Iris Edda Nowenstein


2024

pdf bib
Automatic Extraction of Language-Specific Biomarkers of Healthy Aging in Icelandic
Elena Callegari | Iris Edda Nowenstein | Ingunn Jóhanna Kristjánsdóttir | Anton Karl Ingason
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

This study examines the influence of task type and healthy aging on various automatically extracted part-of-speech features in Icelandic. We administered three language tasks to participants aged 60–80: picture description, trip planning, and description of one’s childhood home. Our findings reveal significant task effects on 11 out of 14 linguistic variables studied, highlighting the substantial influence of sampling methods on language production. Among the variables showing statistically significant task effects, we find the rate of the genitive and subjunctive, variables which can only be studied in morphologically richer languages like Icelandic. On the other hand, rates of pronouns, adverbs, and prepositions remained stable across task types. Aging effects were more subtle, being evident in 3 of the 14 variables, including an interaction with task type for dative case marking. These findings underscore the significance of task selection in studies targeting linguistic features but also emphasize the need to examine languages other than English to fully understand the effects of aging on language production. Additionally, the results have clinical implications: understanding healthy aging’s impact on language can help us better identify and study changes caused by Alzheimer’s Disease in older adults’ speech.