scrosseye
Professor in Special Education focusing on applied linguistics, natural language processing, and learning sciences.
Vanderbilt University
Pinned Repositories
AI-Detection-Student-Writing
Corpus of student essays used in Kaggle AI detection competition
Claim_Identification_Corpus
314 persuasive essays annotated for claims. The essays were written by undergraduate students (N = 314) at a public university in the United States who were native speakers of English.
CLASSE
Common Lit Augmented Student Summary Evaluation (CLASSE) corpus
CLEAR-Corpus
Repository for the CommonLit Ease of Readability Corpus
clear_corpus_analyses
R code for analyses of CLEAR corpus
ELLIPSE-Corpus
the English Language Learner Insight, Proficiency and Skills Evaluation (ELLIPSE) Corpus
PERSUADE_corpus
This is the repository for the PERSUADE corpus which contains over 280,000 discourse annotations for over 25,000 argumentative essays
persuade_corpus_2.0
This is the data associated with the PERSUADE Corpus 2.0 version
tammi
Base code for the Tool for Automatic Measurement of Morphological Information (TAMMI)
transcription_detection
Keystroke logs for 1,000 essays that were naturally written or transcribed.
scrosseye's Repositories
scrosseye/persuade_corpus_2.0
This is the data associated with the PERSUADE Corpus 2.0 version
scrosseye/CLEAR-Corpus
Repository for the CommonLit Ease of Readability Corpus
scrosseye/ELLIPSE-Corpus
the English Language Learner Insight, Proficiency and Skills Evaluation (ELLIPSE) Corpus
scrosseye/PERSUADE_corpus
This is the repository for the PERSUADE corpus which contains over 280,000 discourse annotations for over 25,000 argumentative essays
scrosseye/tammi
Base code for the Tool for Automatic Measurement of Morphological Information (TAMMI)
scrosseye/CLASSE
Common Lit Augmented Student Summary Evaluation (CLASSE) corpus
scrosseye/Claim_Identification_Corpus
314 persuasive essays annotated for claims. The essays were written by undergraduate students (N = 314) at a public university in the United States who were native speakers of English.
scrosseye/clear_corpus_analyses
R code for analyses of CLEAR corpus
scrosseye/Mechanical_turk_essay_scoring
Dataframe for 400 essays, their linguistic features, and expert and non-expert scores
scrosseye/named-entity-ferpa
An R script to pull out named entities from educational data to check for FERPA complaince.
scrosseye/PeRDict-Analyses
The repository contains programming scripts for calculating the mean number of rhymes per word per text as well as code for conducting statistical analyses of the data.
scrosseye/PeRDict-database
The Perfect Rhymes Dictionary Database is housed here
scrosseye/Tammi-Analyses
Analysis of the CLEAR and ELLIPSE corpus using TAMMI