The paper describes a study based on diachronic exploration of Romanian texts in order to implement a technology for detecting automatically the morpho-lexical features from 1840 to nowadays. The aim of this survey is to analyse the morphology and lexical-semantics of Romanian language, based on a few Romanian and Moldavian resources, and an algorithm to explain how the language evolved. We investigated the use of a lexicon-based and a learning-based approach to identify morpho-syntactic and semantic items to reconstruct the general trends in the Romanian language evolution. The study is meant to help linguists, specialists and non-specialists in NLP.