Improving word prediction for augmentative communication by using idiolects and sociolects

Abstract

Word prediction, or predictive editing, has a long history as a tool for augmentative and assistive communication. Improvements in the state-of-the-art can still be achieved, for instance by training personalized statistical language models. We developed the word prediction system Soothsayer. The main innovation of Soothsayer is that it not only uses idiolects, the language of one individual person, as training data, but also sociolects, the language of the social circle around that person. We use Twitter for data collection and experimentation. The idiolect models are based on individual Twitter feeds, the sociolect models are based on the tweets of a particular person and the tweets of the people he often communicates with. The sociolect approach achieved the best results. For a number of users, more than 50% of the keystrokes could have been saved if they had used Soothsayer.

Computational Measures of Deceptive Language: Prospects and Issues

“…Moreover, the use of computational stylometric cues to detect deceit relies on various theoretical hypotheses commonly accepted by the community, such as the Reality Monitoring framework (e.g., Bond and Lee, 2005), or the Interpersonal Deception Theory combined with the Self-Presentation Perspective (e.g., Hancock et al, 2004). And as highlighted previously, the rationale behind stylometry is the one of the idiolect-baseline hypothesis, which has been supported by numerous studies (e.g., Barlow, 2013;Daelemans, 2013;Johnson and Wright, 2017;Kestemont, 2014;Stoop and van den Bosch, 2014;van Halteren et al, 2005;Wright, 2017). We thus argue that the theories underlying the use of the stylometric methodologies have generally been accepted by the scientific community.…”

Evaluation of a Word Prediction System in an Augmentative and Alternative Communication for Disabled People

“…The word selection is done with a single click or with keyboard shortcuts. For example, the Soothsayer completion prototype [15] works with the space key, while the text editor of the Presage prediction engine [2] requires the mouse or the F1 to F6 keys to select the predicted words. The ACAT user interface [3] can display the word list both horizontally and vertically.…”