Text Mining using Non-Negative Matrix Factorizations

Abstract

Previous chapter Next chapter Full AccessProceedings Proceedings of the 2004 SIAM International Conference on Data Mining (SDM)Text Mining using Non-Negative Matrix FactorizationsV. Paul Pauca, Farial Shahnaz, Michael W. Berry, and Robert J. PlemmonsV. Paul Pauca, Farial Shahnaz, Michael W. Berry, and Robert J. Plemmonspp.452 - 456Chapter DOI:https://doi.org/10.1137/1.9781611972740.45PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract This study involves a methodology for the automatic identification of semantic features and document clusters in a heterogeneous text collection. The methodology is based upon encoding the data using low rank non-negative matrix factorization algorithms to preserve natural data non-negativity and thus avoid subtractive basis vector and encoding interactions present in techniques such as principal component analysis. Some existing non-negative matrix factorization techniques are reviewed and some new ones are proposed. Numerical experiments are reported on the use of a hybrid NMF algorithm to produce a parts-based approximation of a sparse term-by-document matrix. The resulting basis vectors and matrix projection can be used to identify underlying semantic features (topics) and document clusters of the corresponding text collection. Previous chapter Next chapter RelatedDetails Published:2004ISBN:978-0-89871-568-2eISBN:978-1-61197-274-0 https://doi.org/10.1137/1.9781611972740Book Series Name:ProceedingsBook Code:PR117Book Pages:xiv + 537Key words:text mining, non-negative matrix factorization, clustering, dimension reduction, semantic feature identification