Principal Component Analysis in Topic Modelling of Short Text Document Collections

This paper presents the motivation for and the preliminary theoretical investigations of the PhD project by the first author. The objective of the research is to propose and to experimentally verify the approach of application of eigendecomposition in principal component analysis for topic modelling of short text document collections. The main hypothesis examined in this project, is that principal component analysis applied to word co-occurrence statistics turns topic modelling into well-defined problem having unique solution with natural fitting parameters. The project is performed at the Dept. of Computer Science of Zaporizhzhya National University.