Prognosis Essay Scoring and Article Relevancy Using Multi-Text Features and Machine Learning
importance 3/10
ai assisted
Text and Document Classification Technologies education technology stage: research open-source model
Problem
Manual essay scoring and article relevancy classification are slow, costly, and inconsistent across evaluators.
Why it matters
Human evaluation consumes evaluator time and may apply criteria unequally.
What the AI did
Ensemble machine learning with multi-text features automatically scored essays and classified articles as IoT-relevant on two datasets.
Results
not stated in source (efficacy comparison truncated in abstract)
Impact
Evidence shows a model tested on two datasets, but performance figures are not visible.
Record
| Venue | Symmetry |
|---|---|
| Published | 2017 |
| Work type | article |
| Authors | Arif Mehmood, Byung-Won On, Ingyu Lee, Gyu Sang Choi |
| Citations | 15 (OpenAlex, at import time) |
| References | 66 |
| Model or method | ensemble machine learning (specific model not stated) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/sym9010011 |
| Open access | gold |
| Keywords | essay scoring, ensemble learning, text features, article classification, bibliometrics |
Importance rating
3
incremental / niche
Manual essay scoring and article relevancy classification are slow, costly, and inconsistent; a real but narrow efficiency gain for evaluators and researchers.