Research map / Architectures and efficiency / RNNs and normalization
Argument Mining for Improving the Automated Scoring of Persuasive Essays
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add argumentative features to base AES features | BASE · TOEFL11 cross-fold | quadratic-weighted kappa: 0.599 -> 0.611 | Helped |
| add argumentative features to base AES features | BASE · ASAP prompt 2 cross-fold | quadratic-weighted kappa: 0.680 -> 0.689 | Helped |
| add argumentative features to base AES features | BASE · ASAP prompt 1 cross-fold | quadratic-weighted kappa: 0.831 -> 0.830 | No clear effect |
| add argumentative features to base AES features | BASE · ASAP cross-prompt P1 to P2 | quadratic-weighted kappa: 0.585 -> 0.622 | Helped |
| add argumentative features to base AES features | BASE · TOEFL11 cross-prompt | quadratic-weighted kappa: 0.591 -> 0.600 | Helped |
| add argumentative features to base AES features | BASE · TOEFL11 test set | quadratic-weighted kappa: 0.604 -> 0.607 | No clear effect |
| use only argumentative features without base features (ablation) | ARG · TOEFL11 cross-fold | quadratic-weighted kappa: 0.599 -> 0.494 | Hurt |
| add argument flow (AF) features (ablation) | All · TOEFL11 cross-fold | quadratic-weighted kappa: 0.604 -> 0.611 | Helped |
| add argument flow (AF) features (ablation) | All · TOEFL11 cross-prompt | quadratic-weighted kappa: 0.601 -> 0.600 | Hurt |
| add structure typology (TS) features (ablation) | All · TOEFL11 and ASAP cross-fold | quadratic-weighted kappa: 0.611 -> 0.611 (TOEFL11) | No clear effect |
| add argument component (AC) features (ablation) | All · ASAP prompt 2 cross-fold | quadratic-weighted kappa: 0.676 -> 0.689 | Helped |
| add relation (RL) features (ablation) | All · ASAP cross-prompt P1 to P2 | quadratic-weighted kappa: 0.626 -> 0.622 | Hurt |
Closest papers by meaning
- Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability (AAAI 2024 · similarity 0.87)
- Corpus Wide Argument Mining—A Working Solution (AAAI 2020 · similarity 0.87)
- Automated Cross-prompt Scoring of Essay Traits (AAAI 2021 · similarity 0.86)
- OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset (NeurIPS 2024 · similarity 0.85)
- H-AES: Towards Automated Essay Scoring for Hindi (AAAI 2023 · similarity 0.85)
- KAES: Multi-aspect Shared Knowledge Finding and Aligning for Cross-prompt Automated Scoring of Essay Traits (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.