AUTHOR=Bright Rebecca , Ashton Elaine , Mckean Cristina , Wren Yvonne 

TITLE=The development of a digital story-retell elicitation and analysis tool through citizen science data collection, software development and machine learning

JOURNAL=Frontiers in Psychology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2023.989499

DOI=10.3389/fpsyg.2023.989499

ISSN=1664-1078

ABSTRACT=To leverage the potential benefits of technology to language assessment processes, large samples of naturalistic language data must be collected and analysed. These samples enable the development and testing of novel software applications with data relevant to their intended clinical application. However, this can be costly and time-consuming. 

This paper describes the development of a novel application designed to elicit and analyse young children’s story retell narratives to provide metrics regarding the use of grammatical structures (micro-structure) and story grammar (macro-structure elements). 

A co-design process was used to design an app to gather children's story retell samples. A citizen science approach was used to encourage participation. A stratified sampling framework ensured a representative sample was obtained across age, gender and five bands of socio-economic disadvantage.  Research Associates (RA) completed transcription and micro and macro-structure analysis of the language samples.  Methods to improve transcriptions produced by automated speech recognition were developed to enable reliable analysis. RA micro-structure analyses were compared to those generated by the application to test its reliability using intra-class correlation (ICC).  RA macro-structure analyses were used to train an algorithm to produce macro-structure metrics. Finally, results from the macro-structure algorithm were compared against a subset of RA macro-structure analyses not used in training to test its reliability using ICC. 

4517 profiles were made in the app; from these, a final set of 599 was drawn. ICC between the RA and application micro-structure analyses ranged from 0.213  to 1.0 with 41 of 44 comparisons reaching ‘good’ (0.70-0.90) or ‘excellent’ (>0.90) levels. ICC between the RA and application macro-structure features were completed for 85 samples not used in training the algorithm. ICC ranged from 0.5577 – 0.939 with 5 of 7 metrics being ‘good’ or better. 

Work to date has demonstrated the potential of semi-automated transcription and linguistic analyses to provide reliable, detailed and informative narrative language analysis for young children and for the use of citizen science approaches to collect representative and informative research data. Clinical evaluation of this new app is ongoing, so we do not yet have data documenting its developmental or clinical sensitivity and specificity.