SUGIANTO, LADY VIONA (2022) Sentiment Analysis on Movie Review Using Random Forest and Logistic Regression Algorithm. Other thesis, Universitas Katholik Soegijapranata Semarang.
![[img]](http://repository.unika.ac.id/style/images/fileicons/text.png) |
Text
18.K1.0023-LADY VIONA SUGIANTO-COVER_a.pdf Download (589kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB I_a.pdf Download (117kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB II_a.pdf Restricted to Registered users only Download (127kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB III_a.pdf Download (118kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB IV_a.pdf Download (658kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB V_a.pdf Download (475kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-BAB VI_a.pdf Download (112kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-DAPUS_a.pdf Download (179kB) |
|
Text
18.K1.0023-LADY VIONA SUGIANTO-LAMP_a.pdf Download (301kB) |
Abstract
In the analysis of the movie classification of a movie, users tend to see whether a movie is good or not from the movie's rating. Most users are not interested in seeing other user reviews before, even though the rating is always tied to the reviews given by users to find out whether the film is good or not. Due to the large number of reviews left by users on a movie website, users have difficulty knowing the classification of positive reviews and negative reviews, and users also do not know the quality of a movie. Therefore, in this project, sentiment analysis was made for a film review. By using 2 algorithms, namely Random Forest Classifier and Logistic Regression to determine the sentiment analysis of each film. Both algorithms determine positive and negative sentiments. The data structure used is a database, which will train data and test data for comparison purposes. The dataset is also converted to CSV for easier analysis. To evaluate the model, a comparison of algorithms based on accuracy was carried out. From implementing the Random Forest algorithm with a data range of 650-2000, the resulting analysis sentiment is 9 positive and 1 negative. While the Logistic Regression algorithm produces 8 positive and 2 negative sentiment analyses. And from the comparison of accuracy, Random Forest is better and more suitable for this research because it has an average accuracy of 72,9261% while the average accuracy of Logistic Regression is 63,516%.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works |
| Divisions: | Faculty of Computer Science > Department of Informatics Engineering |
| Depositing User: | mr AM. Pudja Adjie Sudoso |
| Date Deposited: | 26 Oct 2022 09:25 |
| Last Modified: | 26 Oct 2022 09:25 |
| URI: | http://repository.unika.ac.id/id/eprint/30026 |
Actions (login required)
 |
View Item |
