Using Free Computer-Assisted Language Sample Analysis to Evaluate and Set Treatment Goals for Children Who Speak...

Area of Science:

• Linguistics
• Speech-Language Pathology
• Computational Linguistics

Background:

• Spoken language analysis (LSA) is crucial for assessing child language disorders.
• Current LSA methods may disadvantage speakers of nonmainstream dialects, like African American English (AAE).
• Limited data historically underpins LSA reference values.

Purpose of the Study:

• To provide a tutorial on using free Computerized Language Analysis (CLAN) software for LSA.
• To develop and test language variety-sensitive benchmarks for LSA measures.
• To demonstrate CLAN's utility for dialect-fair assessment and therapy goal setting in AAE-speaking children.

Main Methods:

• Utilized retrospective analysis of data from AAE-speaking children.
• Employed the free Computerized Language Analysis (CLAN) software.
• Applied Developmental Sentence Scoring (DSS) and Index of Productive Syntax (IPSyn) measures.

Main Results:

• Developmental Sentence Scoring (DSS) did not appear to bias against AAE speakers and identified language impairment (LI).
• Other LSA measures were lower in AAE-speaking children with LI but inconsistently identified individuals.
• CLAN software enabled rapid, in-depth analysis for identifying intervention targets.

Conclusions:

• CLAN software facilitates dialect-fair LSA for children speaking diverse English varieties.
• This approach supports accurate identification of language impairment (LI) and informs therapy goal setting.
• CLAN offers a powerful tool for nuanced child language assessment.