RISKIYAH, AMELIYAH (2025) Analisis Sentimen Kepuasan Pelayanan Transportasi Online Pada Twitter Menggunakan Ekstraksi Fitur Word2Vec Text Embedding dan Algoritma Extreme Learning Machine. Undergraduate thesis, UPN Veteran Jawa Timur.
This is the latest version of this item.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (cover)
20083010022-cover.pdf Download (530kB) |
|
Text (Bab 1)
20083010022-bab1.pdf Download (136kB) |
|
Text (Bab 2)
20083010022-bab2.pdf Restricted to Repository staff only until 5 February 2027. Download (257kB) |
|
Text (Bab 3)
20083010022-bab3.pdf Restricted to Repository staff only until 5 February 2027. Download (222kB) |
|
Text (Bab 4)
20083010022-bab4.pdf Restricted to Repository staff only until 5 February 2027. Download (467kB) |
|
Text (Bab 5)
20083010022-bab5.pdf Download (13kB) |
|
Text (Daftar pustaka)
20083010022-daftarpustaka.pdf Download (131kB) |
|
Text (lampiran)
20083010022-lampiran.pdf Restricted to Repository staff only Download (547kB) |
Abstract
There are more and more technological developments in Indonesia, one of which is online transportation. Although there are many developments in online transportation, there are often problems that affect service quality, for example in driver behavior, user behavior, and vehicle conditions. Therefore, this research was conducted with the aim of analyzing public opinion or sentiment about the services provided by online transportation. This research uses Extreme Learning Machine algorithm with Word2Vec feature extraction. Extreme Learning Machine is a machine learning algorithm that has only one hidden layer. The use of this method provides the advantage of speed in the learning process compared to traditional gradient-based methods. Evaluation of the model used is using Confusion Matrix. The online transportation that has the most positive sentiment is GRAB with 844 tweets, followed by GOJEK with 799 tweets and MAXIM with 724 tweets. The most negative sentiment is MAXIM with 724 tweets, GOJEK with 701 tweets, and GRAB with 656 tweets. The best ELM model is the accuracy of the GOJEK ELM model with an accuracy of 0.8533, MAXIM has the same accuracy as GOJEK but the GOJEK ELM model is the best overall because it has the highest F1-Score value of 0.8544 and Recall 0.8529. MAXIM model, F1-Score 0.8523 and recall 0.8514. While the last is GRAB has accuracy 0.84, F1 Score 0.8385 and recall 0.8378.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer Programming | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Ameliyah Amel Riskiyah | ||||||||||||
| Date Deposited: | 05 Feb 2025 07:59 | ||||||||||||
| Last Modified: | 05 Feb 2025 07:59 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/34631 |
Available Versions of this Item
-
Analisis Sentimen Kepuasan Pelayanan Transportasi Online Pada Twitter Menggunakan Ekstraksi Fitur Word2Vec Text Embedding dan Algoritma Extreme Learning Machine. (deposited UNSPECIFIED)
- Analisis Sentimen Kepuasan Pelayanan Transportasi Online Pada Twitter Menggunakan Ekstraksi Fitur Word2Vec Text Embedding dan Algoritma Extreme Learning Machine. (deposited 05 Feb 2025 07:59) [Currently Displayed]
Actions (login required)
 |
View Item |