Deep learning approach-based hybrid fine-tuned Smith algorithm with Adam optimiser for multilingual opinion mining

Abstract

A deep learning-based Hybrid Fine Tuned Smith Algorithm with Adam optimiser (HFS-AO) is introduced for multilingual opinion mining. Initially, data are collected using the web scraping algorithm to collect three different languages data: Marathi, Hindi and English. After the data extraction, the annotation process is suggested to label the collected data using the Zero-shot instance-weighting technique. Further, pre-process the data to remove unnecessary noises and symbols. After that, text vectorisation is performed using Naïve-Bayes vectorisation with Laplace smoothing. Finally, the Fine Tuned Smith algorithm with an Adam optimiser is proposed for polarity classification. From the three languages, the article regulates that it was possible to determine whether an opinion is negative, positive or neutral. The Python Jupiter software is utilised for this research to evaluate the proposed method's performance. The findings illustrate that when compared to other languages English language accuracy is higher which is about 98.8%.