Identifying reading strategies using latent semantic analysis

Comparing semantic benchmarks

Keith Millis, Hyun Jeong Joyce Kim, Stacey Todaro, Joseph P. Magliano, Katja Wiemer-Hastings, Danielle McNamara

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We explored methods of using latent semantic analysis (LSA) to identify reading strategies in students' self-explanations that are collected as part of a Web-based reading trainer. In this study, college students self-explained scientific texts, one sentence at a time. LSA was used to measure the similarity between the self-explanations and semantic benchmarks (groups of words and sentences that together represent reading strategies). Three types of semantic benchmarks were compared: content words, exemplars, and strategies. Discriminant analyses were used to classify global and specific reading strategies using the LSA cosines. All benchmarks contributed to the classification of general reading strategies, but the exemplars did the best in distinguishing subtle semantic differences between reading strategies. Pragmatic and theoretical concerns of using LSA are discussed.

Original languageEnglish (US)
Pages (from-to)213-221
Number of pages9
JournalBehavior Research Methods, Instruments, and Computers
Volume36
Issue number2
StatePublished - May 2004
Externally publishedYes

Fingerprint

Benchmarking
Semantics
Reading
Students
Discriminant Analysis
Benchmark
Latent Semantic Analysis
Reading Strategies

ASJC Scopus subject areas

  • Psychology(all)
  • Experimental and Cognitive Psychology
  • Psychology (miscellaneous)

Cite this

Identifying reading strategies using latent semantic analysis : Comparing semantic benchmarks. / Millis, Keith; Kim, Hyun Jeong Joyce; Todaro, Stacey; Magliano, Joseph P.; Wiemer-Hastings, Katja; McNamara, Danielle.

In: Behavior Research Methods, Instruments, and Computers, Vol. 36, No. 2, 05.2004, p. 213-221.

Research output: Contribution to journalArticle

Millis, Keith ; Kim, Hyun Jeong Joyce ; Todaro, Stacey ; Magliano, Joseph P. ; Wiemer-Hastings, Katja ; McNamara, Danielle. / Identifying reading strategies using latent semantic analysis : Comparing semantic benchmarks. In: Behavior Research Methods, Instruments, and Computers. 2004 ; Vol. 36, No. 2. pp. 213-221.
@article{7d4ddffc30d7437ca4c51352d53fa7e4,
title = "Identifying reading strategies using latent semantic analysis: Comparing semantic benchmarks",
abstract = "We explored methods of using latent semantic analysis (LSA) to identify reading strategies in students' self-explanations that are collected as part of a Web-based reading trainer. In this study, college students self-explained scientific texts, one sentence at a time. LSA was used to measure the similarity between the self-explanations and semantic benchmarks (groups of words and sentences that together represent reading strategies). Three types of semantic benchmarks were compared: content words, exemplars, and strategies. Discriminant analyses were used to classify global and specific reading strategies using the LSA cosines. All benchmarks contributed to the classification of general reading strategies, but the exemplars did the best in distinguishing subtle semantic differences between reading strategies. Pragmatic and theoretical concerns of using LSA are discussed.",
author = "Keith Millis and Kim, {Hyun Jeong Joyce} and Stacey Todaro and Magliano, {Joseph P.} and Katja Wiemer-Hastings and Danielle McNamara",
year = "2004",
month = "5",
language = "English (US)",
volume = "36",
pages = "213--221",
journal = "Behavior Research Methods, Instruments, and Computers",
issn = "1554-351X",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Identifying reading strategies using latent semantic analysis

T2 - Comparing semantic benchmarks

AU - Millis, Keith

AU - Kim, Hyun Jeong Joyce

AU - Todaro, Stacey

AU - Magliano, Joseph P.

AU - Wiemer-Hastings, Katja

AU - McNamara, Danielle

PY - 2004/5

Y1 - 2004/5

N2 - We explored methods of using latent semantic analysis (LSA) to identify reading strategies in students' self-explanations that are collected as part of a Web-based reading trainer. In this study, college students self-explained scientific texts, one sentence at a time. LSA was used to measure the similarity between the self-explanations and semantic benchmarks (groups of words and sentences that together represent reading strategies). Three types of semantic benchmarks were compared: content words, exemplars, and strategies. Discriminant analyses were used to classify global and specific reading strategies using the LSA cosines. All benchmarks contributed to the classification of general reading strategies, but the exemplars did the best in distinguishing subtle semantic differences between reading strategies. Pragmatic and theoretical concerns of using LSA are discussed.

AB - We explored methods of using latent semantic analysis (LSA) to identify reading strategies in students' self-explanations that are collected as part of a Web-based reading trainer. In this study, college students self-explained scientific texts, one sentence at a time. LSA was used to measure the similarity between the self-explanations and semantic benchmarks (groups of words and sentences that together represent reading strategies). Three types of semantic benchmarks were compared: content words, exemplars, and strategies. Discriminant analyses were used to classify global and specific reading strategies using the LSA cosines. All benchmarks contributed to the classification of general reading strategies, but the exemplars did the best in distinguishing subtle semantic differences between reading strategies. Pragmatic and theoretical concerns of using LSA are discussed.

UR - http://www.scopus.com/inward/record.url?scp=4444292281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4444292281&partnerID=8YFLogxK

M3 - Article

VL - 36

SP - 213

EP - 221

JO - Behavior Research Methods, Instruments, and Computers

JF - Behavior Research Methods, Instruments, and Computers

SN - 1554-351X

IS - 2

ER -