Systematic mapping of AI-based speech therapy apps and their pedagogical design
This study systematically maps AI-based speech therapy applications and analyses their pedagogical design. Focusing on end-user mobile apps available in major app stores, we included twenty-five applications that explicitly combined speech, language, or communication therapy with artificial intellig...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Online |
| Language: | English |
| Published: |
Universidade Estadual de Campinas
2026
|
| Subjects: | |
| Online Access: | https://econtents.sbu.unicamp.br/inpec/index.php/joss/article/view/21036 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study systematically maps AI-based speech therapy applications and analyses their pedagogical design. Focusing on end-user mobile apps available in major app stores, we included twenty-five applications that explicitly combined speech, language, or communication therapy with artificial intelligence or automated speech analysis. Each app was coded using a framework informed by speech-language therapy literature, intelligent tutoring systems, and mobile health app evaluation, capturing AI adaptivity, feedback immediacy, multimodal feedback, evidence basis, pedagogical alignment, gamification, stakeholder dashboards, pricing, user rating, and an adoption proxy. Descriptive statistics, Pearson and Spearman correlations, and thematic analysis were applied at the app level. The mapping shows moderate AI adaptivity and rapid feedback in most apps, with substantial variation in evidence basis and pedagogical alignment. Evidence basis and pedagogical alignment were strongly correlated (r ≈ 0.82) and both were positively associated with user ratings and estimated active users, while higher subscription cost showed a moderate negative association with adoption. Thematic analysis revealed recurring design patterns such as gamified home practice, limited clinician-in-the-loop features, uneven data privacy transparency, and partial uptake of multilingual and offline support. The findings highlight a gap between rapidly advancing AI capabilities and consistently principled pedagogical design in commercial speech therapy apps. |
|---|---|
| ISSN: | 2236-9740 |
