Artificial Intelligence and Communication Technologies
Superupervised Enumerable Learning for Sentiment Analysis of Social Media Tweets
Authors: Zeenat Bano, Yogadhar Pandey and Bhupendra Verma
Publishing Date: 03-06-2023
ISBN: 978-81-955020-5-9
Abstract
People express their views on goods, services, governments, and events via words and phrases on social media. Sentiment analysis is a technique used in natural language processing to gather positive and negative feedback on a piece of writing on social media. Academics have been forced to research sentiment analysis by exponential growth in business and e-commerce companies. This study examined emotions in two distinct domains: one for electronics product evaluations and another for film reviews. Due to the enormous volume of data gathered for analysis, it is referred to as massive data. This vast data is multidimensional and includes useless information. Furthermore, this data complicates the analysis since it reduces the effectiveness of machine learning categorization algorithms. As a consequence, the data must be cleansed and pertinent features identified. Numerous methods have been used to eliminate noise from data and identify essential components. There are two methods for determining suitable features: feature selection and feature extraction. The research is split into three stages: the first step involves converting unstructured data to structured data and choosing relevant and feature information. Second, machine learning classification algorithms are employed in conjunction with feature selection approaches, and third, machine learning algorithms are used in conjunction with ensemble learning methods
Keywords
Social Media, Sentiment Analysis, Natural Language Processing, Machine Learning, Supervised Classification, Feature Extraction Super.
Cite as
Zeenat Bano, Yogadhar Pandey and Bhupendra Verma, "Superupervised Enumerable Learning for Sentiment Analysis of Social Media Tweets", In: Saroj Hiranwal and Garima Mathur (eds), Artificial Intelligence and Communication Technologies, SCRS, India, 2023, pp. 1083-1091. https://doi.org/10.52458/978-81-955020-5-9-103