@damiantrilling@akademienl.social avatar

damiantrilling

@[email protected]

Asscoiate Professor at the Department of Communication Science at University of Amsterdam (UvA). Investigates news flows (https://newsflows.eu) and develops and applies computational communication science methods. Wrote a book on #python and #rstats for analyzing communication

This profile is from a federated server and may be incomplete. Browse more on the original instance.

damiantrilling, to communicationscholars Dutch
@damiantrilling@akademienl.social avatar

It can take a long time before papers get out, but in the last week, three that have been on the one way for quite some time got out in which I had the honour to be involved: One on news sharing on Facebook, one on the multilingual classification of online news, and one on transfer learning in communication science 1/4
@communicationscholars @commodon

damiantrilling,
@damiantrilling@akademienl.social avatar

2/3 In "Drivers of News Sharing", @erikknudsen and I use a conjoint experiment to show what drives news sharing on Facebook (spoiler alert: it's not mainly political agreement/selective exposure). Read the full study here: https://doi.org/10.1080/21670811.2023.2255224
@communicationscholars @commodon

damiantrilling,
@damiantrilling@akademienl.social avatar

3/4 In "URLs can facilitate machine learning classification of news stories across languages and contexts", @ernestodeleon @susanvermeer and I show how one can leverage the URLs of news stories to learn whether they are political or not - even if not all URLs are containing information about the 'politicalness' of the story. The approach does not require very little resources and limited technical expertise only @communicationscholars @commodon

damiantrilling,
@damiantrilling@akademienl.social avatar

4/4 Finally, in "Advancing Automated Content Analysis for a New Era of Media Effects Research: The Key Role of Transfer Learning", @annekroon Kasper Welbers, @vanatteveldt and I summarize how Large Language Models and Transfer learning can profoundly change media effects research, and how we need to update our toolbox to incorporate these developments @communicationscholars @commodon

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • random
  • uselessserver093
  • Food
  • aaaaaaacccccccce
  • test
  • CafeMeta
  • testmag
  • MUD
  • RhythmGameZone
  • RSS
  • dabs
  • KamenRider
  • Ask_kbincafe
  • TheResearchGuardian
  • KbinCafe
  • Socialism
  • oklahoma
  • SuperSentai
  • feritale
  • All magazines
    •