Visual support for text information retrieval based on matrix's singular value decomposition

The paper presents a prototype visualization system for text information retrieval and its technical details on algorithm design. The system supports the user in constructing an initial query type and further refining the query by visual interaction. Visualization of text information retrieval is an attractive research area in information retrieval. There are many mathematical algorithms used for information retrieval. The authors investigate an approach to construct visual representations based on singular value decomposition (SVD) of matrices and implement visual interfaces using Java. Experimental results show the feasibility of the proposed approach. The ideas in this approach can also be helpful in other visualization environments.