The Swype and the Shark

Swype is a commercial text input system developed originaly by Swype Inc. an latter acquired by Nuance Communications. It was first presented at the TechCrunch50 in 2008. After that several similar keyboards appeared for smartphones.

Swype (www.swype.com)

To enter a word in swype, the user draws a  continuous line over the characters without lifting the finger from the screen.  The software uses  an algorithm to determine the word that is more closely related to the input pattern.

Since there is no need to be precise and since you do not need to take your finger from the surface for each letter, you can type very fast. In fact, in 2010 a Swype employee gained a entry into the  Guinness World Record  for the fastest text message on a touchscreen mobile phone.

The technique used in Swype is similar to the one presented five years early, on the CHI 2003 conference and later in UIST 2004. In the paper Shorthand writing on the stylus keyboard, Zhai and Kristensson present SHARK, a technique that contains most of the benefits we see in Swype today.

In SHARK each word is also defined by a pattern drawn over a keyboard layout. In this work, however, the authors used the ATOMIK keyboard instead of a QWERTY. The ATOMIK was designed to minimized the gesture time between keys that are more frequently used. The authors argue that gesture input for words can be better than tapping letters if you are able design them in a way that require less visual precision. This explains why even though you require more travel time, it is still fast to input text with this technique. The authors, however, were targeting the use of the gestures as a shortcut for most used words. The ideia is that after training a user would be able to input words without using the keyboard as a guide. They created an alphabet for the most frequent 100 words. Words that were not on this group used normal tapping input. 

ATOMIK keyboard layout.

In SHARK words are recognized using dynamic programming to compare the distance between the gesture and a template. The most similar word is returned. If only the direction and shape of the gestures are considered then some ambiguity still remain. The authors proposed that the initial or center position of the gesture could be used to solve this problem. In SHARK2 they improve upon the previous system by adding visual trace to the gestures (similar to what Swype does) and by assuring that every word could by entered by the same method. This more advanced system combined information from shape and location classifiers as well as a language model to increase the discrimination power. The inclusion of visual guided input works very well as an scaffolding technique. Even after using Swype for while, I don't think I was ever able to draw a word from memory alone.