# Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems

arXiv: https://arxiv.org/abs/2103.07785 · HTML: https://mlsanity.com/paper/2103.07785/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 51 references that are in the map.
- First posted on arXiv 13 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification](https://mlsanity.com/paper/2004.12617/) (2020)
- [Cross-lingual RST Discourse Parsing](https://mlsanity.com/paper/1701.02946/) (2017)
- [Toward Fast and Accurate Neural Discourse Segmentation](https://mlsanity.com/paper/1808.09147/) (2018)
- [Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph](https://mlsanity.com/paper/1804.05918/) (2018)
- [Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System](https://mlsanity.com/paper/2005.02431/) (2020)
- [Implicit Discourse Relation Classification via Multi-Task Neural Networks](https://mlsanity.com/paper/1603.02776/) (2016)
- [A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM](https://mlsanity.com/paper/2005.06616/) (2020)
- [Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks](https://mlsanity.com/paper/1702.05398/) (2017)
- [Neural Generative Rhetorical Structure Parsing](https://mlsanity.com/paper/1909.11049/) (2019)
- [From News to Medical: Cross-domain Discourse Segmentation](https://mlsanity.com/paper/1904.06682/) (2019)

## Built on by (most cited first, 8 of 8)

- [A Survey of Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2203.02982/) (2022)
- [LLMs in Education: Novel Perspectives, Challenges, and Opportunities](https://mlsanity.com/paper/2409.11917/) (2024)
- [Catalyzing Equity in STEM Teams: Harnessing Generative AI for Inclusion and Diversity](https://mlsanity.com/paper/2402.00037/) (2024)
- [Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems](https://mlsanity.com/paper/2206.04187/) (2022)
- [A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions](https://mlsanity.com/paper/2203.03724/) (2022)
- [Leveraging Large Language Model and Story-Based Gamification in Intelligent Tutoring System to Scaffold Introductory Programming Courses: A Design-Based Research Study](https://mlsanity.com/paper/2302.12834/) (2023)
- [Comparative Study of Learning Outcomes for Online Learning Platforms](https://mlsanity.com/paper/2104.07763/) (2021)
- [Computer Vision for Objects used in Group Work: Challenges and Opportunities](https://mlsanity.com/paper/2507.00224/) (2025)

## Abstract (arXiv)

We explore creating automated, personalized feedback in an intelligent tutoring system (ITS). Our goal is to pinpoint correct and incorrect concepts in student answers in order to achieve better student learning gains. Although automatic methods for providing personalized feedback exist, they do not explicitly inform students about which concepts in their answers are correct or incorrect. Our approach involves decomposing students answers using neural discourse segmentation and classification techniques. This decomposition yields a relational graph over all discourse units covered by the reference solutions and student answers. We use this inferred relational graph structure and a neural classifier to match student answers with reference solutions and generate personalized feedback. Although the process is completely automated and data-driven, the personalized feedback generated is highly contextual, domain-aware and effectively targets each student's misconceptions and knowledge gaps. We test our method in a dialogue-based ITS and demonstrate that our approach results in high-quality feedback and significantly improved student learning gains.