CitizenHelper-Adaptive: Expert-Augmented Streaming Analytics System for Emergency Services and Humanitarian Organizations

There is an increasing amount of information posted on Web, especially on social media during real world events. Likewise, there is a vast amount of information and opinions posted about humanitarian issues on social media. Mining such data can provide timely knowledge to inform disaster resource allocation for who needs what and where as well as policies for humanitarian causes. However, information overload is a key challenge in leveraging this big data resource for organizations. We present an interactive user-feedback based streaming analytics system `CitizenHelper-Adaptive' to mine social media, news, and other public Web data streams for emergency services and humanitarian organizations. The system aims to collect, organize, and visualize the vast amounts of data across various user and content-based information attributes using the adaptive machine learning models, such as intent classification models to continuously identify requests for help or offers of help during disasters. This demonstration shows the first application of transfer-active learning methods for time-critical events, when there is an availability of abundant labeled data from past events but a scarcity of the sufficient labeled data for the ongoing event. The proposed system provides a user interface to solicit expert feedback on the predicted instances from pretrained models and actively learns to improve the models for efficient information processing and organization. Finally, the system regularly updates the predicted information categories in the visualization dashboard. We will demo CitizenHelper-Adaptive system for case studies in both mass emergency events and humanitarian related topics such as gender violence using datasets of more than 50 million Twitter messages and news streams collected between 2016 and 2018.