Word Prediction Software Research Articles

Exploring the impact of word prediction assistive features on smartphone keyboards for blind users

Assistive technologies have been developed to enhance blind users’ typing performance, focusing on speed, accuracy, and effort reduction. One such technology is word prediction software, designed to minimize keystrokes required for text input. This study investigates the impact of word prediction on typing performance among blind users using an on-screen QWERTY keyboard. We conducted a comparative study involving eleven blind participants, evaluating both standard QWERTY input and word prediction-assisted typing. Our findings reveal that while word prediction slightly improves typing speed, it does not enhance typing accuracy and increases both physical and temporal workload compared to the default keyboard. We conclude with recommendations for improving word prediction systems, including more efficient editing methods and the integration of voice pitch variations to aid error recognition.

Emergent Bilinguals’ Use of Word Prediction Software Amid Digital Composing

AbstractComposing is an essential part of literacy development in early childhood classrooms, and writing experiences are continually changing through advances in technology. Writing in a new language can be particularly challenging for emergent bilinguals as they navigate learning how to spell in English as part of the writing process. New pedagogical tools must be used to support these students as meaning makers and composers. In this study, we investigated how a group of first‐grade emergent bilinguals used word prediction software as they created digital compositions over the course of a year. The results suggest several positive ways, such as basic spelling support, extended written responses, and additional opportunities to practice reading, that this digital tool enhanced the meaning‐making process of emergent bilingual writers. Recommendations for educators to implement word prediction software in classrooms are included.

Influence of training protocols on text input speed on a computer in individuals with cervical spinal cord injury: a randomised controlled trial.

Randomised controlled trial. To evaluate the impact of two different word prediction software (WPS) training protocols on text input speed (TIS) in people with tetraplegia and to determine which was the most effective. Rehabilitation department, Garches, France. Participants with neurological levels between C6 and C8 were allocated to one of three different groups. The REHAB group underwent training with an occupational therapist. The SELF group carried out a standardised home self-training with a written training guide. The CONTROL group had no training. Participants were assessed at day 15 (D15) and day 30 (D30). The primary outcome was a copying task with and without WPS (WITH and WITHOUT). Forty-two participants (mean age ± SD of 39.8 ± 12) were included and 38 completed the study. At D30, the mean (95% confidence interval) difference in TIS between the CONTROL and SELF groups was 3.8 [-1.7 to 9.4] characters per minute (cpm) (p = 0.23), between the REHAB and SELF groups was 12.9 [7.4 to 18.4] cpm (p < 0.001), and between the REHAB and CONTROL groups was 9.1 [3.5 to 14.6] cpm (p < 0.001). The results of this study showed that occupational therapist-supervised training improved TIS but word prediction software did not increase TIS. These results suggest that supervised training should be provided to all individuals who are prescribed with devices and systems to facilitate computer access in order to increase their TIS.

Training programs on text input speed in persons with cervical spinal cord injury

Computer access is important for social participation for people with cervical spinal cord injury (SCI). Different devices have been developed to enable them to use a computer but text input speed (TIS) with them is low. Several methods [e.g., word prediction software (WPS)] have been developed to increase TIS. In the literature, the effect of WPS on TIS was debatable. One hypothesis to explain the disparity is the lack of specific WPS-training programs for people with cervical SCI. The aim of this study was to compare the influence of three WPS-training programs on TIS in people with cervical SCI, and to determine which was the most effective. Participants were randomized to one of three different groups: a group with training with an occupational therapist (REHAB), a group with a standardized home self-training with a written training guide (SELF), and a third group that had no training (CONTROL). Forty-two participants were included and 38 completed the study. TIS improved significantly more in the REHAB group (with and without WPS) than in the CONTROL ( P < 0.001) and SELF groups ( P < 0.001) between D0 and D30. The results of this study showed that OT-supervised training improved TIS but did not provide any specific improvements in the use of WPS on TIS, although the number of recorded errors decreased when using WPS after training and the improvement of the rate of word prediction use. These results suggest that supervised training should be developed when providing patients with word prediction software, in order to increase their TIS.

