Structured Sentiment Analysis as Dependency Graph Parsing
This work addresses the issue of over-subdivision in sentiment analysis for researchers and practitioners, offering a more integrated approach.
The authors tackled the problem of fragmented structured sentiment analysis by proposing a unified framework that treats it as dependency graph parsing, achieving strong improvements over state-of-the-art baselines across five datasets in four languages.
Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e,g,, target extraction or targeted polarity classification. We argue that this division has become counterproductive and propose a new unified framework to remedy the situation. We cast the structured sentiment problem as dependency graph parsing, where the nodes are spans of sentiment holders, targets and expressions, and the arcs are the relations between them. We perform experiments on five datasets in four languages (English, Norwegian, Basque, and Catalan) and show that this approach leads to strong improvements over state-of-the-art baselines. Our analysis shows that refining the sentiment graphs with syntactic dependency information further improves results.