PROJECT TITLE :

Exploring Evolving Media Discourse Through Event Cueing

ABSTRACT:

Online news, microblogs and alternative media documents all contain valuable insight regarding events and responses to events. Underlying these documents is that the concept of framing, a method in which communicators act (consciously or unconsciously) to construct a point of read that encourages facts to be interpreted by others during a particular manner. As media discourse evolves, how topics and documents are framed can undergo change, shifting the discussion to totally different viewpoints or rhetoric. What causes these shifts will be tough to determine directly; but, by linking secondary datasets and enabling visual exploration, we have a tendency to will enhance the hypothesis generation process. During this paper, we gift a visible analytics framework for event cueing using media knowledge. As discourse develops over time, our framework applies a time series intervention model which tests to work out if the amount of framing is different before or when a given date. If the model indicates that the times before and once are statistically significantly completely different, this cues an analyst to explore related datasets to assist enhance their understanding of what (if any) events may have triggered these changes in discourse. Our framework consists of entity extraction and Sentiment Analysis as lenses for information exploration and uses 2 completely different models for intervention analysis. To demonstrate the usage of our framework, we tend to gift a case study on exploring potential relationships between climate change framing and conflicts in Africa.