Word prediction software in people with cervical spinal cord injury: A literature review

Individuals with cervical spinal cord injury (ICSCI) have difficulty accessing computers through conventional methods. The purpose of this paper was to provide a critical narrative review on types of computer access devices and word prediction software for ICSCI. A search was conducted in several electronic databases. There is limited data about Test Input Speed (TIS) in ICSCI. One study showed that TIS in ICSCI was significantly lower [mean = 11 words per minute (wpm)] ( P = 0.001) than TIS of abled-bodied individuals (19 wpm). In a sample of ICSCI, there was a significant difference between voice recognition system (mean = 18 wpm), a standard keyboard (mean = 8 wpm) and an onscreen keyboard (mean = 3 wpm) ( P < 0.001). However, the literature suggested that the impact of Word Prediction Software (WPS) for increasing TIS remains questionable. Indeed, there is limited scientific documentation of the influence of the parameters of WPS on TIS. Regarding the number of words displayed in the prediction list, this parameter did not increase TIS. For the parameter “frequency of use”, use of WPS with the activation of frequency of use increased TIS in participants with high-level tetraplegia. For participants with low-level tetraplegia, the use of WPS with frequency of use activated only decreased the number of errors. Each professional could provide clear and accurate information on the benefits of WPS for people with cervical SCI. WPS must be set regarding the needs of people with cervical SCI. If not, the use of these software's may go against the expected benefits.

The effect of word prediction settings (frequency of use) on text input speed in persons with cervical spinal cord injury: a prospective study

Purpose: To determine whether activation of the frequency of use and automatic learning parameters of word prediction software has an impact on text input speed.Methods: Forty-five participants with cervical spinal cord injury between C4 and C8 Asia A or B accepted to participate to this study. Participants were separated in two groups: a high lesion group for participants with lesion level is at or above C5 Asia AIS A or B and a low lesion group for participants with lesion is between C6 and C8 Asia AIS A or B. A single evaluation session was carried out for each participant. Text input speed was evaluated during three copying tasks:• without word prediction software (WITHOUT condition)• with automatic learning of words and frequency of use deactivated (NOT_ACTIV condition)• with automatic learning of words and frequency of use activated (ACTIV condition)Results: Text input speed was significantly higher in the WITHOUT than the NOT_ACTIV (p< 0.001) or ACTIV conditions (p = 0.02) for participants with low lesions. Text input speed was significantly higher in the ACTIV than in the NOT_ACTIV (p = 0.002) or WITHOUT (p < 0.001) conditions for participants with high lesions.Conclusions: Use of word prediction software with the activation of frequency of use and automatic learning increased text input speed in participants with high-level tetraplegia. For participants with low-level tetraplegia, the use of word prediction software with frequency of use and automatic learning activated only decreased the number of errors.Implications in rehabilitation Access to technology can be difficult for persons with disabilities such as cervical spinal cord injury (SCI). Several methods have been developed to increase text input speed such as word prediction software.This study show that parameter of word prediction software (frequency of use) affected text input speed in persons with cervical SCI and differed according to the level of the lesion.• For persons with high-level lesion, our results suggest that this parameter must be activated so that text input speed is increased.• For persons with low lesion group, this parameter must be activated so that the numbers of errors are decreased.• In all cases, the activation of the parameter of frequency of use is essential in order to improve the efficiency of the word prediction software.• Health-related professionals should use these results in their clinical practice for better results and therefore better patients ‘satisfaction.

Influence of the Number of Predicted Words on Text Input Speed in Participants With Cervical Spinal Cord Injury

ObjectivesTo determine whether the number of words displayed in the word prediction software (WPS) list affects text input speed (TIS) in people with cervical spinal cord injury (SCI), and whether any influence is dependent on the level of the lesion. DesignA cross-sectional trial. SettingA rehabilitation center. ParticipantsPersons with cervical SCI (N=45). Lesion level was high (C4 and C5, American Spinal Injury Association [ASIA] grade A or B) for 15 participants (high-lesion group) and low (between C6 and C8, ASIA grade A or B) for 30 participants (low-lesion group). InterventionTIS was evaluated during four 10-minute copying tasks: (1) without WPS (Without); (2) with a display of 3 predicted words (3Words); (3) with a display of 6 predicted words (6Words); and (4) with a display of 8 predicted words (8Words). Main Outcome MeasuresDuring the 4 copying tasks, TIS was measured objectively (characters per minute, number of errors) and subjectively through subject report (fatigue, perception of speed, cognitive load, satisfaction). ResultsFor participants with low-cervical SCI, TIS without WPS was faster than with WPS, regardless of the number of words displayed (P<.001). For participants with high-cervical SCI, the use of WPS did not influence TIS (P=.99). There was no influence of the number of words displayed in a word prediction list on TIS; however, perception of TIS differed according to lesion level. ConclusionsFor persons with low-cervical SCI, a small number of words should be displayed, or WPS should not be used at all. For persons with high-cervical SCI, a larger number of words displayed increases the comfort of use of WPS.

