%0 Conference Proceedings
%4 sid.inpe.br/mtc-m16c/2018/12.27.18.33
%2 sid.inpe.br/mtc-m16c/2018/12.27.18.33.17
%@issn 2179-4847
%T Does keyword noise change over space and time? a case study of social media messages
%D 2018
%A Andrade, Sidgley C. de,
%A Degrossi, Livia Castro,
%A Restrepo-Estrada, Camilo,
%A Delbem, Alexandre C. B.,
%A Albuquerque, João Porto de,
%@affiliation Universidade Tecnologia Federal do Paraná (UTFPR)
%@affiliation Universidade de São Paulo (USP)
%@affiliation University of Antioquia
%@affiliation Universidade de São Paulo (USP)
%@affiliation University of Warwick
%@electronicmailaddress sidgleyandrade@utfpr.edu.br
%@electronicmailaddress degrossi@icmc.usp.br
%@electronicmailaddress camilo.restrepo@udea.edu.co
%@electronicmailaddress acbd@icmc.usp.br
%@electronicmailaddress porto@warwick.ac.uk
%E Vinhas, Lúbia (INPE),
%E Campelo, Claudio (UFCG),
%B Simpósio Brasileiro de Geoinformática, 19 (GEOINFO)
%C Campina Grande
%8 05-07 dez. 2018
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 116-121
%X Social media is a valuable source of information for different do- mains, since users share their opinion and knowledge in (near) real-time. More- over, users usually use different words to refer to a particular event (e.g., a rain event). These words may be later employed to filter social media messages re- garding new occurrences of the event and, thus, to reduce the number of unre- lated messages. These words, however, may have different meanings and, thus, may not reduce the number of messages. In this work, we conduct a case study to measure which rain- or flood-related keywords are less relevant to reduce the number of unrelated messages. The results show that the keywords change over space, due to local language/culture, and time, specially in different time scales.
%@language pt
%3 p11.pdf