Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system

Treviso, Marcos; Santos, Leandro Borges dos; Shulby, Christopher; Hübner, Lilian Cristine; Aluísio, Sandra Maria

doi:10.15448/1984-7726.2018.1.30955

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(a) fairy-tale retell is a useful type of narrative for this purpose that, unlike most language assessment tools, is not copyrighted and is much less time consuming to carry out; (b) from the transcribed retold stories it is possible to automatically extract a great number of metrics that indicate expressive oral abilities in various languages (English, Portuguese, Spanish) using free computer software such as Coh-Metrix and NILC-Metrix that avoids errors and time-consuming subjective manual assessments of narratives, making the results more reliable (see Miller et al, 2016) and easier to replicate Treviso et al, 2018); (c) it is feasible and simple to use various language metrics grouped into language categories that correspond to the use of language at the word, sentence and inter-sentence levels, which facilitates comparisons across studies, especially those that analyze a limited number of different metrics; (d) all main category levels of oral language skills seem to improve with age in early adolescence, even when a simple narrative is involved; (e) clear developmental effects can be found according to chronological age (but it is probably wise to do so in months), pubertal status or school grade, although the two latter factors may have differential effects if samples are very large, but are probably of little practical application; (f) since preposition diversity was the metric that presented the largest effect size for all developmental measures, it might be interesting to investigate this improvement further in future studies; this seems to be the case for the Portuguese language, however other languages might differ in this aspect, which should also be further explored;…”

Section: Implications and Applications Of The Resultsmentioning

confidence: 99%

Tell me a fairy tale: an automated approach to analyze expressive language development in adolescents

Pedroni¹,

Rocha²,

Puglisi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Expressive oral language development (EOLD) in adolescence is understudied and usuallyinvolves a small set of language parameters. To explore this development in more detail, weused automated language analyses of transcripts of narrative speech (fairy-tale retellings) of257 Portuguese-speaking 9-15-year-olds. We grouped multiple linguistic parameters intoword/lexical, sentence/grammar and inter-sentence/cohesion category levels entered asmultivariate factors in general linear models considering the effects of development, sex andparental schooling. We found substantial EOLD at all levels, with negligible effects (exceptin one level) of sex, and parental schooling (a measure of participants’ socioeconomic status).Age (months), pubertal status and school grade generally showed comparable EOLD effects,suggesting sexual maturation and participants’ grade are not more determinant factors thanage. In summary, automated scoring of linguistic features of transcribed fairy-tale retellings isa sensitive, inexpensive, and ecological way of identifying EOLD in adolescence whichminimizes socioeconomic effects on oral language.

show abstract

Section: Implications and Applications Of The Resultsmentioning

confidence: 99%

Tell me a fairy tale: an automated approach to analyze expressive language development in adolescents

Pedroni¹,

Rocha²,

Puglisi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, studies should better look at the impact of discourse task typologies on language automatic assessment, enabling the development of intervention strategies to assist in the diagnosis of cognitive decline at earlier stages. Automatic language assessment is a promising tool for researchers and clinicians, as it provides data to detect language impairments and characterize typical adults and older adult groups according to their linguistic performance, such as in high compared to low educational-level groups [62], and was useful in differentiating AD patients from healthy elderly adults in our study, which included low education and low SES samples.…”

Section: Linguistic Features and Memorymentioning

confidence: 99%

Automatic Assessment of Connected Speech and Its Relation to Memory in Alzheimer’s Disease in Low Education

