OutdoorSent: Sentiment Analysis of Urban Outdoor Images by Using Semantic and Deep Features

Autor(es)

de Oliveira, Wyverson Bonasoli ^[1] ; Dorini, Leyza Baldo ^[1] ; Minetto, Rodrigo ^[1] ; Silva, Thiago H. ^[2]

Afiliação do(s) autor(es)

^[1] Univ Tecnol Fed Parana, DAINF, Av 7 Setembro 3165, BR-80230901 Curitiba, Parana - Brazil

^[2] Univ Toronto, Myhal Ctr, Suite 853, 55 St George St, Toronto, ON M5S 0C9 - Canada

• Tipo de documento: Artigo Científico
• Fonte: ACM TRANSACTIONS ON INFORMATION SYSTEMS; v. 38, n. 3 JUN 2020.
• Citações Web of Science: 0

Resumo

Opinion mining in outdoor images posted by users during different activities can provide valuable information to better understand urban areas. In this regard, we propose a framework to classify the sentiment of outdoor images shared by users on social networks. We compare the performance of state-of-the-art ConvNet architectures and one specifically designed for sentiment analysis. We also evaluate how the merging of deep features and semantic information derived from the scene attributes can improve classification and cross-dataset generalization performance. The evaluation explores a novel dataset-namely, OutdoorSent- and other publicly available datasets. We observe that the incorporation of knowledge about semantic attributes improves the accuracy of all ConvNet architectures studied. Besides, we found that exploring only images related to the context of the study-outdoor, in our case-is recommended, i.e., indoor images were not significantly helpful. Furthermore, we demonstrated the applicability of our results in the United States city of Chicago, Illinois, showing that they can help to improve the knowledge of subjective characteristics of different areas of the city. For instance, particular areas of the city tend to concentrate more images of a specific class of sentiment, which are also correlated with median income, opening up opportunities in different fields. (AU)

• Processo FAPESP: 18/23011-1 - GoodWeb: uso de sensoriamento social para aprimorar a qualidade de vida em cidades e alavancar novos serviços
• Beneficiário: Thiago Henrique Silva
• Modalidade de apoio: Auxílio à Pesquisa - Regular