STM Journals Peer-reviewed research from Consortium e-Learning Network

Recent Trends in Programming languages

Unleashing the Power of Mathematics in Natural Language Processing: Sentiment Analysis Perspectives

  1. Mritunjay Kumar Ranjan
  2. Sanjay Kumar Tiwari
  3. Arif Md. Sattar

Abstract

Sentiment analysis (SA), which utilizes natural language processing (NLP), computational linguistics, text analysis, image processing, and video processing to extract and analyze subjective information from the internet, social media, and other sources, is becoming increasingly popular in both the business world and the scientific community. It is even possible to model it so that it focuses on polarity, sentiments and emotions, urgency, and even goals. It is able to distinguish between positive, negative, and neutral data. Document-level sentiment analysis (DLSA), aspect-based sentiment analysis (ABSA), and data-driven sentiment analysis (DSA) are the three levels that are included in sentiment analysis. It is frequently utilized for the classification of text, the translation of speech, the recognition of faces, objects, patterns, and voices, as well as the identification of spam in electronic communications. In recent years, deep learning strategies have become the method of choice for applications that require computer vision and pattern recognition. The convolutional neural network (CNN) modeling technique is one of the deep learning approaches that is utilized most frequently for image processing. Opinion clustering, opinion idea or entity extraction, opinion summarization, and opinion categorization are just some of the actions and processes that are involved in text mining utilizing deep learning. Text categorization is one of the most critical processes in the text mining process that uses machine learning, while working on a project involving machine learning, it is essential to have a solid understanding of the mathematical model and to predefine the feature extraction model before utilizing the choice classification technique. With the help of NLP, X(formally known as twitter)'s representation, and deep learning-based data mining techniques, this study provides an approach called opinion mining that is based on deep learning to analyze Twitter opinion data. The accuracy and reliability of detection systems can be evaluated with the help of confusion matrices by comparing the aggregated opinions of Twitter users through the application of numerical techniques, as well as by building and labeling separate camps of Twitter opinion. The predicted class instances are shown in the form of a list, whereas the actual class instances are presented in the form of a table with rows and columns. In our study, we design CNN-based opinion classification approach and mathematical opinion mining classification model to find sentiment.

Keywords

Support