Past
Models, Misfires, and Meaningful Nulls: Computational Explorations in Platform Governance Research
Date & Time
04/03/2026 1:15 pm – 2:45 pm
Maria Arango-Kure
Jönköping International Business School
I’m a doctoral candidate at Jönköping International Business School (JIBS), affiliated with the Media, Management and Transformation Centre (MMTC). My research explores how digital technologies shape institutions, influence, and ethical boundaries in complex and evolving ways.
My dissertation examines platform dynamics in the media industry, particularly how interactions between actors, algorithms, institutions, and infrastructures relate to what is perceived as legitimate, ethical, or possible in digital environments. I employ a mixed-methods approach, combining computational and interpretive methods, to analyze these dynamics and their implications for governance, communication, and social outcomes.
More broadly, my work examines the ethical dimensions of digital systems: how they frame information, constrain agency, and distribute harm. I also contribute computational methodological expertise to collaborative interdisciplinary projects.
About the Event
In this seminar, Maria opens the garage door on their computational workflow. Drawing on a longitudinal study of platform governance, they present three modeling efforts: a multi class transformer classifier for identifying organizational values in corporate text, a clickbait classifier to trace editorial shifts over time, and embedding based topic models for analyzing legitimation strategies.
Maria walks through what worked, what did not, and what remains to be seen. Going over he practical decisions behind each approach, including corpus construction, annotation, model selection, parameter tuning, and validation, and what happens when the computational part runs beautifully but the interpretive work reveals that there is, substantively, nothing there.
The session creates space for an honest conversation about operationalizing abstract concepts, diagnosing model behavior, and interpreting meaningful null results in computational platform research.
Sign up to our seminars calendar
When you sign up, we’ll email you a link to the Data Methods Initiative Events Calendar Feed, where you can access Zoom links and stay updated on all future seminars.
You can also subscribe to our newsletter to receive detailed information, event reminders, and the latest news about our initiative directly in your inbox.
Your data is safe with us—we’ll never share it with anyone else. You can unsubscribe from our emails anytime by using the link in our emails.
For more details, check out our Privacy Notice.