Presenter: Kênia Carolina
Friday, 26 February, 11:30 PM
Location: Sala Grande Covivio, Corso Ferrucci 112
ABSTRACT
Kênia is a PhD candidate in Computer Science, in a joint program between UFMG, Brazil, and UniTo, Italy. She has worked in the field of computing for over 20 years, having worked in software development, project management, and teaching in various disciplines. She is returning to academia as a PhD candidate to study and promote the particularities of children and adolescents on social media platforms. Currently, Kênia is part of the LOCUS research laboratory in Brazil, led by Professor Jussara Almeida, focusing on Social Computing, and the Content Centered Computing (CCC) group at UniTo with Professor Viviana Patti.
BIOGRAPHY
Children and adolescents are increasingly connected, mainly through social media. Children have specific vulnerabilities regarding the use of social media and the potential harm to which they may be exposed. Our current objective is to present a comprehensive assessment of the properties of content directed at children on various popular social media platforms, aiming to generate fundamental knowledge, mainly related to potential harms, that can guide us in future developments of tools to protect them in the online world. I will show the main results obtained so far from our characterizations and our proposal for constructing a taxonomy to identify potential harms for children and adolescents on social media. The use of unsupervised machine learning automatic detection techniques based on similarity between datasets will be explored with the final aim of triggering alerts about potential immediate damage, and the ambition of detecting subtle and insidious cases beyond the obvious and explicit manifestations of harm.