Influence of word prediction settings (number of words displayed and frequency of use) on text input speed in persons with cervical spinal cord injury

Different devices have been developed to enable persons with cervical spinal cord injury (SCI) to use a computer. However, text input speed (TIS) remains low for these persons. Several methods have been developed to increase TIS, such as word prediction software (WPS). Data in the literature are discordant regarding the effect of WPS on TIS, with decreases of up to 71% in some studies and increases of up to 45% in others. The main reason suggested for these differences is the cognitive load caused by the visual searching for words in the prediction list. It is thus likely that the number of words in the prediction list influences TIS. Moreover, WPS can be customized using different settings. For example, the prediction list can be ordered according to the frequency of occurrence of words in the language (frequency of use) and the automatic learning of new words can be activated. Until now, no studies in the literature have evaluated the influence of these parameters on TIS. The aims of this study are to determine if the number of words displayed in the WPS list and activation of the frequency of use and automatic learning parameters of WPS affects TIS in people with tetraplegia. Forty-five persons with cervical SCI between C4 and C8 Asia AIS A or B and who were computer users were included. For the parameter “Number of Words displayed”, TIS was evaluated during 4 10-minute copying tasks (without WPS, with a display of 3 6 8 predicted words). For the parameter “frequency of use”, TIS was evaluated during 3 copying tasks (without WPS (WITHOUT), with automatic learning of words and frequency of use desactivated (NOT_ACTIV) or activated (ACTIV)). There was no effect of the number of words displayed in a word prediction list on TIS, however perception of TIS differed according to lesion level. Use of word prediction software with activation of frequency of use and automatic learning increased TIS in participants with high-level tetraplegia. For participants with low-level tetraplegia, use of word prediction software with frequency of use and automatic learning activated only decreased the number of errors.

Recommendations and settings of word prediction software by health-related professionals for people with spinal cord injury: A prospective observational study

For people with cervical Spinal Cord Injury (SCI), access to computers can be difficult, thus several devices have been developed to facilitate their use. However, text input speed remains very slow compared to users who do not have a disability, even with these devices. Several methods have been developed to increase text input speed, such as Word Prediction Software (WPS). Health-Related Professionals (HRP) often recommend this type of software to people with cervical SCI. WPS can be customized using different settings. It is likely that the settings used will influence the effectiveness of the software on text input speed. However, there is currently a lack of literature regarding professional practices for the setting of WPS as well as the impact for users. The aim of this study is to analyze word prediction software settings used by HRP for people with cervical SCI. A questionnaire was submitted to HRP who advise tetraplegic people regarding the use of communication devices. A total of 93 professionals responded to the survey. The most frequently recommended software was Skippy, a commercially available software. HRP rated the importance of the possibility to customise the settings as high. Moreover, they rated some settings as more important than others ( p < 0.001). However, except for the number of words displayed, each setting was configured by less than 50% of HRP. The results showed that there was a difference between the perception of the importance of some settings and data in the literature regarding the optimization of settings. Moreover, although some parameters were considered as very important, they were rarely specifically configured. Confidence in default settings and lack of information regarding optimal settings seem to be the main reasons for this discordance. This could also explain the disparate results of studies which evaluated the impact of WPS on text input speed in people with cervical SCI.

Effectiveness of Word Prediction Software WORDQ: “...Predict it, Hear it, Choose it, Review it, Correct it, Write it now...”

Our cluster receives a number of referrals from schools requesting support with the implementation of assistive technology tools (particularly word prediction software) to support struggling reluctant writers. It is widely acknowledged that writing is pivotal for academic success, and when a learner has difficulty expressing their ideas they often can become alienated and frustrated. Fledging research suggests that the appropriate use of assistive technology like word prediction software can remove such barriers for struggling writers. A popular word prediction software tool used in New Zealand schools is WordQ. This article discusses the background to WordQ, summarises the research supporting its effectiveness as a tool to support struggling writers, and highights ways to overcome barriers to enable the successful implementation of WordQ in schools.

