This document proposes creating an open dataset of 600 million anonymized Swedish tweets and establishing a collaborative research center to conduct interdisciplinary studies of digital media using computational analysis. It identifies challenges of accessing commercial social media data, requiring technical skills, and enabling collaboration. Example research areas discussed include mapping information diffusion, identifying topics in shared links, measuring social media's role in constructing identity, and analyzing writing styles. The proposal seeks long-term funding to host the dataset and support technical, ethical and administrative needs.
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
New Interdisciplinary Approaches to Analyzing Digital Media Landscapes
1. Twitter, interpretation
and math
New interdisciplinary approaches to large-scale analysis
of the digital media landscape
Mattias Östmar,
independent data scientist
2. Problem 1: Access
• New media data is locked-in by commercial
companies
• E.g. audience studies of news diffusion, digital
antropological studies of cultural expression.
• High costs for buying media data from e.g. GNIP
3. Problem 2: Coding skills
• The data volumes requires technical data-analysis
skills
• E.g. quantitative content analysis of the topics of
millions of news media links shared and
discussed on Twitter.
• Natural Language Processing, Information
Retrieval, API-usage
4. Problem 3: Collaboration
• True interdisciplinary research groups are still ad-
hoc at best
• E.g. social science, computer science and
theology studying the media logics of kindness.
• Technical infrastructure and competence is
scattered geographically and across institutions
5. Why I am doing this
• How do ideas spread?
• How do we construct identity with digital tools?
• Can we measure the “social health” of society?
6. The proposal
• I donate a dataset of 600+ million Swedish
(scrubbed) tweets from 450+ thousand
(anonymized) users
• Seek long-term funding for technical, administrative
hosting in an collaborative academic setting by
initiators at Södertörn University, possibly together
with KTH.
17. Ethics: challenges
• Twitter user privacy, deleted tweets, opinions etc
• Twitter terms of service, API rate limits etc
• Research ethics, types of questions studies etc
18. Ethics: A starting point
• Distant reading by default (structure over meaning)
• Individuals can donate API access to research
• Improve academic institutions data ethics policies!