Affiliations: GIBIS Lab., Instituto de Ciência e Tecnologia, Universidade Federal de São Paulo, Campus de São José dos Campos, CEP 12231-280, São José dos Campos, SP, Brazil
Correspondence:
[*]
Corresponding author. Elder Donizetti dos Santos, GIBIS Lab., Instituto de Ciência e Tecnologia, Universidade Federal de São Paulo, Campus de São José dos Campos, CEP 12231-280, São José dos Campos, SP, Brazil. Tel.: +55 12 3924 9782; E-mail: [email protected].
Abstract: Online social networks like Instagram has more than 600 million users and creates over 300 million new posts every day. All those data can be used to detect real world events. Many works have been proposed in the literature to detect such events using different techniques, but this task is still hard. It involves many challenges including the processing of large volumes of data, the lack of a ground truth and the need for an adaptive approach. In this sense, our work attempts to tackle these problems with a semi-supervised learning approach to overcome those challenges using times series from Instagram posts. Experimental studies demonstrate that similar time series can be used to generalize the knowledge and predict the occurrence of an event. Also, we demonstrate that Support Vector Regression is a good alternative to Gaussian Process Regression as the first provides good results using much less computing resources than the second. Moreover, we made our labeled dataset public, hoping it can be useful to other researchers as well.
Keywords: Event detection, social networks, Instagram, Pearson correlation
It is about how to detect events (like riots, car accidents, political protests, etc) in real time in a scalable and fast way using Instagram as a source of data
Why is it important?
This work presents a novel approach which is more scalable and faster than the current options.
