Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/25429
Autoria: | Vicente, M. Batista, F. Carvalho, J. P. |
Editor: | Carvalho, J. P., Lesot, M.-J., Kaymak, U., Vieira, S., Bouchon-Meunier, B., and Yager, R. R. |
Data: | 2016 |
Título próprio: | Creating extended gender labelled datasets of Twitter users |
Volume: | 611 |
Paginação: | 690 - 702 |
Título do evento: | 16th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2016 |
ISSN: | 1865-0929 |
ISBN: | 978-3-319-40581-0 |
DOI (Digital Object Identifier): | 10.1007/978-3-319-40581-0_56 |
Palavras-chave: | Gender classification Twitter users Gender database Text mining |
Resumo: | The gender information of a Twitter user is not known a priori when analysing Twitter data, because user registration does not include gender information. This paper proposes an approach for creating extended gender labelled datasets of Twitter users. The process involves creating a smaller database of active Twitter users and to manually label the gender. The process follows by extracting features from unstructured information found on each user profile and by creating a gender classification model. The model is then applied to a larger dataset, thus providing automatic labels and corresponding confidence scores, which can be used to estimate the most accurately labeled users. The resulting databases can be further enriched with additional information extracted, for example, from the profile picture and from the user location. The proposed approach was successfully applied to English and Portuguese users, leading to two large datasets containing more than 57K labeled users each. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | IT-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
conferenceobject_30894.pdf | Versão Aceite | 1,84 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.