Modeling the speed of text entry with a word prediction interface

Abstract

This paper focuses on user performance with word predic-Absstract-This study analyzes user performance of text entry tasks with word prediction by applying modeling techniques developed in the field of human-computer interaction. Fourteen subjects transcribed text with and without a word prediction feature for seven test sessions. Eight subjects were able-bodied and used mouthstick typing, while six subjects had high-level spinal cord injuries and used their usual method of keyboard access. Use of word prediction decreased text generation rate for the spinal cord injured subjects and only modestly enhanced it for the able-bodied subjects. This suggests that the cognitive cost of using word prediction had a major impact on the performance of these subjects. Performance was analyzed in more detail by deriving subjects' times for keypress and list search actions during word prediction use. All subjects had slower keypress times during word prediction use as compared to letters-only typing, and spinal cord injured subjects had much slower list search times than able-bodied subjects. These parameter values were used in a two-parameter model to simulate subjects' word entry times during word prediction use, with an average model error of 16%. These simulation results are an encouraging first step toward demonstrating the ability of analytical models to represent user performance with word prediction. I. BACKGROUNDOMPUTER-BASED augmentative and alternative com-C munication (AAC) systems provide people who have severe disabilities with the opportunity to communicate independently in the areas of speech, writing, and computer applications. A major goal in the design and prescription of these systems is to provide the user with the fastest means of communication possible. A variety of techniques designed to enhance user performance are currently used in AAC systems, including word abbreviations [ 11, [2], message encoding [3], [4], and word prediction [5], [6]. There continues to be a need for greater understanding of the efficacy of these systems.A primary aim in most rate enhancement approaches is to reduce the motor requirements placed on the user. This is clearly an important goal, since the vast majority of users have severe physical impairments. However, a frequent consequence of reducing motor requirements is to increase the cognitive and perceptual loads on the user 141, [7], [SI. The net balance of this trade-off determines whether the user's overall performance will be enhanced or inhibited with a system [9].

Modelling text prediction systems in low- and high-inflected languages

“…For example, most of the anticipators have been evaluated showing the keystroke savings they obtain Garay-Vitoria and Abascal, 1994;Hunnicutt, 1987;Hunnicutt, 1989;Swiffin et al, 1987a;Swiffin et al, 1987b). There are others which show the message composition time saved, which is directly associated with the keystroke savings (Copestake, 1997;Koester and Levine, 1994). The hit ratio may also be shown (Garay-Vitoria, 2001), as previously noted.…”

“…Data related to the user's preferences may also be obtained. Therefore, several authors prefer to perform tests with real users Koester and Levine, 1994;Newell et al, 1992;Venkatagiri, 1993). In our opinion, the second method is the better one for obtaining a validation of the design under real conditions; however, it presents the difficulty of finding a set of people who represent the entire population of possible users of the system.…”

DualScribe: A Keyboard Replacement for Those with Friedreich’s Ataxia and Related Diseases

“…After each character, a list of extensions of the string is presented, and the user can select among those candidates. This reduces the physical load on the user, but looking through the list to find the desired word increases the cognitive load; so, word completion is not always faster [2]. Since someone with FA usually has motor problems leading to unsteady movement, utilizing a full-size keyboard may be problematic due to key-to-key "travel" distances.…”

Ambiguous keyboards for AAC

“…However disambiguation does not appear to be accepted as a popular and widespread technique in its own right. 'Traditional' word prediction (Koester & S. P. Levine, 1994) and more recent methods of prediction such as Dasher (Ward et al 2000) also rely on the entropy of language in their method of operation but do not use ambiguous keyboards.…”