Dimensions overall score 5.0

GitHub Code Pulse

No public code linked for this paper yet.

• Automated classification of learners entails risks of harmful labelling, covert screening, algorithmic bias, and institutional misuse.limitation 90%
• Dyslexic spelling errors exhibit systematic phonological and orthographic patterns that distinguish them from errors produced by typically developing writers.result 95%
• Prior work on dyslexic-specific spell-checking has focused predominantly on error correction rather than attribution, and has largely neglected ethical risks.limitation 90%
• The proposed twin-input neural model achieves 93.01% accuracy and an F1-score of 94.01% for dyslexic error attribution.result 95%
• Phonetically plausible errors and vowel confusions emerge as the strongest attribution signals for dyslexic error patterns.result 90%
• Feasibility of high-accuracy dyslexic error attribution is insufficient for deployment in high-stakes educational contexts without ethical safeguards.limitation 85%
• The paper formulates dyslexic error attribution as a binary classification task based on misspelt words and their correct target forms.method 90%
• The proposed approach uses a comprehensive feature set capturing orthographic, phonological, and morphological properties of each error.method 85%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card