Investigating input technologies for children and young adults with Down syndrome

Using computers as an assistive technology for people with various types of physical and perceptual disabilities has been studied extensively. However, research on computer technology used by individuals with Down syndrome is limited. This paper reports an empirical study that investigated the use of three input techniques (keyboard and mouse, word prediction, and speech recognition) by children and young adults with Down syndrome and neurotypical children. The results suggest that the performance of the Down syndrome participants vary substantially. The high performing Down syndrome participants are capable of using the keyboard or the word prediction software to generate text at approximately 6 words per minute with error rates below 5%, which is similar to the performance of the younger neurotypical participants. No significant difference was observed between the keyboard condition and the word prediction condition. Recognition error rate observed under the speech input condition is very high for the Down syndrome participants. The neurotypical children achieved better performance than the participants with Down syndrome on the input tasks and demonstrated different preferences when interacting with the input techniques. Limitations of this study and implications for future research are also discussed.

Word Prediction Programs with Phonetic Spelling Support: Performance Comparisons and Impact on Journal Writing for Students with Writing Difficulties

This investigation examined the effects of currently available word prediction software programs that support phonetic/inventive spelling on the quality of journal writing by six students with severe writing and/or spelling difficulties in grades three through six during a month-long summer writing program. A changing conditions single-subject research design was used and replicated across the participants. Using a daily writing prompt, students alternated between Co:Writer, WordQ, and WriteAssist word prediction programs. The results provided evidence for the effectiveness of various word prediction programs over word processing, and demonstrated improvements in spelling accuracy across conditions. Relative gains in the total number of words and composition rate were modest for the majority of the participants and should be interpreted with caution due to several methodological issues. The social validity interviews revealed that all students enjoyed the word prediction programs and found them beneficial. Study limitations and recommendations for future research are discussed.

Evaluating the Benefits of Displaying Word Prediction Lists on a Personal Digital Assistant at the Keyboard Level

ABSTRACT Visual-cognitive loads influence the effectiveness of word prediction technology. Adjusting parameters of word prediction programs can lessen visual-cognitive loads. This study evaluated the benefits of WordQ word prediction software for users' performance when the prediction window was moved to a personal digital assistant (PDA) device placed at the keyboard level. Twenty-one young people aged 11–14 (11 new users and 10 experienced users) participated in the study. The Canadian Occupational Performance Measure was used to measure users' self-ratings of performance and satisfaction. Results of two-tailed paired t-tests reveal significantly (p < .05) higher performance and satisfaction ratings when the word prediction list was displayed on the PDA. Users reported that it was easier to look for the words at the keyboard level and to select words directly from the PDA. Visual comparisons of the users' typing speed and accuracy show that experienced users had faster typing rates and new users appeared to have better accuracy when they typed with WordQ on the PDA display. Further studies with larger samples of individuals with different diagnoses and ages are required to confirm the benefit of using a PDA display in enhancing typing rate and accuracy.

Using Software to Enhance the Writing Skills of Students with Special Needs

This study used a modified multiple-baseline design to determine the effects on the writing performance of seven students with special needs when a talking word processor with spell checker software was used independent of and in conjunction with word prediction software as accommodations in daily writing exercises. Results indicated that, in general, the impact of using writing software was positive. The group mean for number of misspellings decreased, accuracy percentage increased, number of words increased, and overall district writing rubric scores increased. Further, the software had different benefits for different students and students expressed preferences for particular software functions. Implications for practice and research are presented.

Preliminaries to Finnish Word Prediction

Commercial word prediction software is thus far mainly available for uninflected languages such as English. In the present study, we investigate word prediction in highly inflected languages, using Finnish as an example. Despite its high degree of case inflection, about one third of word tokens in a Finnish text appear in their uninflected base form. As a result, simple prediction techniques such as word completion, originally developed for English, can be used for investigating characteristics of word prediction in inflected languages. Our preliminary results show that about 45% of characters can roughly be saved in Finnish word prediction in general for uninflected and inflected tokens. The most interesting result of our prediction experiments is, however, showing the distribution of character savings to the most common cases and their cumulative effect on the total percentage of character savings that may be achievable in Finnish word prediction. The major conclusions of the study are that word prediction in a highly inflected language such as Finnish is feasible provided that the case form used with a word appearing in a given context of use can be predicted correctly, at least in some cases, and the cognitive load of the resulting prediction system for the user is not too high when the prediction of the case form fails.

