Trouble information extraction based on a bootstrap approach from Twitter

摘要

In this paper, we propose a method for extracting trouble information from Twitter. One useful approach is based on machine learning techniques such as SVMs. However, trouble information is a fraction of a percent of all tweets on Twitter. In general, imbalanced distribution is not suitable for machine learning techniques to generate a classifier. Another approach is to extract trouble information by using handwritten rules. However, constructing high coverage rules by handwork is costly. First, we verify these problems in a preliminary experiment. Then, to solve these problems, we apply a bootstrapping method to our trouble information extraction task. We introduce three characteristics and a scoring method to the bootstrapping. As a result, the iteration process on the bootstrapping increased the number of tweets and patterns for trouble information dramatically.