Improved Text Entry Method Using Eye Gaze Direction and Language Model

Title: Improved Text Entry Method Using Eye Gaze Direction and Language Model

Research Question: Can we develop a more efficient and accurate method for text entry using eye gaze direction and a language model?

Methodology: The researchers created a system called Dasher that allows users to write text by directing their gaze at specific areas on a screen. This system uses a language model to predict the probability of each letter's occurrence in a given context, which helps to allocate shelf space for each letter of the alphabet.

Results: Dasher was found to be more efficient and accurate than traditional on-screen keyboards. Users could write at higher speeds and made fewer errors with Dasher compared to an on-screen keyboard. Users also reported that Dasher was less stressful to use.

Implications: Dasher has the potential to be an efficient, accurate, and fun writing system not only for disabled computer users but also for users of mobile computers. It can be used with various pointing devices and adapts to different languages. This research suggests that eye gaze direction and language models can significantly improve text entry methods.

Link to Article: https://arxiv.org/abs/0204030v4 Authors: arXiv ID: 0204030v4