# CrisisKD: Five-Stage Knowledge Distillation for Aspect-Level Sentiment and Emotion Analysis in Crisis Discourse

arXiv: https://arxiv.org/abs/2609.05757 · HTML: https://mlsanity.com/paper/2609.05757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 11 of 11)

- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Deep Learning for Sentiment Analysis : A Survey](https://mlsanity.com/paper/1801.07883/) (2018)
- [A large-scale COVID-19 Twitter chatter dataset for open scientific research -- an international collaboration](https://mlsanity.com/paper/2004.03688/) (2020)
- [METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets](https://mlsanity.com/paper/2209.13773/) (2022)
- [TBCOV: Two Billion Multilingual COVID-19 Tweets with Sentiment, Entity, Geo, and Gender Labels](https://mlsanity.com/paper/2110.03664/) (2021)
- [TweetsCOV19 -- A Knowledge Base of Semantically Annotated Tweets about the COVID-19 Pandemic](https://mlsanity.com/paper/2006.14492/) (2020)
- [M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2502.11824/) (2025)
- [It is Simple Sometimes: A Study On Improving Aspect-Based Sentiment Analysis Performance](https://mlsanity.com/paper/2405.20703/) (2024)
- [Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs](https://mlsanity.com/paper/2506.09983/) (2025)
- [SenWave: A Fine-Grained Multi-Language Sentiment Analysis Dataset Sourced from COVID-19 Tweets](https://mlsanity.com/paper/2510.08214/) (2025)

## Abstract (arXiv)

Identifying the target of emotional words or phrases in crisis situations, especially health-related ones, is important for understanding public concerns across cultural and linguistic contexts. We propose CrisisKD, a five-stage teacher--student knowledge distillation framework for aspect-level sentiment and emotion analysis on unannotated social media data. A teacher LLM generates aspect-level labels and reasoning traces that supervise a smaller student model across aspect extraction, syntactic parsing, opinion extraction, sentiment classification, and emotion classification. Using this framework, we construct and release a dataset containing 50,615 aspect-level labels, together with the annotation and fine-tuning scripts as open-source resources. The resulting student supports end-to-end ABSA and emotion detection at substantially lower inference cost than the teacher. On a manually annotated 500-tweet gold set, the 5-task Qwen2.5-7B student improves over the untuned model by 7.9 F1 points on aspect extraction, 17.0 points on emotion accuracy, and 6.5 points on sentiment accuracy. On the external ABEA benchmark, CrisisKD improves the same-model Qwen2.5-7B ICL baseline by 2.8 F1 points on ATE and 3.8 F1 points on joint ATE+AEC.