Using keywords in the automatic classification of language of gender violence

This paper employs lexical analysis tools, quantitative processing methods, and natural language procedures to analyze samples identify items that support automatic topic detection in processing. discusses how keyword extraction, a technique from corpus linguistics, can be employed obtaining features improve classification; particular, this research is concerned with extracting keywords obtained social networks. The consists of 1,841,385 words subdivided into three sub-corpora have been categorized according the comments each one them. These topics are violence against women, LGBT community, general. has by scraping YouTube videos address issues such as street harassment, femicide, feminist movements, drug trafficking, forced disappearances, equal marriage, among others. tasks performed extracted media showed rendered 98% accuracy when classifying collection 51 videos, categories mentioned above, 92% almost 7,500 individually. When were removed classification task all used perform task, dropped an average 17%. results argument for relevance detection.