Noun-verb semantic distance analyses in sentence production of Alzheimer’s disease

EasyChair Preprint no. 6393

Abstract

In this study, the sentence production behavior of individuals with AD was analyzed by using the DementiaBank, which is a part of the TalkBank projects. We applied machine-learning approach to analyze the noun-verb semantic distance of AD. Moreover, verb clusters were analyzed with those nouns and how they are associated with the demographic factors (age, education, and dementia severity).

99 probable AD participants from the DementiaBank(Becker et al., 1994) were analyzed on the sentence construction task. They constructed a sentence with given words (pencil, tree) which is similar to Altmann’s(2004). To compare the semantic distances between two different text corpora (DementiaBank vs. Wikipedia(or Blog)), independent samples t-test was conducted. Stepwise logistic regression was conducted to identify whether the verb clusters are associated with demographic factors.

In noun-verb semantic distance, DementiaBank showed significantly higher results compared to the Wikipedia and Blog database on ‘pencil’ and ‘tree’. These results indicate that the semantic distance between the noun and verb is closer in the DementiaBank. In the verb clustering and regression analyses, education had a significantly positive effect on the choice of ‘write(baseline)’ or be-verb for the ‘pencil’, but marginally positive on the choice of verb ‘write’(baseline) or ‘use’ for the noun ‘pencil’. For MMSE scores, it was   significantly negative on the choice of verb, either ‘write’(baseline) or ‘be’ for the ‘pencil’, and significantly positive on the choice of either ‘be’(baseline) or ‘grow’ for the noun ‘tree’.

In conclusion, semantic distances between nouns and verbs are shorter in AD patients compared to the existing big databases. Moreover, the semantic weight of verbs that AD patients used was significantly related to the severity of dementia, indicating they tend to use more light verbs as their disease progress.

Keyphrases: Alzheimer’s disease, semantic distance, verb cluster

@Booklet{EasyChair:6393,
  author = {Jee Eun Sung and Yoonseob Lim and Kimun Kim and Sujin Choi},
  title = {Noun-verb semantic distance analyses in sentence production of Alzheimer’s disease},
  howpublished = {EasyChair Preprint no. 6393},

  year = {EasyChair, 2021}}