View in EDS

Predicting Contextual Informativeness for Vocabulary Learning

Saved in:
Bibliographic Details
Title: Predicting Contextual Informativeness for Vocabulary Learning
Language: English
Authors: Kapelner, Adam, Soterwood, Jeanine, NessAiver, Shalev, Adlof, Suzanne
Source: Grantee Submission. 2018.
Peer Reviewed: Y
Page Count: 17
Publication Date: 2018
Sponsoring Agency: Institute of Education Sciences (ED)
Contract Number: R305A130467
Document Type: Reports - Research
Education Level: High Schools
Secondary Education
Descriptors: Vocabulary Development, Databases, Training, Models, Statistical Analysis, Prediction, Performance, High School Students, Language Arts, Secondary School Teachers, Surveys, Context Effect
Geographic Terms: South Carolina, Connecticut
DOI: 10.1109/TLT.2018.2789900
Abstract: Vocabulary knowledge is essential to educational progress. High quality vocabulary instruction requires supportive contextual examples to teach word meaning and proper usage. Identifying such contexts by hand for a large number of words can be difficult. In this work, we take a statistical learning approach to engineer a system that predicts informativeness of a context for target words that span the range of difficulty from middle school to college level. Our database (released open source) includes 1,000 hand-selected words associated with approximately 70,000 contextual examples gathered from the Internet. Our training data included each context rated by 10 individuals on a four-point informativeness scale. We process the text of each context into a novel collection of approximately 600 numerical features that captures diverse linguistic information. We then fit a nonparametric regression model using Random Forests and compute out-of-sample prediction performance using cross-validation. Our system performs well enough that it can replace a human judge: for a target word not found in our dataset, we can provide curated contexts to a student learner such that most of the contexts (54 percent) feature rich contextual clues and confusing contexts are rare (<1 percent). The quality of our curated contexts was validated by an independent panel of high school language arts teachers. [This paper was published in "IEEE Transactions on Learning Technologies" v11 n1 p13-26 Jan-Mar 2018 (ISSN 1939-1382) (EJ1174702).]
Abstractor: As Provided
IES Funded: Yes
Entry Date: 2018
Accession Number: ED589145
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=ED589145
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: ED589145
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Predicting Contextual Informativeness for Vocabulary Learning
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kapelner%2C+Adam%22&quot;&gt;Kapelner, Adam&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Soterwood%2C+Jeanine%22&quot;&gt;Soterwood, Jeanine&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22NessAiver%2C+Shalev%22&quot;&gt;NessAiver, Shalev&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Adlof%2C+Suzanne%22&quot;&gt;Adlof, Suzanne&lt;/searchLink&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;SO&quot; term=&quot;%22Grantee+Submission%22&quot;&gt;&lt;i&gt;Grantee Submission&lt;/i&gt;&lt;/searchLink&gt;. 2018.
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 17
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2018
– Name: SourceSuprt
  Label: Sponsoring Agency
  Group: SrcSuprt
  Data: Institute of Education Sciences (ED)
– Name: NumberContract
  Label: Contract Number
  Group: NumCntrct
  Data: R305A130467
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Reports - Research
– Name: Audience
  Label: Education Level
  Group: Audnce
  Data: &lt;searchLink fieldCode=&quot;EL&quot; term=&quot;%22High+Schools%22&quot;&gt;High Schools&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;EL&quot; term=&quot;%22Secondary+Education%22&quot;&gt;Secondary Education&lt;/searchLink&gt;
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Vocabulary+Development%22&quot;&gt;Vocabulary Development&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Databases%22&quot;&gt;Databases&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Training%22&quot;&gt;Training&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Models%22&quot;&gt;Models&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Statistical+Analysis%22&quot;&gt;Statistical Analysis&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Prediction%22&quot;&gt;Prediction&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Performance%22&quot;&gt;Performance&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22High+School+Students%22&quot;&gt;High School Students&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Language+Arts%22&quot;&gt;Language Arts&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Secondary+School+Teachers%22&quot;&gt;Secondary School Teachers&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Surveys%22&quot;&gt;Surveys&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Context+Effect%22&quot;&gt;Context Effect&lt;/searchLink&gt;
– Name: Subject
  Label: Geographic Terms
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22South+Carolina%22&quot;&gt;South Carolina&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Connecticut%22&quot;&gt;Connecticut&lt;/searchLink&gt;
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1109/TLT.2018.2789900
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Vocabulary knowledge is essential to educational progress. High quality vocabulary instruction requires supportive contextual examples to teach word meaning and proper usage. Identifying such contexts by hand for a large number of words can be difficult. In this work, we take a statistical learning approach to engineer a system that predicts informativeness of a context for target words that span the range of difficulty from middle school to college level. Our database (released open source) includes 1,000 hand-selected words associated with approximately 70,000 contextual examples gathered from the Internet. Our training data included each context rated by 10 individuals on a four-point informativeness scale. We process the text of each context into a novel collection of approximately 600 numerical features that captures diverse linguistic information. We then fit a nonparametric regression model using Random Forests and compute out-of-sample prediction performance using cross-validation. Our system performs well enough that it can replace a human judge: for a target word not found in our dataset, we can provide curated contexts to a student learner such that most of the contexts (54 percent) feature rich contextual clues and confusing contexts are rare (&lt;1 percent). The quality of our curated contexts was validated by an independent panel of high school language arts teachers. [This paper was published in &quot;IEEE Transactions on Learning Technologies&quot; v11 n1 p13-26 Jan-Mar 2018 (ISSN 1939-1382) (EJ1174702).]
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: CodeSource
  Label: IES Funded
  Group: SrcInfo
  Data: Yes
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2018
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED589145
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED589145
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TLT.2018.2789900
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
    Subjects:
      – SubjectFull: Vocabulary Development
        Type: general
      – SubjectFull: Databases
        Type: general
      – SubjectFull: Training
        Type: general
      – SubjectFull: Models
        Type: general
      – SubjectFull: Statistical Analysis
        Type: general
      – SubjectFull: Prediction
        Type: general
      – SubjectFull: Performance
        Type: general
      – SubjectFull: High School Students
        Type: general
      – SubjectFull: Language Arts
        Type: general
      – SubjectFull: Secondary School Teachers
        Type: general
      – SubjectFull: Surveys
        Type: general
      – SubjectFull: Context Effect
        Type: general
      – SubjectFull: South Carolina
        Type: general
      – SubjectFull: Connecticut
        Type: general
    Titles:
      – TitleFull: Predicting Contextual Informativeness for Vocabulary Learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kapelner, Adam
      – PersonEntity:
          Name:
            NameFull: Soterwood, Jeanine
      – PersonEntity:
          Name:
            NameFull: NessAiver, Shalev
      – PersonEntity:
          Name:
            NameFull: Adlof, Suzanne
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2018
          Titles:
            – TitleFull: Grantee Submission
              Type: main
ResultId 1