Sentiment Analysis of Covid-19 Tweets Using Machine Learning Algorithm - Brossura

Dip, Ahmed Rasidun Bari; Sadik, Md.Shihab; Rozario, Omi Evance

Brossura

ISBN 10: 6208118107 ISBN 13: 9786208118105

Casa editrice: LAP LAMBERT Academic Publishing, 2024

Riassunto

Main theme: This article demonstrates that, among a large number of prediction models, the Facebook Prophet Model had the highest accuracy when it came to anticipating pandemic circumstances.Result Analysis: They presented how the models performed on the test sets using the regression and time series models, as well as the analysis using Facebook Prophet. They can calculate the Root Mean Square Error (RMSE) for each model using these results. The comparison of the models based on their RMSE scores is shown in Table I. Table I indicates that when forecasting confirmed instances, the FPM has the lowest average error. Second place goes to the ARIMA model, which is followed by the AR and MA models. However, because the ARIMA incorporates both the MA and AR models, they are not taken into account.The HWA model, which comes after these two, has the lowest score, followed by the PR. Table I shows that the findings are almost identical to the table confirmed cases results, with the FPM coming out on top, followed by the ARIMA, HWA, and PR, in that order. As a result, they come to the conclusion that the best models for anticipating the pandemic situation are as follows: Facebook.

Dettagli dell'edizione

• Editore: LAP LAMBERT Academic Publishing
• Data di pubblicazione: 2024
• Lingua: Inglese
• ISBN 10: 6208118107
• ISBN 13: 9786208118105
• Rilegatura: Copertina flessibile
• Numero di pagine: 52
• Contatto del produttore: non disponibile
• Persona responsabile: KreGa Onlinehandel GmbH; 4950000000000; info@krega-onlinehandel.de; ; Birkenweg 31; Brakel; 33034; Germania