Accuracy of the Language Environment Analysis (LENATM) System Segmentation and Metrics: A Systematic Review
Purpose: The Language Environment Analysis (LENATM) system provides automated measures facilitating clinical and non-clinical research and interventions on language development, but there are only a few, scattered independent reports of these measures’ validity. The objectives of the current systematic review were to (1) Discover studies comparing LENATM output with manual annotation, namely accuracy of talker labels, as well as involving Adult Word Counts (AWC), Conversational Turn Counts (CTC), and Child Vocalization Counts (CVC); (2) Describe them qualitatively; (3) Quantitatively integrate them to assess central tendencies; and (4) Quantitatively integrate them to assess potential moderators. Method: Searches on Google Scholar, PubMed, Scopus, and PsycInfo were combined with expert knowledge, and inter-article citations resulting in 238 records screened, and 73 records whose full-text was inspected. To be included, studies must target children under age 18 years and report on accuracy of LENATM labels (e.g., precision and/or recall), and/or AWC, CTC, or CVC (correlations and/or error metrics). Results: A total of 33 studies, in 28 articles, were discovered. A qualitative review revealed most validation studies had not been peer-reviewed as such and failed to report key methodology and results. Quantitative integration of the results was possible for a broad definition of recall and precision (mean = 59% and 68% respectively, N = 12-13), for AWC (mean r = .79, N = 13), CVC (mean r = .77, N = 5), and CTC (mean r = .36, N = 6). Publication bias and moderators could not be assessed meta-analytically. Conclusion: Further research and improved reporting are needed in studies evaluating LENA segmentation and quantification accuracy, with work investigating CTC being particularly urgent.
