On the way to a science intelligence: visualizing TEL tweets for trend detection

摘要: This paper presents an adaptable system for detecting trends based on the micro-blogging service Twitter, and sets out to explore what extent such a tool can support researchers. Twitter has high uptake in scientific community, but there is need means of extracting most important topics from stream. There are too many tweets read them all, no organized way keeping up with backlog. Following cues visual analytics, we use visualizations show both temporal evolution topics, relations between different topics. The Trend Detection was evaluated domain Technology Enhanced Learning (TEL). evaluation results indicate that our prototype supports trend detection reveals refined preprocessing, further zooming filtering facilities.