Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Latent Semantic Analysis Discriminates Children with Developmental Language Disorder (DLD) from Children with Typical Language Development

Bååth, Rasmus LU ; Sikström, Sverker LU orcid ; Kalnak, Nelli LU ; Hansson, Kristina LU orcid and Sahlén, Birgitta LU (2019) In Journal of Psycholinguistic Research 48(3). p.683-697
Abstract

Computer based analyses offer a possibility for objective methods to assess semantic-linguistic quality of narratives at the text level. The aim of the present study is to investigate whether a semantic language impairment index (SELIMI) based on latent semantic analysis (LSA) can discriminate between children with developmental language disorder (DLD) and children with typical language development. Spoken narratives from 54 children with DLD and 54 age matched controls with typical language development were summarized in a semantic representation generated using LSA. A statistical model was trained to discriminate between children with DLD and children with typical language development, given the semantic vector representing each... (More)

Computer based analyses offer a possibility for objective methods to assess semantic-linguistic quality of narratives at the text level. The aim of the present study is to investigate whether a semantic language impairment index (SELIMI) based on latent semantic analysis (LSA) can discriminate between children with developmental language disorder (DLD) and children with typical language development. Spoken narratives from 54 children with DLD and 54 age matched controls with typical language development were summarized in a semantic representation generated using LSA. A statistical model was trained to discriminate between children with DLD and children with typical language development, given the semantic vector representing each individual child’s narrative. The results show that SELIMI could distinguish between children with DLD and children with typical language development significantly better than chance and thus has a potential to complement traditional analyses focussed on form or on the word level.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Developmental language disorder, Latent semantic analysis, Narratives, Semantic linguistic ability
in
Journal of Psycholinguistic Research
volume
48
issue
3
pages
683 - 697
publisher
Springer
external identifiers
  • pmid:30684119
  • scopus:85060711149
ISSN
0090-6905
DOI
10.1007/s10936-018-09625-8
language
English
LU publication?
yes
id
6596ae6f-1cc4-4c35-a461-39f58798a2a9
date added to LUP
2019-02-06 14:26:50
date last changed
2024-10-15 18:19:49
@article{6596ae6f-1cc4-4c35-a461-39f58798a2a9,
  abstract     = {{<p>Computer based analyses offer a possibility for objective methods to assess semantic-linguistic quality of narratives at the text level. The aim of the present study is to investigate whether a semantic language impairment index (SELIMI) based on latent semantic analysis (LSA) can discriminate between children with developmental language disorder (DLD) and children with typical language development. Spoken narratives from 54 children with DLD and 54 age matched controls with typical language development were summarized in a semantic representation generated using LSA. A statistical model was trained to discriminate between children with DLD and children with typical language development, given the semantic vector representing each individual child’s narrative. The results show that SELIMI could distinguish between children with DLD and children with typical language development significantly better than chance and thus has a potential to complement traditional analyses focussed on form or on the word level.</p>}},
  author       = {{Bååth, Rasmus and Sikström, Sverker and Kalnak, Nelli and Hansson, Kristina and Sahlén, Birgitta}},
  issn         = {{0090-6905}},
  keywords     = {{Developmental language disorder; Latent semantic analysis; Narratives; Semantic linguistic ability}},
  language     = {{eng}},
  month        = {{01}},
  number       = {{3}},
  pages        = {{683--697}},
  publisher    = {{Springer}},
  series       = {{Journal of Psycholinguistic Research}},
  title        = {{Latent Semantic Analysis Discriminates Children with Developmental Language Disorder (DLD) from Children with Typical Language Development}},
  url          = {{http://dx.doi.org/10.1007/s10936-018-09625-8}},
  doi          = {{10.1007/s10936-018-09625-8}},
  volume       = {{48}},
  year         = {{2019}},
}