Challenges for Open-domain Targeted Sentiment Analysis

TL;DR

This paper introduces a new dataset and annotation schema for open-domain targeted sentiment analysis, utilizing BART for sequence-to-sequence modeling, and highlights existing challenges and room for improvement in the field.

Contribution

The paper presents a novel dataset with document-level annotations and a nested target schema, enhancing the scope and depth of open-domain targeted sentiment analysis research.

Findings

Large room for improvement in open-domain targeted sentiment analysis

Challenges in handling long documents and complex target structures

Domain variances significantly affect model performance

Abstract

Since previous studies on open-domain targeted sentiment analysis are limited in dataset domain variety and sentence level, we propose a novel dataset consisting of 6,013 human-labeled data to extend the data domains in topics of interest and document level. Furthermore, we offer a nested target annotation schema to extract the complete sentiment information in documents, boosting the practicality and effectiveness of open-domain targeted sentiment analysis. Moreover, we leverage the pre-trained model BART in a sequence-to-sequence generation method for the task. Benchmark results show that there exists large room for improvement of open-domain targeted sentiment analysis. Meanwhile, experiments have shown that challenges remain in the effective use of open-domain data, long documents, the complexity of target structure, and domain variances.