Text Classification using Siamese Graph Convolutional Pyramid Attention Network using Binary Light Spectrum Optimizer

Text classification is the process of classifying text into specified categories for effective information organization. The lot of techniques is implemented for Text Classification. But the existing methods have lot of disadvantages such as high error rate and low accuracy. To overcome the before mentioned problem, Text Classification Using Siamese Graph Convolutional Pyramid Attention Network using Binary Light Spectrum Optimizer (TxtCSGC-PAN-BLSO) is proposed for Text Classification with high accuracy. In this input data is taken from AG News dataset.. To reduce noise in the input data, Natural Language (NL) based preprocessing is proposed. Following that, the pre-processed images undergo feature extraction using Modified Term Frequency and Inverse Document Frequency (MTF-IDF). After that classification is done using Text Classification Using Siamese Graph Convolutional Pyramid Attention Network (TxtCSGC-PAN) and optimized using Binary Light Spectrum Optimizer (BLSO) for text classification demonstrating superior efficiency and accuracy.