ML-EPIC: Collection and Translation of Multilingual Social Media Data

Data-intensive systems are powerful platforms for collecting and exploring big data. Project EPIC (Empowering the Public with Information in Crisis) has been designing and developing data-intensive systems in support of crisis informatics research since Fall 2009. However, Project EPIC (https://epic.cs.colorado.edu/) has always focused on collecting and analyzing tweets written in English, which raises an interesting question: how do we collect and get insight into tweets from multiple languages during crisis events? We report on our efforts to design and develop a multilingual cloud-based analytical platform---ML-EPIC---which enhances Project EPIC's ability to perform crisis informatics research on global events. More generally, our research provides insight into tackling the challenges of big data in a multilingual context.