{"title":"Sentimental Analysis on Social Media Dataset Using Different Algorithms in Machine Learning","authors":"Lavanya Y N, R. N, Sumanth K, Asha Rani K P, G. S","doi":"10.1109/ICAISS55157.2022.10011134","DOIUrl":null,"url":null,"abstract":"The total amount of data created for social networks is growing significantly every day. On social media, both public and private opinions on various topics or concerns are shared Various people use different media to keep themselves updated, especially in social media network sites, for example Facebook, Twitter, Instagram etc. An information shared on social media directly affects people's life. People occasionally responded well to it, while other times it had a negative effect on daily life. Sentiment analysis is a technique for examining the sentiment that is embedded in a remark. By using sentiment analysis, a powerful marketing tactic, and their advertising efforts, product managers can better grasp the opinions of their customers. It has a big impact on customer loyalty, satisfaction, marketing, advertising efficacy, and product adoption. The sentiment of your brand on social media is shown through this investigation. The sentiment scores are categorized as positive (+ve) and negative (-ve) by considering the Recurrent Neural Network (RNN), Support Vector Machine (SVM), Random Forest (RF), Naive Bayes, Convolution Neural Network (CNN), and Logistic Regression. In this work, Sentimental analysis is used to analyze a variety of data available on social media site including Twitter, Facebook, Instagram. Evaluation of performance was measured with accuracy. From the obtained results, it is observed that the Support Vector Machine outperforms all the other algorithms with an accuracy of 85.9% considered for the Twitter dataset, 94.4% for the Facebook dataset, and 84% for the Instagram dataset better than other algorithms.","PeriodicalId":243784,"journal":{"name":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","volume":"8 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAISS55157.2022.10011134","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The total amount of data created for social networks is growing significantly every day. On social media, both public and private opinions on various topics or concerns are shared Various people use different media to keep themselves updated, especially in social media network sites, for example Facebook, Twitter, Instagram etc. An information shared on social media directly affects people's life. People occasionally responded well to it, while other times it had a negative effect on daily life. Sentiment analysis is a technique for examining the sentiment that is embedded in a remark. By using sentiment analysis, a powerful marketing tactic, and their advertising efforts, product managers can better grasp the opinions of their customers. It has a big impact on customer loyalty, satisfaction, marketing, advertising efficacy, and product adoption. The sentiment of your brand on social media is shown through this investigation. The sentiment scores are categorized as positive (+ve) and negative (-ve) by considering the Recurrent Neural Network (RNN), Support Vector Machine (SVM), Random Forest (RF), Naive Bayes, Convolution Neural Network (CNN), and Logistic Regression. In this work, Sentimental analysis is used to analyze a variety of data available on social media site including Twitter, Facebook, Instagram. Evaluation of performance was measured with accuracy. From the obtained results, it is observed that the Support Vector Machine outperforms all the other algorithms with an accuracy of 85.9% considered for the Twitter dataset, 94.4% for the Facebook dataset, and 84% for the Instagram dataset better than other algorithms.