A Rubric for Extracting Idea Density from Oral Language Samples

Abstract

While past research has demonstrated that low idea density (ID) scores from natural language samples correlate with late life risk for cognitive decline and Alzheimer’s disease pathology, there are no published rubrics for collecting and analyzing language samples for idea density to verify or extend these findings into new settings. This paper outlines the history of ID research and findings, discusses issues with past rubrics, and then presents an operationalized method for the systematic measurement of ID in language samples, with an extensive manual available as a supplement to this article (Analysis of Idea Density, AID). Finally, reliability statistics for this rubric in the context of dementia research on aging populations and verification that AID can replicate the significant association between ID and late life cognition are presented.

Idea density for predicting Alzheimer's disease from transcribed speech

“…We show that on the DementiaBank data the POS-based PID scores are actually higher for AD patients than they are for normal controls, contrary to the expectations from the AD literature (Engelman et al, 2010;Chand et al, 2012;Kemper et al, 2001). By studying the character-istics of the DementiaBank we are able to adapt DEPID such that its PID values become significantly different between the patient and control groups in the expected direction.…”

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

“…We show that on the DementiaBank data the POS-based PID scores are actually higher for AD patients than they are for normal controls, contrary to the expectations from the AD literature (Engelman et al, 2010;Chand et al, 2012;Kemper et al, 2001). By studying the characteristics of the DementiaBank we are able to adapt DEPID such that its PID values become significantly different between the patient and control groups in the expected direction.…”

“…In order to check that we manually annotated the propositions of 20 interviews from DementiaBank according to the guidelines given by Chand et al (2012). We found that both CPIDR and DEPID overestimate the PID values although CPIDR does it to much greater extent.…”

Automated Proposition Density Analysis for Discourse in Aphasia

“…Farias et al (2012) recently reported a significant association between low PD measured in late life and steeper subsequent declines in cognitive function. Many authors describe proposition density as an index of "cognitive reserve" or a buffer against the effects of neuropathology (Chand et al, 2012;Engelman et al, 2010;Iacono et al, 2009;Snowdon et al, 1996). As mentioned earlier, PD has been shown to decline in cases of traumatic brain injury (Coelho et al, 2005).…”

“…Studies have also shown relationships between low PD scores in early adult life and greater severity of Alzheimer's disease pathology in the neocortex (Riley et al, 2005;Snowdon, Greiner, & Markesbery, 2000). Two other studies have confirmed that proposition density is not significantly different in groups with mild cognitive impairment and healthy older adults (Chand et al, 2012;Roark et al, 2011).…”