Best paper award 5th International Conference on Social Informatics!
all from COMMIT/project INFINITI (Information retrieval for information services), win the best paper award for their paper "Automatic thematic content analysis: Finding frames in news” at the 5th International Conference on Social Informatics (SocInfo2013), in Kyoto, Japan.
What is special about the paper?
When COMMIT/ asked Daan Odijk why he thought this paper won the award, he responded: “What I find good about this article is that it is highly embedded in both the Communication Science (Social) and the Information Retrieval (Informatics) and thus particularly relevant for Social Informatics".
Automatic thematic content analysis: Finding frames in news
Framing in news is the way in which journalists depict an issue in terms of a "central organizing idea." We explore the automatic classification of four generic news frames:
- conflict;
- human interest;
- economic consequences and
- morality.
Complex characteristics of messages such as frames have been studied using thematic content analysis. Indicator questions are formulated, which are then manually coded by humans after reading a text and combined into a characterization of the message.
Two-stage automatic classification approach
Inspired by the way-of-working of media analysts, we propose a two-stage automatic classification approach, where we first rate a news article using indicator questions for a frame and then use the outcomes to predict whether a frame is present. We approach human accuracy on almost all indicator questions and frames.
INFINITI (Information Retrieval for Information Services)
Ook dit is een COMMIT/project.