Abstract:
With the recent rise in electronic data, and the pressing time needs of daily life, there is scope for a good document clustering system that can divide a set of documents into similar topic clusters. A lot of different algorithms have been attempted towards this end, from statistical learning methods to neural networks. In more recent years, there has been a growing interest in collective intelligence as often displayed in nature by ants and birds. We would like to do a survey of this last field, and look for possible applications of algorithms in this area for the document clustering problem.
