Hafiz, Y. A. and , Dimas Aryo Anggoro, S.Kom., M.Sc (2024) Analisis Sentimen Masyarakat Terhadap Isu Kelangkaan Beras Berdasarkan Media Sosial X Dengan Pendekatan Bidirectional Encoder Representation From Transformers (BERT). Skripsi thesis, Universitas Muhammadiyah Surakarta.
![[img]](https://eprints.ums.ac.id/style/images/fileicons/application_pdf.png) |
PDF (Naskah Publikasi)
Naskah Publikasi.pdf Download (701kB) |
|
PDF (Surat Pernyataan Publikasi)
Surat Pernyataan Publikasi.pdf Restricted to Repository staff only Download (433kB) |
Abstract
The issue of rice scarcity in Indonesia is often caused by unpredictable weather, distribution problems, and accessibility issues for farmers to consumers, significantly impacting the social and economic aspects of society as rice is a staple food. Discussions on this issue have surged on social media platforms like X, making sentiment analysis highly relevant for understanding public perception. This research utilizes the deep learning model BERT (Bidirectional Encoder Representations from Transformers) to analyze public sentiment towards the rice scarcity issue. The aim is to gauge public perception regarding this issue. Data was collected from X using the Tweet-Harvest tool with the keyword "rice scarcity" from February 16-24, 2024. The data underwent preprocessing steps including data cleaning, case folding, tokenization, normalization, stop word removal, and stemming. Data labeling was conducted using a sentiment lexicon method to categorize tweets into positive, negative, or neutral sentiments. BERT model implementation utilized IndoBERTweet-base-uncased from IndoLEM, optimized for Indonesian language texts. The model was trained with a 90:10 data split for training and testing. Model evaluation showed an accuracy of 80.20%, precision of 71.71%, recall of 73.09%, and an F1 score of 80.40%. This research aims to provide valuable insights into understanding public perception of the rice scarcity issue on social media platform X. Visualization through word clouds also offers a clear depiction of public sentiment towards this issue.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Analisis Sentimen, BERT, Data X, Kelangkaan Beras |
| Subjects: | T Technology > TZ Technical Information T Technology > TZ Technical Information > TA02 Software. Aplication > Pemograman T Technology > TZ Technical Information > TA02 Software. Aplication > Software Engineering |
| Divisions: | Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika |
| Depositing User: | Y. A. HAFIZ |
| Date Deposited: | 12 Aug 2024 08:55 |
| Last Modified: | 12 Aug 2024 08:55 |
| URI: | http://eprints.ums.ac.id/id/eprint/126530 |
Actions (login required)
 |
View Item |
