com/. In future, we endeavor to combine this tornado event-based dataset with social media-based tornado data (as reported in our recent research [9]) for performing deep learning. As shown in our recent studies, deep learning algorithms like Convolutional Neural Network (CNN) based anomaly detection can provide comprehensive understanding of disaster features [7][8][9]15].…”