Without formal structure data are those that have no prearranged form or structure and are full of textual data. Typical unstructured systems include emails, reports, telephone or messaging conversations, etc. The main goal of this work is to extract the keywords from a conversation using Swarm Intelligence (SI) techniques. Keywords are grouped together under their classification and then suggested to the user. In proposed work, by using crisscross searching techniques, keywords are easy to search and provide some important top keywords. Separate algorithms are used for searching and clustering. Firefly algorithm is used for clustering to identify similar related keywords. Finally the results show that SI techniques have a better effect and convergence performance compared with existing diverse keyword extraction technique.