SHO-CNN: A Metaheuristic Optimization of a Convolutional Neural Network for Multi-Label News Classification

Abstract

News media always pursue informing the public at large. It is impossible to overestimate the significance of understanding the semantics of news coverage. Traditionally, a news text is assigned to a single category; however, a piece of news may contain information from more than one domain. A multi-label text classification model for news is proposed in this paper. The proposed model is an automated expert system designed to optimize CNN’s classification of multi-label news items. The performance of a CNN is highly dependent on its hyperparameters, and manually tweaking their values is a cumbersome and inefficient task. A high-level metaheuristic optimization algorithm, spotted hyena optimizer (SHO), has higher advanced exploration and exploitation capabilities. SHO generates a collection of solutions as a group of hyperparameters to be optimized, and the process is repeated until the desired optimal solution is achieved. SHO is integrated to automate the tuning of the hyperparameters of a CNN, including learning rate, momentum, number of epochs, batch size, dropout, number of nodes, and activation function. Four publicly available news datasets are used to evaluate the proposed model. The tuned hyperparameters and higher convergence rate of the proposed model result in higher performance for multi-label news classification compared to a baseline CNN and other optimizations of CNNs. The resulting accuracies are 93.6%, 90.8%, 68.7%, and 95.4% for RCV1-v2, Reuters-21578, Slashdot, and NELA-GT-2019, respectively.

Automated Identification of Sensitive Financial Data Based on the Topic Analysis

“…The word frequency is calculated by Equations ( 3)-( 5) to obtain the corpus dictionary D and corpus word frequency table F of the word segmentation corpus. The word frequency in the text conforms to a long-tail pattern [12], where a small number of words occur frequently when the majority of words have low frequencies. The word vectors of these low-frequency words are difficult to train, which affects their quality and accuracy.…”

Text Document Clustering Using Chaotic Northern Goshawk Optimization with K-means Algorithm

“…𝑋 𝑖 = {𝑥 𝑖 𝑛𝑒𝑤,𝑝2 , 𝐹 𝑖 𝑛𝑒𝑤,𝑝2 < 𝐹 𝑖 𝑋 𝑖 , 𝐹 𝑖 𝑛𝑒𝑤,𝑝2 ≥ 𝐹 𝑖 (7) Where, 𝑡iteration counter; 𝑇maximum number of iterations; 𝑥 𝑖 𝑛𝑒𝑤,𝑝2new status for 𝑖 th solution; 𝑥 𝑖,𝑗 𝑛𝑒𝑤,𝑝2 -𝑗 th dimension; 𝐹 𝑖 𝑛𝑒𝑤,𝑝2objective function value using NGO phase. The chaotic series is performed in location as well as identification phase, as well as enhancing the exploration capability of NGO.…”

“…Recently, subject replicas have been significantly used in different applications such as document clustering, recapitulation, retrieval as well as classification for numerous linguistics [5,6]. Natural Language Processing (NLP) is absolutely a substitute in some cases and requires unique computational difficulties as well as still not completely proven [7].…”

Computational Integral Imaging Reconstruction Based on Generative Adversarial Network Super-Resolution

“…In recent years, deep learning has become a popular technique in computer vision and has made significant progress in various areas such as speech and image recognition and classification [31], novel view synthesis [32], and image super-resolution (SR) [33]. Image SR is a technique used to restore high-resolution images with more details from low-resolution images.…”