In this paper the computational tool called "El Manchador de Textos" is described and exemplified. This tool helps find and highlight co-occurring linguistic features in digital texts and corpus. These features can be visualized in texts through colors, associated to each of these features. The computational tool also helps quantify co-occurring linguistic features producing an index that represents the density of the text prose. As an example of the use of the tool, a research focused on co-occurring informativity features in a diversified sample of texts is conducted (scientific, science popularization and journalistic). The results show statistical differences between the registers, considering the informativity indexes.
|Translated title of the contribution||Informational density in Texts: Computational approach using "El Manchador de Textos"|
|Number of pages||27|
|State||Published - 2008|