Typing on smartphones is regarded as slow and cumbersome. Nevertheless we use it every day even to type longer texts. Most keyboards try to make typing faster and easier by implementing predictive methods such as autocorrection and word prediction. However, it is unclear in how far these methods are useful for typing on smartphones and some studies even showed that word prediction impairs typing performance .
The of this thesis is to answer the question whether autocorrection and word prediction are useful for mobile text input or not and potentially develop methods to improve their usefulness. Therefore, we offer a large dataset of mobile text input which should be analyzed with regard to this question.
 Quinn, P., & Zhai, S. (2016, May). A cost-benefit study of text entry suggestion interaction. In Proceedings of the 2016 CHI conference on human factors in computing systems (pp. 83-88). ACM.
Analyze a large dataset of mobile typing data to answer the question whether autocorrection and word prediction are useful for mobile text input or not and develop methods to improve it.
Dr. Anna Maria Feit
IDEA League Student Grant (IDL)
CLS Student Project (MPG ETH CLS)
ETH Organization's Labels (ETHZ)
Information, Computing and Communication Sciences