Dataset: Conectando Personagens, Revelando Gêneros — Uma Análise Computacional da Literatura em Português

Dataset and code for the article Conectando Personagens, Revelando Gêneros: Uma Análise Computacional da Literatura em Português. This repository contains the processed data and Jupyter notebooks used to build and analyze character social networks in a corpus of Portuguese-language literature, investigating gender representation through co-occurrence networks, agency analysis, and named entity recognition (NER). Contents: complete_corpus_data.tar.gz — Full processed data for the complete corpus (592 literary works): NER output, dependency parsing, agency analysis, gender classification, co-occurrence graphs, and result CSVs. new_corpus_data.tar.gz — Processed data for the supplementary new corpus. Pipeline: Raw texts → NER (character extraction) → co-occurrence network construction → gender classification → agency analysis (verb/adjective associations) → social network metrics.