Filtering Tweets for Social Unrest
This work addresses the need for efficient tweet filtering for downstream analysis in social unrest monitoring, but it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of filtering Arabic tweets for social unrest relevance by training a supervised classifier, achieving high reliability and optimizing performance with training data size and confidence thresholds.
Since the events of the Arab Spring, there has been increased interest in using social media to anticipate social unrest. While efforts have been made toward automated unrest prediction, we focus on filtering the vast volume of tweets to identify tweets relevant to unrest, which can be provided to downstream users for further analysis. We train a supervised classifier that is able to label Arabic language tweets as relevant to unrest with high reliability. We examine the relationship between training data size and performance and investigate ways to optimize the model building process while minimizing cost. We also explore how confidence thresholds can be set to achieve desired levels of performance.