Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification
This addresses text classification in graph-structured data, which is an incremental advance for applications like social network analysis or document categorization.
The paper tackled the problem of classifying text data in graphs by proposing a graph-to-tree conversion mechanism and a deep-tree recursive neural network, achieving improved performance over state-of-the-art methods on three real-world datasets.
A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs. The DTG method can generate a richer and more accurate representation for nodes (or vertices) in graphs. It adds flexibility in exploring the vertex neighborhood information to better reflect the second order proximity and homophily equivalence in a graph. Then, a Deep-Tree Recursive Neural Network (DTRNN) method is presented and used to classify vertices that contains text data in graphs. To demonstrate the effectiveness of the DTRNN method, we apply it to three real-world graph datasets and show that the DTRNN method outperforms several state-of-the-art benchmarking methods.