Smidarle,

Wilson,

Leal

et al. 2023

Folia Phoniatr Logop

View full text Add to dashboard Cite

Introduction: Discourse is one of the main linguistic aspects affected by Alzheimer’s Disease (AD) and its relationship with memory needs to be further studied, mainly in low education and low socioeconomic status (SES) groups. The present study aimed at investigating differences in the recall of short narratives between participants with mild AD (AD) and a control group of typical older adults (CG) with the use of automatic assessment. Methods: 17 older adults diagnosed with AD (mean age 76.41, mean education 5,82) and 34 typical older adults (mean age 74.26, mean education 7.09) were asked to listen to and then retell a short story. Syntactic, lexical, and semantic features were assessed via the NILC-Metrix software, and the features were correlated with episodic, working, and semantic memory assessment. Results: Differences were found in 7 of the 34 features assessed. Syntactically, the group diagnosed with AD produced narratives with fewer sentences, fewer words per sentence, and lower Yngve depth scores. Lexically, the AD group produced narratives with fewer words and prepositions per sentence. Semantically, the narratives produced by the AD group featured words with a lower mean age of acquisition, and lower Brunét’s index scores. For the CG group, episodic memory performance correlated with the ratio of conjunctions. No other significant correlation was found for semantic and working memory in the CG. No correlation was found between memory performance and linguistic features for the AD group. Discussion: The automatic assessment of linguistic features showed impaired narrative recall in participants diagnosed with AD relative to healthy controls at the syntactic, lexical, and semantic levels of discourse. These findings corroborate previous literature showing a decline in discourse production performance resulting from cognitive impairment in AD. Conclusion: The assessment of linguistic performance through a narrative recall task provides valuable insights into cognitive decline related to Alzheimer’s disease.

show abstract

“…Faz-se necessário, portanto, analisar o efeito dos hábitos de leitura e escrita na produção discursiva oral (e em outros domínios da linguagem), em especial em países onde os níveis de escolaridade são baixos e esses hábitos poderiam compensar a baixa escolaridade (COTRENA et al, 2016). Outra linha emergente de estudos, não encontrada nesta revisão, trata do uso de softwares para análise da relação entre hábitos de leitura e de escrita ou escolaridade na produção discursiva oral (TREVISO et al, 2018;SANTOS et al, 2019).…”

Section: I S C U S S ã Ounclassified

Avaliação Da Produção Discursiva Oral No Envelhecimento E Sua Relação Com Escolaridade E Hábitos De Leitura E Escrita: Uma Revisão Sistemática

Malcorra

Wilson

Hübner

2021

Estud. interdiscip. envelhec.

Self Cite

View full text Add to dashboard Cite

A presente revisão sistemática tem por objetivo verificar quais as tarefas comumente utilizadas para elucidação da produção discursiva oral do adulto idoso e sua relação com escolaridade e hábitos de leitura e escrita. Para tanto, buscaram-se artigos publicados nas bases de dados Scopus, Web of Science, PubMed, MEDLINE e LILACS. Os termos utilizados foram (“discourse production” OR “oral production” OR “narrative production”) AND (aging OR elderly OR “older adults”) AND (education OR schooling OR “reading habits” OR “writing habits”). Os critérios de seleção incluíram: (a) artigo original avaliado por pares; (b) com foco na produção discursiva oral no envelhecimento típico; (c) publicado entre 1990 e 2019. Foram encontrados, no total, 456 registros, dos quais 393 foram excluídos pelo título e 12 após leitura na íntegra, por não se relacionarem ao tema. De acordo com os critérios de seleção, 19 artigos foram selecionados. Verificou-se que grande parte das pesquisas utiliza tarefas baseadas em estímulos visuais, sobretudo em seu formato sequencial, enquanto uma pequena parte utiliza tarefas baseadas em eventos autobiográficos, conversações livres ou descrição de procedimentos. Algumas pesquisas compararam a produção discursiva oral da amostra em questão em diferentes tarefas. Poucos estudos incluíram a variável escolaridade em seus experimentos, enquanto nenhum estudo investigou o efeito dos hábitos de leitura e escrita. Devido à sua complexidade, estudos no nível do discurso precisam considerar a influência do tipo de tarefa para a elucidação do processamento, assim como fatores sociodemográficos e culturais dos seus participantes.

show abstract

Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system

Cited by 4 publications

References 19 publications

Tell me a fairy tale: an automated approach to analyze expressive language development in adolescents

Tell me a fairy tale: an automated approach to analyze expressive language development in adolescents

Automatic Assessment of Connected Speech and Its Relation to Memory in Alzheimer’s Disease in Low Education

Avaliação Da Produção Discursiva Oral No Envelhecimento E Sua Relação Com Escolaridade E Hábitos De Leitura E Escrita: Uma Revisão Sistemática

Contact Info

Product

Resources

About