BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.pydata.org//pydataglobal2025//speaker//UYRBHX
BEGIN:VEVENT
SUMMARY:Text Mining Orkut’s Community Data with Python: Cultural Memory
 \, Platform Neglect\, and Digital Amnesia - Rodrigo Silva Ferreira
DTSTART:20251209T160000Z
DTEND:20251209T163000Z
DTSTAMP:20261006T033743Z
UID:pretalx-pydataglobal2025-QHTA73@cfp.pydata.org
DESCRIPTION:*Orkut* was once the emotional and cultural core of Brazil’s
  internet. Its scraps\, testimonials\, and communities gave users a way to
  publicly shape identity\, build relationships\, and engage with everythin
 g from music and religion to politics and humor. When Google shut it down 
 in 2014\, most of its data was deleted. What remains today is fragmented a
 nd buried in the Wayback Machine.\n\nIn this talk\, I use Python to recove
 r and analyze limited traces of *Orkut*’s digital legacy. I scraped thou
 sands of community names from archived HTML using `requests` and `Beautifu
 lSoup`\, processed them with multilingual sentence embeddings from `senten
 ce-transformers`\, and applied `scikit-learn` and `BERTopic` to cluster th
 e data\, surface major social themes\, and quantify them. These techniques
  reveal how users created meaning\, formed subcultures\, and expressed ide
 ntity through online interactions.\n\nAlongside the technical walkthrough
 \, I draw on Cory Doctorow’s concept of *enshittification*\, defined as 
 the slow decline of platforms as they shift from serving users to exploiti
 ng them. *Orkut* is a case of *enshittification* by neglect: its shutdown 
 led not just to the death of a platform\, but to the erasure of a generati
 on’s digital memory. According to Google's farewell announcement\, over 
 its 10 years of existence\, *Orkut* hosted 51 million communities\, 120 mi
 llion discussion topics\, and more than 1 billion interactions\; most of w
 hich were permanently deleted.\n\nThis talk is for Python users interested
  not only in working with social media text data but also in uncovering th
 e cultural narratives embedded within it. It invites the audience to see d
 atasets as more than technical artifacts\, viewing them instead as living 
 records of online social life.
LOCATION:General Track
URL:https://cfp.pydata.org/pydataglobal2025/talk/QHTA73/
END:VEVENT
END:VCALENDAR