A combination of LSA, frequency-weighted word overlap, and regular expressions is AutoTutor's best semantic matcher; syntactic parsers proved not useful¶
Claim · All claims
Evidence · 1 study · reviewr2·q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2019: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? The best semantic matching results for comparing student contributions with expectations and misconceptions came from combining latent semantic analysis, frequency-weighted word overlap, and regular expressions, while syntactic computations did not prove useful. → Graesser 2016
Evidence¶
Graesser 2016¶
Graesser, A. C. (2016). Conversations with AutoTutor Help Students Learn. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-015-0086-4
q2 · i? · review · r2
The article reports the authors' multi-year evaluation of semantic matchers for AutoTutor, finding the LSA plus word overlap plus regular expressions combination best, with LSA plus regular expressions showing "high reliability scores" against human experts. Syntactic computations were not useful because student contributions are often telegraphic and ungrammatical.
"The best results are a combination of latent semantic analysis (LSA) (Landauer et al. 2007), frequency weighted word overlap (rarer words and negations have higher weight), and regular expressions. In fact, LSA plus regular expressions have had high reliability scores in comparisons wi th human experts"
Discussion¶
Related Claims¶
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
lsa-word-overlap-regex-best-semantic-matcher |
title |
A combination of LSA, frequency-weighted word overlap, and regular expressions is AutoTutor's best semantic matcher; syntactic parsers proved not useful |
description |
A combination of LSA, frequency-weighted word overlap, and regular expressions is AutoTutor's best semantic matcher; syntactic parsers proved not useful |
status |
review |
evidence_strength |
weak |
newest_evidence |
2016 |
recheck_by |
2019 |
generated |
by process:wiki-ingest on 2026-10-17 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — graesser-2016 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.