Typing speed, spelling accuracy, and the use of word-prediction

Children with spelling difficulties are limited in their participation in all written school activities. We aimed to investigate the influence of word-prediction as a tool on spelling accuracy and typing speed. To this end, we selected 80 Grade 4 – 6 children with spelling difficulties in a school for special needs to participate in a research project involving a cross-over within-subject design. The research task took the form of entering 30 words through an on-screen keyboard, with and without the use of word-prediction software. The Graded Word Spelling Test served to investigate whether there was a relationship between the children's current spelling knowledge and word-prediction efficacy. The results indicated an increase in spelling accuracy with the use of word-prediction, but at the cost of time and the tendency to use word approximations, and no significant relationship between spelling knowledge and word-prediction efficacy. Keywords : spelling difficulties; word approximations; word-prediction; writing support South African Journal of Education Vol. 28 (1) 2008: pp. 117-134

The Effects of Word Completion and Word Prediction on Typing Rates Using On-Screen Keyboards

Word prediction is often recommended by therapists as a means to improve typing speed for clients with physical limitations. Although literature suggests that word prediction does have an effect on writing proficiency, increased speed is not one of its benefits when used with a standard keyboard. One reason given for the failure of word prediction to accelerate typing is that the user must look away from any source document to scan the prediction list during typing. Looking away from the source document may slow the typist more than any acceleration offered by word prediction. For input methods that already require the typist to look away from the copy, this effect might be irrelevant. The focus of this research was to determine whether word completion or word prediction programs would increase typing speed when used with an input method (an on-screen keyboard) that also requires looking away from the source document. Ten people, five men and five women, aged 20 to 38 years, participated in this study. The study used a single-subject, successive intervention design to test typing speed and accuracy using an on-screen keyboard with integrated word prediction software. Seven participants had their fastest typing speed with word prediction. Two participants had their fastest typing speed with word completion. Only one participant demonstrated no improvement in speed when using these two programs. Overall, these results show that the use of word prediction and word completion may assist on-screen keyboard users to improve typing speed.

The Impact of Word Prediction Software on the Written Output of Students with Physical Disabilities

This study examined the impact of a word prediction software program, Co:Writer, on the written output of 24 students with physical disabilities that affected their ability to write by hand. Surveys were completed by both students who used Co:Writer and their teachers/adult supporters in schools, and 10-minute writing samples were obtained from students in three modalities: handwriting, word processing, and word processing with Co:Writer. Two-thirds or more of the students and 50% or more of the adults believed that Co:Writer helped the students to spell better; use a wider variety of words; write faster; produce neater, easier-to-read work; and write more correct sentences. Further, two-thirds or more of the adults and 50% or more of the students believed that Co:Writer helped the students to write more without tiring, experience less frustration when writing, and read what they had written. The writing sample analyses indicated no significant difference between the three writing modes with regard to the total number of words produced in 10 minutes. However, word processing and/or Co:Writer resulted in higher percentages of legible words, correctly spelled words, and correct word sequences; and in longer mean lengths of consecutive correct word sequences than handwriting. The results are discussed in terms of their relevance to educational technology supports for students with physical disabilities.

Evaluating accessibility by simulating the experiences of users with vision or motor impairments

User studies involving users with disabilities often incur greater financial cost and complexity than those involving general populations. Consequently, accessibility issues may not be identified during the earlier phases of software design, when designs are still malleable. Additionally, it can be difficult to create controlled studies with multiple groups of very similar subjects due to the extremely heterogeneous nature of the impact of many motor and visual disabilities. This paper examines the feasibility of simulating the interaction experiences of users with low vision or motor impairments. Based on empirical studies in the literature of the impact of these impairments on the experience of computer use, we have developed EASE (Evaluating Accessibility through Simulation of User Experience), a tool that can help developers identify disability-related usability problems early in the design process. EASE can also be used to allow fine-grained exploration of user capabilities that are difficult to control, such as achievable typing speed. We present a study of the use of word prediction software that illustrates the value of fine-grained control over typing speed and that also shows word prediction is most useful at typing speeds between 5 and 8 words per minute.

Using Word Prediction Software to Increase Typing Fluency with Students with Physical Disabilities

Although word prediction software was originally developed for individuals with physical disabilities, no previous research was found that included participants with significant physical disabilities that affected hand use. Using two-minute trials, two participants improved their typing rate using word prediction software, one participant had mixed results, and the participant with the fastest pre-intervention typing speed had a decreased typing rate with word prediction. This study indicates that the effectiveness of using word prediction software to increase typing speed may vary due to the severity of physical disability or pre-intervention typing rate.