Automated English Essay Scoring and Feedback System

54.5 KB of code implements a system for automated English writing scoring and feedback using deep semantic analysis. The system, created by Shuling Yang and uploaded in April 2026, processes the ASAP-AES dataset to predict overall essay scores and four dimensional scores. It includes modules for error detection and personalized feedback generation.

Use Cases

• Predict overall essay scores using a BERT-based model with multi-task learning.
• Generate dimensional scores for linguistic expression, content quality, structural logic, and grammar accuracy.
• Detect writing errors using a pattern matching and BiLSTM-CRF module.
• Produce hierarchical, personalized feedback by combining template-based and generative approaches.

Strengths

• System implements five core modules for a complete scoring and feedback pipeline.
• Model predicts both an overall score and four specific dimensional scores.
• License is CC-BY-4.0, permitting open sharing and adaptation.

Limitations

• 54.5 KB size indicates a small codebase, not a large dataset.
• No dataset rows or columns are provided, only implementation code.
• Relies on the external ASAP-AES dataset, which is not included.

Provenance

Source

Shuling Yang via figshare.

Collection Method

Code implementation of a scoring system.

Freshness

Last updated April 2026.