Recently I’ve been thinking of ways to detect bias as well as look into what makes people share. Yes understanding dynamics and trends over time, like the chart below (Topsy is a great simple, free easy tool to get basic Twitter trends), can be helpful – especially with forecasting. None the less they reach their limits when we want to look for deeper meaning – say at the cognitive or “information flow” level.
Enter coordinates and networks. The advantages are not possible to do with a tradition KPI’s like volume over time. Through mapping out the a network based on entities, extracted locations and similar text and language characteristics it’s possible to map coordinates of how a headlines, entities or article exists in space within the specific domain. And this happens to deadly representative of the physical world.. especially since more information is reported online everyday.
When put together (shown below), I found a way to detect bias. Using to online news articles and Bit.ly link data, I found articles with less centrality to their domain, which denote variables being left out (of the article), typically got shared the most on social channels. In short some bias = more sharing… Interesting – although more research is needed.