Density-Based Clustering of Massive Short Messages Using Domain Ontology

With the rapid development of information technology, huge data is accumulated. A vast amount of such data appears as short messages such as emails in companies or conversations in open chatting rooms. It is useful to find the themes or exceptional information from the messages by clustering the short documents based on density. However, traditional vector space model based text clustering algorithms can not get acceptable accuracy because the key words appear at low frequency. On the other hand, traditional text clustering algorithms become very inefficient or even unavailable when processing massive data at TB level. In this paper a density-based short message clustering algorithm using domain ontology based is presented. This algorithm uses domain ontology to calculate the semantic similarity between short messages which improves the parallel method is also used to get better scalability.