Extractive summarization using complex networks and syntactic dependency

► In this paper we have enhanced the statistics-based methods introducing new measurements of network topology and dynamics. ► For the first time, we used the diversity, betweenness and vulnerability to analyze texts. ► A better performance in automatic summarization is achieved in comparison to previous work employing complex networks. ► We have showed that the diversity measurement generates good summarizers because it usually choose good candidates for keywords.