English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Given the success of Graph Neural Networks (GNNs) for structure-aware machinelearning, many studies have explored their use for text classification, butmostly in specific domains with limited data characteristics. Moreover, somestrategies prior to GNNs relied on graph mining and classical machine learning,making it difficult to assess their effectiveness in modern settings. This workextensively investigates graph representation methods for text classification,identifying practical implications and open challenges. We compare differentgraph construction schemes using a variety of GNN architectures and setupsacross five datasets, encompassing short and long documents as well asunbalanced scenarios in diverse domains. Two Transformer-based large languagemodels are also included to complement the study. The results show that i)although the effectiveness of graphs depends on the textual input features anddomain, simple graph constructions perform better the longer the documents are,ii) graph representations are especially beneficial for longer documents,outperforming Transformer-based models, iii) graph methods are particularlyefficient at solving the task.

Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?