# A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution

arXiv: https://arxiv.org/abs/1911.01460 · HTML: https://mlsanity.com/paper/1911.01460/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training](https://mlsanity.com/paper/2304.09563/) (2023)
- [Zero-Shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2202.01924/) (2022)
- [Interventional Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2104.11681/) (2021)

## Abstract (arXiv)

Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence. However, we discovered that many existing approaches fail to learn an effective ASC classifier but more like a sentence-level sentiment classifier because they have difficulty to handle sentences with different polarities for different aspects.~This paper first demonstrates this problem using several state-of-the-art ASC models. It then proposes a novel and general adaptive re-weighting (ARW) scheme to adjust the training to dramatically improve ASC for such complex sentences. Experimental results show that the proposed framework is effective footnoteThe dataset and code are available at urlhttps://github.com/howardhsu/ASCfailure..