ANALISIS SENTIMEN ULASAN PRODUK BERBAHASA INDONESIA MENGGUNAKAN DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK DAN WORD2VEC

DAFA, REVAN MUHAMMAD and Abdiansah, Abdiansah and Rodiah, Desty (2022) ANALISIS SENTIMEN ULASAN PRODUK BERBAHASA INDONESIA MENGGUNAKAN DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK DAN WORD2VEC. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181722081.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021181722081_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (396kB)
	Text RAMA_55201_09021181722081_0001108401_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (313kB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (274kB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (585kB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12kB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (86kB) | Request a copy
	Text RAMA_55201_09021181722081_0001108401_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy

Abstract

The phenomenon of electronic commerce arises as a result of the rapid development of technology and communication media. Product reviews are important information for users of electronic commerce media, but reviews are often written incorrectly. The Deep Learning method is a method that is developing very rapidly at this time. We used the Convolutional Neural Network method with the Word2Vec feature to carry out a sentiment analysis of 5,080,101 reviews. Probability of Similarity will be used as an additional pre-processing process to determine the effect of the corrected word on the model being trained. Based on the test results, the model shows excellent performance with an accuracy of 0.91119, a precision of 0.91123, a recall of 0.91232, and an F1-score of 0.91178. The performance of the model with the normalization stage which has quite good performance compared to the stemming and stopword removal stages. The stages of word improvement using the Probability of Similarity method improve 4 out of 5 data schemes, but with large enough training data this process is considered to be quite time consuming and resource consuming.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Sentimen Analysis, Convolutional Neural Network, Word2Vec
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Revan Muhammad Dafa
Date Deposited:	11 Aug 2023 08:14
Last Modified:	11 Aug 2023 08:14
URI:	http://repository.unsri.ac.id/id/eprint/126981

Actions (login required)

View Item