| Full text | |
| Author(s): |
dos Santos, Nicolas R.
;
Minatel, Diego
;
Valejo, Alan D. B.
;
Lopes, Alneu A.
Total Authors: 4
|
| Document type: | Journal article |
| Source: | 40TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING; v. N/A, p. 3-pg., 2025-01-01. |
| Abstract | |
Graph Neural Networks (GNNs) have shown remarkable success in text classification through diverse graph types for representing a corpus and strategies to enrich their structure. In this context, bipartite graphs are particularly effective due to their ability to represent dyadic interactions naturally. However, when the focus is on analyzing a single entity type, one-mode projection stands out as a prominent technique. Specifically, it transforms bipartite graphs into unipartite ones consisting of a single node type, linking them based on shared neighbors from the other type. While one-mode projection has been utilized in machine learning, its potential for GNN-based text classification remains unexplored. To address this gap, we propose a novel method called One-mode Projection of Bipartite Graphs for Text Classification (OPTIC). Concretely, OPTIC projects the document partition of a document-word bipartite graph and applies a GNN to the unipartite graph for text classification. Experiments on eight datasets show that OPTIC achieves on-par accuracy on all datasets compared to the baselines. Code and supplementary material are available at https://github.com/nicolasrsantos/optic. (AU) | |
| FAPESP's process: | 22/03090-0 - Analysis of large amounts of political data and complex networks: mining modelling and applications in Computational Political Science |
| Grantee: | Sylvia Iasulaitis |
| Support Opportunities: | Research Grants - Initial Project |
| FAPESP's process: | 20/09835-1 - IARA - Artificial Intelligence in the Remaking of Urban Environments |
| Grantee: | André Carlos Ponce de Leon Ferreira de Carvalho |
| Support Opportunities: | Research Grants - Research Centers in Engineering Program |
| FAPESP's process: | 22/09091-8 - Criminality, insecurity, and legitimacy: a transdisciplinary approach |
| Grantee: | Luis Gustavo Nonato |
| Support Opportunities: | Research Grants - eScience and Data Science Program - Thematic Grants |
| FAPESP's process: | 21/06210-3 - Urban spaces-aware services via federated learning in intelligent transport systems |
| Grantee: | Geraldo Pereira Rocha Filho |
| Support Opportunities: | Regular Research Grants |