A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis

By Qingshan Jiang, Lei-tai Chen, Ruifeng Xu, Xiang Ao, Min Yang. Conference on Empirical Methods in Natural Language Processing, 2019

333 citations recorded by the source corpus.

Aspect-based sentiment analysis (ABSA) has attracted increasing attention recently due to its broad applications. In existing ABSA datasets, most sentences contain only one aspect or multiple aspects with the same sentiment polarity, which makes ABSA task degenerate to sentence-level sentiment analysis. In this paper, we present a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities. The release of this dataset would push forward the research in this field. In addition, we propose simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances. Experiments on our new dataset show that the proposed model significantly outperforms the state-of-the-art baseline methods

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/78fe2ea5fc700ca7fe2907772e139b0f10b13557

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Corpus Creation for Sentiment Analysis in Code-Mixed Tamil-English Text (2020, background): “For monolingual analysis, there exist various corpora for English (Hu and Liu, 2004; Wiebe et al., 2005; Jiang et al., 2019), Russian (Rogers et al., 2018), German (Cieliebak et al., 2017), Norwegian (Mæhlum et al., 2019) and Indian languages (Agrawal et al., 2018; Rani et al., 2020).”
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges (2022, background): “Jiang et al. [118] present a Multi-Aspect Multi-Sen-timent (MAMS) dataset where each sentence in MAMS contains at least two aspects with different sentiment polarities, thus making the dataset more challenging.”