Wouldn’t it be great to extract meaning from an unread document? TextArc is a remarkable step towards advancing that goal.

A TextArc is a visual representation of a text—the entire text (twice!) on a single page. A funny combination of an index, concordance, and summary; it uses the viewer’s eye to help uncover meaning . . .
TextArc is a tool designed to help people discover patterns and concepts in any text by leveraging a powerful, underused resource: human visual processing. It compliments approaches such as Statistical Natural Language Processing and Computational Linguistics by providing an overview, letting intuition help extract meaning from an unread text. . .

TextArc represents the entire text as two concentric spirals on the screen: each line is drawn in a tiny (one pixel tall) font around the outside, starting at the top; then each word is drawn in a more readable size. . . Frequently used words stand out from the background more intensely. . .

Some words appear inside the spirals. This is the key organizing structure of TextArc: words that appear more than once are drawn at their average position. Imagine each word attached to where it belongs around the spiral by a tiny rubber band; if the word appears in two places two rubber bands are attached. The net result of this rubber band tug-of-war is that a word will appear closer to places where it is used more.

Source: TextArc.org

Do yourself a favor and take some time to examine the interactive version of the Alice in Wonderland TextArc here.

Comments