Abstract FR:

This thesis focuses on one of the currently active areas of Human-Computer Interaction (HCI): text entry on mobile devices. Specifically, it deals with the evaluation of text entry method interfaces on mobile devices. We address the two main approach of the evaluation: empirical user testing and model based evaluation. A platform is presented for empirical user tests. The platform aims to shorten the evaluation time and make the evaluation more reproducible and generalizable. It’s implemented on mobile device and equipped with many existing entry methods. It also facilitates the implementation of a new idea for text entry. New ideas can be tested by comparison to the already implemented methods. The platform also includes valuable tools for the evaluation. One tool is provided to help in the creation of a set of test phrases that represent a given language. Another tool is for automating the most common analysis in text entry tests. We presented a framework to identify, classify and model the different operation in the text entry process on mobile devices. It divides the process to two stages: action planning stage and execution stage. The action planning stage studies how the word or the text to be typed is mapped to the physical actions allowed by the entry system used. The execution stage concerns the primitive tasks the user should done to produce text. Some measures are proposed for the evaluation of the two stages. The framework also identifies the different entities that should be taken into account during the evaluation. Model based evaluation requires human performance models for the primitive tasks used in the entry process. We studied three tasks frequently used in the execution stage of the entry process: word disambiguation, word selection from a list, and tilt based interaction. We present an algorithm and design guidelines for the design of efficient ambiguous keyboard layout. A model for the selection of a word from a word-list is constructed from an experimental study. Another model for pointing and scrolling using tilt sensor on a mobile device is also presented. Finally, we present new design directions for the action planning stage that we think more interesting when compared to current designs. They are based on knowledge we already have about our life and about the text we write. They use this knowledge to allow typing a word in a more direct way compared to typing it letter by letter as it’s the case in the current designs. We provide two implementations to help the concretization of the concepts presented in that part of Page 6 Abstract Text entry interfaces on mobile devices: Modeling, design and evaluation, PhD thesis 2009 the thesis. The first shows how our knowledge can be used to type frequent words through using pictographs. The second exploits language syntax to enable the user to type fast and to protect her/him from committing typing errors. The two implementations employ a specially constructed text prediction engine. It implements language redundancy in storage efficient data structures. It introduces the concept of meaning (concept, object, action, relation, etc. ) and separates it from its lexical representation in a given language.