Self-organizing map (SOM) method developed by Kohonen [T. Kohonen, Self-Organizing Maps, Springer Series in Information Sciences, Vol. 30, 1995.] has been applied to problems of chemical analysis using AES, XPS, and XRD (X-ray Diffraction) data. Using two-dimensional SOM, information described qualitatively by linguistic expressions can be explained more quantitatively by the position of the spectral data on the SOM together with the gray level expression. Furthermore, composition of unknown sample can be determined precisely by SOM that has been constructed using spectra from samples of known composition.