IMPLEMENTASI JARINGAN SARAF KONVOLUSI TERHADAP ANALISIS SENTIMEN TENTANG KULIAH ONLINE PADA MASA COVID-19

dc.contributor.authorPratama, Putra Agung
dc.contributor.supervisorAdnan, Arisman
dc.date.accessioned2022-08-02T04:43:23Z
dc.date.available2022-08-02T04:43:23Z
dc.date.issued2022-03
dc.description.abstractThis paper discusses online course that use the internet network to stay connected during the activity. This study aims to see the impact of online course based on someone's opinion. One of the appropriate methods for this research is sentiment analysis. For this reason, there are 7000 tweets is analyzed from media social twitter April 2020–April 2021 which convey opinions about online course. Sentiment analysis uses a convolution neural network (one directional convolution) which classifies data in the form of text documents. Convolutional neural network is trained using keras programming with 100 epoch. The convolutional neural network trains using 5600 tweets and predicts 1400 different tweets. The training results from the convolution neural network give a neutral sentiment as the most dominant sentiment with amount 76.5% accuracy level.en_US
dc.description.sponsorshipFakultas Matematika dan Ilmu Pengetahuan Alam Universitas Riauen_US
dc.identifier.citationPerpustakaanen_US
dc.identifier.issnElfitra
dc.identifier.urihttps://repository.unri.ac.id/handle/123456789/10630
dc.language.isoenen_US
dc.publisherElfitraen_US
dc.subjectOnline courseen_US
dc.subjectOnline courseen_US
dc.subjectsentiment analysisen_US
dc.subjectconvolutional neural networken_US
dc.subjecttwitteren_US
dc.titleIMPLEMENTASI JARINGAN SARAF KONVOLUSI TERHADAP ANALISIS SENTIMEN TENTANG KULIAH ONLINE PADA MASA COVID-19en_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Putra Agung Pratama_compressed.pdf
Size:
251.87 KB
Format:
Unknown data format
Description:
artikel
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections