Oral Transcripts and Linguistic Features for Cognitive Ability Screening

Raw oral transcription texts, preprocessing results, and derived linguistic feature datasets for cognitive ability research. It includes code for classification experiments. The author is chen, xuanshu, and the dataset was last updated in February 2026.

Use Cases

• Train a classifier using the linguistic feature datasets to predict cognitive ability scores from oral transcripts.
• Analyze the relationship between specific grammatical features in the raw oral transcription texts and cognitive screening outcomes.
• Reproduce or extend the automated screening method using the provided classification experiment code.

Strengths

• Includes both raw data (oral transcription texts) and processed outputs (linguistic feature datasets).
• Provides classification experiment code, enabling methodological reproducibility.
• Last updated in February 2026, indicating recent maintenance.

Limitations

• The sample size (number of transcripts or participants) is unknown, limiting assessment of statistical power.
• The specific linguistic features and their extraction methods are not detailed in the provided input.
• The demographic or clinical characteristics of the source population are unspecified, which may affect generalizability.

Provenance

Source

Harvard Dataverse

Collection Method

Experimental data collection, likely involving oral recordings and subsequent transcription.

Freshness

Last updated 2026-02-24.