Defesa de Exame de Qualificação de Tese de Doutorado de Maxwell Guimarães de Oliveira

postado em 2 de fev. de 2016 06:54 por Coordenação da Pós-graduação em Computação da UFCG
Candidato: Maxwell Guimarães de Oliveira
Título do trabalho: Towards Urban Complaint Identification from Social Media data with focus on Location and Semantics
Orientador(es): Cláudio de Souza Baptista e Cláudio Elízio Calazans Campelo

Data: 24/02/2016
Horário: 9h
Local: Auditório do CEEI

Banca examinadora:(mais detalhes abaixo) Renato Fileto (Universidade Federal de Santa Catarina), Fabio Gomes de Andrade (Instituto Federal da Paraíba), Carlos Eduardo Santos Pires (UFCG), Joseana Macêdo Fechine Régis de Araújo (UFCG).
Resumo: Urban complaints is a term given to reported issues related to the urban infrastructure in cities, such as potholes in a road, rubbish in an unauthorized place, traffic light not working in an intersection, among others. There are many Location-Based Social Networks (LBSN) in the smart cities domain where people share their complaints and local authorities are aware to fix the problems worldwide. Citizens became able to share valuable spatial, temporal and semantic information regarding urban neighborhoods. With the advent of social networks such as Facebook and Twitter, people tend to complain in an unstructured, sparse and unpredictable way, being difficult to let local authorities know about such complaints. Social media data, especially Twitter posts, photos, and check-ins, have played an important role in many fields, including city’s dynamics. However, discovering specific and relevant conversations about certain types of subjects is a challenge which gets worse on processing informal language, vernacular terms and all the noisy data found in social media streams. In this context, this research investigates computational methodologies in order to provide automated identification of urban complaints shared in social media streams. Once identified, such complaints could be semantically and spatially linked in a LBSN and become useful for citizens and authorities. Thus, this project proposes an approach for identification of urban complaints on social media considering both semantic and geographical dimensions, which involves Information Extraction, Geographic Information Retrieval, Volunteered Geographic Information and Domain Ontologies.