Using Latent Semantic Analysis to Evaluate the Contributions of Students in AutoTutor

Graesser, Arthur C.; Hastings, Peter; Wiemer-Hastings, Katja; Harter, Derek; Person, Natalie K.

doi:10.1076/1049-4820(200008)8:2;1-b;ft129

Cited by 139 publications

(95 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Second, the LSA-based assessment of the source of self-explanations was, in fact, remarkably simi- lar to human-based assessments. This illustrates the validity of the LSA-based approach and is consistent with prior research demonstrating that LSA cosines are similar to human judgments of similarity (Graesser et al, 2000;Landauer & Dumais, 1997;. Finally, we were able to classify 86% of self-explanationseither as minimalist (paraphrases) or as using multiple strategies (knowledge building), with only three LSA-based predictors (i.e., two benchmarks and vector length).…”

Section: Discussionsupporting

confidence: 71%

See 1 more Smart Citation

Using latent semantic analysis to assess reader strategies

Magliano

Wiemer-Hastings

Millis

et al. 2002

Behavior Research Methods, Instruments, & Computers

Self Cite

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 71%

“…Furthermore, Graesser and his colleagues have successfully used LSA in a computerized tutor called AutoTutor (Graesser et al, 2000;Wiemer-Hastings, Wiemer-Hastings, & Graesser, 1999). With AutoTutor, students are asked questions by a computerized tutor and are required to type their answers into the computer.…”

Section: Using Lsa To Assess Compliance With Sertmentioning

confidence: 99%

Using latent semantic analysis to assess reader strategies

Magliano

Wiemer-Hastings

Millis

et al. 2002

Behavior Research Methods, Instruments, & Computers

Self Cite

View full text Add to dashboard Cite

“…For example, LSA has been found to correlate well with expert graders in grading essay papers (Foltz, Laham, & Landauer, 1999), and it is generally consistent with human judgments of similarity (Landauer & Dumais, 1997;Landauer, Laham, Rehder, & Schreiner, 1997;Magliano et al, 2002). In addition, LSA has been successfully used within a computer literacy tutor called AutoTutor (Graesser et al, 2000;Wiemer-Hastings, Wiemer-Hastings, & Graesser, 1999). AutoTutor presents questions to students, evaluates students' answers, and gives appropriate feedback.…”

Section: Computerizing Reading Trainingmentioning

confidence: 99%

Computerizing reading training: Evaluation of a latent semantic analysis space for science text

Kurby

Wiemer-Hastings

Ganduri

et al. 2003

Behavior Research Methods, Instruments, & Computers

Self Cite

View full text Add to dashboard Cite

The effectivenessof a domain-specific latent semantic analysis (LSA) in assessing reading strategies was examined. Students were given self-explanation reading training (SERT) and asked to think aloud after each sentence in a science text. Novice and expert human raters and two LSA spaces (general reading, science) rated the similarity of each think-aloud protocol to benchmarks representing three different reading strategies (minimal, local, and global). The science LSA space correlated highly with human judgments, and more highly than did the general reading space. Also, cosines from the science LSA spaces can distinguish between different levels of semantic similarity, but may have trouble in distinguishing local processing protocols. Thus, a domain-specific LSA space is advantageous regardless of the size of the space. The results are discussed in the context of applying the science LSA to a computerbased version of SERT that gives online feedback based on LSA cosines.

show abstract

“…Applying this method eliminates the need for initial stereotypical profiles or any additional input from a user. In the second phase of learning, a rule induction procedure [15] is employed to generate rules. These rules describe the concept of cluster membership or relationships.…”

Section: B ML Tutormentioning

confidence: 99%