


Volume 20 No 20 (2022)
Download PDF
Mean Silhouette Genetic and Elman Deep Recurrent Network based Sentimental Analysis for Twitter Social Media Healthcare Data
Dr.D.Sasikala, Dr.S.Sukumaran
Abstract
Employment of social media is becoming all-pervasive and disease analogous communities
are organizing online, together with communities of attentiveness encompassing health care
domain. Despite Facebook being the most sought out social media platform, utilization of
supplementary social media platform like Twitter is increasing. To be more specific, in recent days
patients with COVID and diabetes commenced to gather and take active participations in online
discussions about diabetes and COVID on Twitter, engross in communication and sharing virtually
and perceive peer support online. In this work a method called, Mean Silhouette-based Genetic and
Elman Deep Sentiment Analysis (MSG-EDSA) is proposed. Elman Deep Recurrent Network Sentiment
Classification is applied to the selected features, to classify the tweets in an accurate and timely
manner. The tweets are finally classified as extremely positive, positive, extremely negative,
negative or neutral from the tweets obtained via different users. The proposed MSG-EDSA is
experimented with using the diabetes and COVID real-time datasets from social media platforms to
analyze healthcare sentimental analysis. The parameters like, precision, recall, accuracy and error
rate are selected to analyze the performance against the state-of-the-art sentimental analysis
methods.
Keywords
Employment of social media is becoming all-pervasive and disease analogous communities are organizing online, together with communities of attentiveness encompassing health care domain. Despite Facebook being the most sought out social media platform, utilization of supplementary social media platform like Twitter is increasing. To be more specific, in recent days patients with COVID and diabetes commenced to gather and take active participations in online discussions about diabetes and COVID on Twitter, engross in communication and sharing virtually and perceive peer support online. In this work a method called, Mean Silhouette-based Genetic and Elman Deep Sentiment Analysis (MSG-EDSA) is proposed. Elman Deep Recurrent Network Sentiment Classification is applied to the selected features, to classify the tweets in an accurate and timely manner. The tweets are finally classified as extremely positive, positive, extremely negative, negative or neutral from the tweets obtained via different users. The
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.