Skip to content

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

Sep 2026 · 0 citations · 27 references
Computer Science

TL;DR

CrisisKD, a five-stage teacher--student knowledge distillation framework for aspect-level sentiment and emotion analysis on unannotated social media data, is proposed and a dataset containing 50,615 aspect-level labels is constructed and released.

Abstract

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.

View source

Similar papers

Sep 2026

Large Language Model-Driven Hard Negatives Generation for Contrastive Aspect-Based Sentiment Analysis

This paper introduces the sentiment-aware chain-of-thought (SACoT) framework, which emulates a human-like reasoning process to manipulate the sentiment polarity of aspect terms and proposes a novel approach that leverages LLMs to generate “hard negatives” for ABSA.

Ling-Ling Xu, Hao-Ran Xie, S. Qin et al. · 0 citations
Review Open access Sep 2026

Bridging Aspect-Level and Document-Level Sentiment Analysis in Online Education Through Constrained Multi-Granularity Generative Modeling

Automated sentiment analysis of online-education reviews is useful for understanding learner feedback. Classification-based methods usually capture only document-level polarity. They may miss aspect-level signals and may collapse to the majority class under the heavy imbalance typical of course reviews. When the task i...

Shen-Yi Guo, Youchen Kao, Lu-Chu Cao · 0 citations
Open access Sep 2026

Aligning Acoustic and Semantic Representations for Speech Aspect-Based Sentiment Analysis

This work introduces a novel speech aspect-based sentiment analysis task, taking raw speech signals as input and adopting a cross-modal mixup approach based on optimal transport to jointly extract sentiment elements from both speech and ASR-generated text and effectively align acoustic and semantic representations.

Yi-Fei Miao, Zhong-Qing Wang, Guo-Dong Zhou · 0 citations
Sep 2026

Deep Learning-based Multi-Class Sentiment Classification from Social Media Comments using LSTM Architecture

This paper presents a lightweight sentiment classification model based on Long Short-Term Memory networks, developed as a foundational text-analysis component for future multimodal emotion recognition systems, and provides a reproducible and computationally efficient baseline suitable for integration into broader multi...

Munmun Kakkar, Hemant Patidar · 0 citations
Open access Sep 2026

A Hybrid Framework for Real-Time Sentiment Analysis and Adaptive Conversational Outcome Prediction in Domain-Specific Dialogue Systems

The lack of non-verbal signals in text-based communication forces dialogue systems to rely entirely on dynamic textual sentiment changes to infer user intent and emotional shifts. However, substantial class imbalance and the static, post-hoc nature of existing text analysis models prevent dialogue systems from recogniz...

Mejdl S. Safran · 0 citations
Open access Sep 2026

An External Knowledge-Guided Generative Model for Few-Shot Aspect Category Sentiment Analysis

A generative ACSA model that incorporates external knowledge is proposed, which retrieves fine-grained aspect-related terms from external knowledge bases and uses them to construct contrastive sentence pairs, generating enhanced aspect-related representations, thereby bridging the gap between the original text and pred...

Yan Xiang, Hao-Quan Luo, Yuan Qin et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.