An Improved Single-Pass Topic Detection Method
Qian Zhou, Lei Shi, Liancheng Xu, Wenfeng Liu · 2018
In recent years, with the rapid growth of microblog's data, it is a challenging task to mine important hidden topics from massive data. In the task of topic detection, we first extract the feature words of a Microblog content by the method of feature extraction; Secondly, the improved single-pass clustering algorithm was used to compare the similarities between the extracted feature words and the texts afterwards. According to the set threshold, the topic was divided into different coarse and fine granularity levels. Ultimately effective microblogging topic detection. Experiments shows that this method can effectively improve the rate of topic detection and can detected different granularity topics according to the threshold.