Sentiment analysis using machine learning: Progress in the machine intelligence for data science

Sentiments and emotions of a person on social media is classified by the effective data science approaches. Data science is an inter-disciplinary domain that utilizes the scientific techniques, processes and algorithms to retrieve the sentiments from the twitter tweets. The classification of sentime...

Full description

Saved in:

Bibliographic Details
Published in:	Sustainable energy technologies and assessments Vol. 53; p. 102557
Main Authors:	Revathy, G., Alghamdi, Saleh A., Alahmari, Sultan M., Yonbawi, Saud R., Kumar, Anil, Anul Haq, Mohd
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01-10-2022
Subjects:	Classification Data science Machine learning Neural network and NLP Sentiment analysis Data science Sentiment analysis Neural network and NLP Machine learning Classification
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Sentiments and emotions of a person on social media is classified by the effective data science approaches. Data science is an inter-disciplinary domain that utilizes the scientific techniques, processes and algorithms to retrieve the sentiments from the twitter tweets. The classification of sentiments plays significant role in many application domain and with the assistance of the people emotions business industry can be developed accordingly. The sentiment extraction and the classification is attained by several approaches namely neuro-fuzzy and optimization algorithms. The technical contribution of this article is double feed forward neural network. These approaches face ineffective in classification when the real-time data contains numerous characters and stream of information. To attain proficient classification, double feed forward neural network is utilized and the output layer information is transmitted to the double layer of the network. Hence, the information’s are optimized and processed effectively, whereby the classification of sentiment is achieved. The entire process of the algorithm is carried and the acquired results are compared with the neuro-fuzzy and optimization algorithm. The DFFNN outperforms the existing algorithm in terms of classification parameters.
ISSN:	2213-1388
DOI:	10.1016/j.seta.2022.102557