Serviços Personalizados
Journal
Artigo
Indicadores
- Citado por SciELO
- Acessos
Links relacionados
- Similares em SciELO
Compartilhar
Computación y Sistemas
versão On-line ISSN 2007-9737versão impressa ISSN 1405-5546
Resumo
ORTEGA MENDOZA, Rosa María; FRANCO ARCEGA, Anilú e MONTES Y GOMEZ, Manuel. Author Profiling on Social Media using New Weighting Schemes that Emphasize Personal Information. Comp. y Sist. [online]. 2019, vol.23, n.2, pp.501-510. Epub 10-Mar-2021. ISSN 2007-9737. https://doi.org/10.13053/cvs-23-2-3005.
This paper summarizes the thesis: "Identificación del perfil de autores en redes sociales usando nuevos esquemas de pesado que enfatizan información de tipo personal" whose main idea indicates that terms located in phrases exposing personal information are highly valuable for the AP task. Firstly, it is presented an study on the relevance of this information to this task. Secondly, it is proposed a novel approach, which aims to emphasize the value of this type of terms by two proposals: a feature selection method and a term weighting scheme; both of them are based on a novel measure called personal expression intensity, which estimates the quantity of personal information revealed by each term. The approach was evaluated in age and gender prediction on different social media. The results are encouraging, with average improvements about 7.34% and 5.76% for age and gender identification respectively in comparison with the best results from the state of the art. These results allow concluding that personal information play an important role in the task.
Palavras-chave : Author profiling; term weighting schemes; personal information; PEI; DPP; EXPEI.