Earticle

In recently years, there has been rapid growth in discussion groups and micro blogging, in which an important characteristic of the entries is their trending topics on some generalized categories. Many researchers have attempted to classify trending topics by using only keywords, trending topics are rarely straightforward; they are normally expressed in a more subtle manner. It is well accepted that using high-dimensional multi-modal language features for tweets content representation and classifier training may achieve more sufficient characterization of the diverse properties of the tweets and further result in higher discrimination power of the classifiers. However, training the classifiers in a high-dimensional multi-modal feature space requires a large number of labeled training tweets, which will further result in the problem of curse of dimensionality. To tackle this problem, a hierarchical feature subset selection algorithm need to be used to enable more accurate tweets classification; where the processes for feature selection and classifier training are seamlessly integrated in a single framework. In this article, we used the LingPipe classifier to accurately classify the Twitter trending topics where it shows a substantial improvement over their state-of-the art trending topics-trained counterparts.