calcDPC: An Algorithm for Analysing Psycholinguistics Aspects in Machine Translations

This work presents calcDPC, an algorithm to analyze psychological and linguistic changes in texts translated from English to Brazilian Portuguese, and compare differences between automatic and human-translated texts. For this purpose, we use the Brazilian Portuguese version of a tool named LIWC, that distributes lexical words in categories with linguistic and psychological characteristics. By counting words in categories, this work seeks to evaluate the percentage of psycholinguistic changes in automatically translated texts and compare them with a reliable translation performed by a human expert. In this way, this study aims to contribute to the improvement of automatic translation tools. Experimental results indicate promising directions for further research.