A novel metaheuristic optimisation approach for text sentiment analysis

Abstract

Automated sentiment analysis is considered an area in natural language processing research that seeks to understand a text author's mood, thoughts, and feelings. New opportunities and challenges have arisen in this field due to the popularity and accessibility of a variety of resources of ideas, such as online review websites, personal blogs, and social media. Feature selection, which can be conducted using metaheuristic algorithms, is one of the steps of sentiment analysis. It is crucial to use high-performing algorithms for feature selection. This paper applies the Horse herd Optimisation Algorithm (HOA) for feature selection in text sentiment analysis. HOA is a metaheuristic algorithm and uses six key behaviours to simulate the social performance of horses of various ages, to solve high-dimensional optimisation problems. In order to improve HOA, this paper adds another behaviour of horses to the basic algorithm; thus, the new algorithm uses seven key behaviours of horses of different ages to imitate their social performance. It is then discretised and converted to a multi-objective algorithm. The improved algorithm's performance is evaluated using 15 CEC benchmark functions, and the results are compared to the Binary Social Spider Algorithm, the Binary Grey Wolf Optimizer, and the Binary Butterfly Optimization Algorithm. The new algorithm, the Multi-objective Binary Horse herd Optimisation Algorithm (MBHOA), excels at solving high-dimensional complex problems. To evaluate the algorithm's performance in feature selection, as a practical example, it is employed in text sentiment analysis and examined on various data sets. The simulation results indicate that MBHOA has a better performance in analysing sentiment compared to similar approaches.

Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training

“…Xiong et al [5] focused on fine-grained sentiment analysis tasks, developing a module based on machine reading comprehension to accomplish this task. Hosseinalipour et al [6] developed the Horse Herd Optimisation Algorithm and applied it in the field of sentiment analysis, achieving very good results. Jiang et al [7] focused on methodology by combining methods such as K-means++ [8], SMOTE [9], CNN [10], and BiLSTM [11] models to perform sentiment analysis on texts.…”

A Comprehensive Review of Bio-Inspired Optimization Algorithms Including Applications in Microelectronics and Nanophotonics

“…), data clustering and mining [ 52 ], civil engineering [ 53 , 54 ], architectural design [ 55 ], urban engineering [ 56 ], smart cities [ 57 ], traffic control and engineering [ 58 ], biomedicine and healthcare [ 59 , 60 ], pharmacy [ 61 , 62 ], bioinformatics [ 63 ], genomics [ 64 ], computational biology [ 60 ], environmental pollution control [ 65 ] and computational chemistry [ 66 ]. Other optimization fields where biomimetic algorithms find application include transportation and logistics [ 67 ], industrial production [ 68 ], manufacturing including production planning, supply chains, resource allocation and management [ 69 ], food production and processing [ 70 ], agriculture [ 71 ], financial markets [ 72 ] including stock market prediction [ 73 ], as well as cryptocurrencies and blockchain technology [ 74 ], and even such seemingly unlikely fields as language processing and sentiment analysis [ 75 ]. The cited applications are just a tip of an iceberg, and there is a vast number of other uses not even mentioned here.…”