Answers are grounded in this paper and cite their sources.
Many novel applications have been built based on analyzing tweets about specific topics. While these applications provide different kinds of analysis, they share a common task of monitoring "target" tweets from the Twitter stream for a topic. The current solution for this task tracks a set of manually selected keywords with Twitter APIs. Obviously, this manual approach has many limitations. In this paper, we propose a data platform to automatically monitor target tweets from the Twitter stream for any given topic. To monitor target tweets in an optimal and continuous way, we design Automatic Topic-focused Monitor (ATM), which iteratively 1) samples tweets from the stream and 2) selects keywords to track based on the samples. To realize ATM, we develop a tweet sampling algorithm to sample sufficient unbiased tweets with available Twitter APIs, and a keyword selection algorithm to efficiently select keywords that have a near-optimal coverage of target tweets under cost constraints. We conduct extensive experiments to show the effectiveness of ATM. E.g., ATM covers 90% of target tweets for a topic and improves the manual approach by 49%.
No takes yet. Share an insight, caveat, or question.
Li et al. (2013) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: