De 1 de março a 31 de Agosto de 2021, Janna Joceli Omena (ICNOVA) será bolseira de investigação (research fellow) do Center for Advanced Internet Studies (CAIS), Bochum, Alemanha, com o projeto intitulado Computer vision networks. Developing digital visual methods for social and medium research. O projeto propõe o uso de computer vision networks para o estudo de imagens online. A proposta de investigação apresenta dois objetivos principais, que interrogam simultaneamente as potencialidades e limitações das APIs de visão computacional para a investigação social e dos media, ao mesmo tempo que visa desenvolver formas de criação técnica-metodológica com métodos digitais.
Abstract do projeto de investigação:
Computer vision networks are valuable assets to digital research. Afforded by machine learning models and a range of research software, these networks inform new ways of enquiring socio-technological phenomena, providing novel perspectives but also challenges for digital visual methods. Although the automated services for describing large image datasets (either by labels or web entities) and the detection of safe search or sites of image circulation have been serving well big tech companies for many years, the potentialities of computer vision for the purpose of digital network studies are still unknown or little explored. Against this background, this research proposal presents two main objectives, which simultaneously interrogates the potentialities and limitations of computer vision APIs for social and medium research, while aiming to develop forms of technical-methodological creation with digital methods. To achieve this goal, the project will explore what counts in the processes of building and interpreting computer vision networks – here taken as an ensemble of machines, data, methods and research practices. The entanglements of a technical understanding on Vision APIs (application programming interfaces) infrastructure combined with the research practices part of the full range of digital methods (curating, capturing, visualising, analysing and repurposing online data and methods) and visual network exploration are to be taken into account. Through situated case studies, this project aims to shed light on how to read networks of images and their correspondent descriptions, and networks of images and their sites of circulation across the web. The expected results include practical and conceptual research models for using computer vision networks in social and medium research.