# It is Simple Sometimes: A Study On Improving Aspect-Based Sentiment Analysis Performance

arXiv: https://arxiv.org/abs/2405.20703 · HTML: https://mlsanity.com/paper/2405.20703/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 31 May 2024.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Aspect Based Sentiment Analysis with Gated Convolutional Networks](https://mlsanity.com/paper/1805.07043/) (2018)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning](https://mlsanity.com/paper/2305.11383/) (2023)
- [SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods](https://mlsanity.com/paper/1610.03771/) (2016)
- [Instruction Tuned Models are Quick Learners](https://mlsanity.com/paper/2306.05539/) (2023)
- [Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction](https://mlsanity.com/paper/2001.01989/) (2020)
- [Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2210.06629/) (2022)
- [Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning](https://mlsanity.com/paper/2010.13378/) (2020)
- [CERM: Context-aware Literature-based Discovery via Sentiment Analysis](https://mlsanity.com/paper/2402.01724/) (2024)

## Built on by (most cited first, 4 of 4)

- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data](https://mlsanity.com/paper/2503.08042/) (2025)
- [Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis](https://mlsanity.com/paper/2605.20998/) (2026)
- [CrisisKD: Five-Stage Knowledge Distillation for Aspect-Level Sentiment and Emotion Analysis in Crisis Discourse](https://mlsanity.com/paper/2609.05757/) (2026)

## Abstract (arXiv)

Aspect-Based Sentiment Analysis (ABSA) involves extracting opinions from textual data about specific entities and their corresponding aspects through various complementary subtasks. Several prior research has focused on developing ad hoc designs of varying complexities for these subtasks. In this paper, we present a generative framework extensible to any ABSA subtask. We build upon the instruction tuned model proposed by Scaria et al. (2023), who present an instruction-based model with task descriptions followed by in-context examples on ABSA subtasks. We propose PFInstruct, an extension to this instruction learning paradigm by appending an NLP-related task prefix to the task description. This simple approach leads to improved performance across all tested SemEval subtasks, surpassing previous state-of-the-art (SOTA) on the ATE subtask (Rest14) by +3.28 F1-score, and on the AOOE subtask by an average of +5.43 F1-score across SemEval datasets. Furthermore, we explore the impact of the prefix-enhanced prompt quality on the ABSA subtasks and find that even a noisy prefix enhances model performance compared to the baseline. Our method also achieves competitive results on a biomedical domain dataset (ERSA).