Innovative Social Data Science research based on digital methods, computational tools, qualitative analyses and
statistical techniques
Monitored Ecosystem
NetLab's multidisciplinary team has developed its own infrastructure for data collection and constant monitoring of platforms and websites. This system is continuously updating to adapt to frequent changes in platform data sharing policies and interfaces.
​
Our infrastructure, a one of it's kind in Brazil, is capable of constantly monitoring profiles and themes according to the Laboratory's research agenda.
​
We currently collect data from X/Twitter, Instagram, Facebook, YouTube, TikTok, WhatsApp, Telegram, Google Ads and Meta Ads, as well as professional news portals, local vehicles and junk news.
Data
Collection
& Analysis
Despite the important role digital platforms play today in shaping public opinion, transparency and public understanding about how they work are disproportionate to the potential impact they can have on social life.
The digital data we collect is processed and analyzed by our researchers. From this information, we provide evidence and insights into the the phenomenon of online disinformation to support the fight against public opiniom manipulation strategies in Brazil, informing the public and governance policies that generate a real impact on society.
Methods, Analysis & Development
NetLab UFRJ develops social science methods to expand, create and implement research strategies in order to empirically and critically investigate the effects of the media ecosystem on public opinion - including mass media, alternative media, hyperpartisan media, news websites fakes and social media.
Based on the theoretical-conceptual framework of digital methods, our research combines various qualitative and quantitative analyses with a non-obtrusive approach. In non-obstructive observation, data are collected without researchers interfering with the object of study. This data, known as “digital traces”, provides indicators about type and ammount of social interactions on platforms.
Taking an interdisciplinary perspective, we combine traditional social science research approaches with innovative approaches, including the development of AI, algorithms and computational solutions for social data analysis. We develop customized machine learning computational tools to detect harmful agents, fraudulent strategies and identify problematic content.