A concept-driven algorithm for clustering search results

The Lingo algorithm combines common phrase discovery and latent semantic indexing techniques to separate search results into meaningful groups. It looks for meaningful phrases to use as cluster labels and then assigns documents to the labels to form groups. The algorithm uses the vector space model (VSM) and singular value decomposition (SVD) method. VSM is a method of information retrieval that uses linear-algebra operations to compare textual data. Unlike VSM, LSI aims to represent the input collection using concepts found in the documents rather than the literal terms appearing in them.