Aspect-Based Sentiment Analysis Pada Data Multi Modal Twitter Untuk Benchmark Performa Produk Studi Kasus Smartphone

Simbolon, Tegar Oktavianto (2025) Aspect-Based Sentiment Analysis Pada Data Multi Modal Twitter Untuk Benchmark Performa Produk Studi Kasus Smartphone. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21082010140-cover.pdf Download (1MB)
	Text (Bab 1) 21082010140-bab1.pdf Download (319kB)
	Text (Bab 2) 21082010140-bab2.pdf Restricted to Repository staff only until 18 June 2027. Download (457kB) \| Request a copy
	Text (Bab 3) 21082010140-bab3.pdf Restricted to Repository staff only until 18 June 2027. Download (5MB) \| Request a copy
	Text (Bab 4) 21082010140-bab4.pdf Restricted to Repository staff only until 18 June 2027. Download (9MB) \| Request a copy
	Text (Bab 5) 21082010140-bab5.pdf Download (175kB)
	Text (Daftar pustaka) 21082010140-daftarpusataka.pdf Download (258kB)
	Text (Lampiran) 21082010140-lampiran.pdf Restricted to Repository staff only Download (1MB) \| Request a copy

Abstract

This study develops a smartphone benchmarking dashboard based on Aspect-Based Sentiment Analysis (ABSA) using multimodal data from tweet texts and images extracted through Optical Character Recognition (OCR). The methods employed include text preprocessing (case folding, tokenization, and stopword removal) and sentiment classification using the Support Vector Machine (SVM) algorithm on product aspects such as camera, performance, and others. The dataset consists of tweet texts and image URLs listed in a CSV file. Images from these URLs are processed with OCR to convert them into text, which is then combined with the tweet text before being predicted by the model to determine sentiment. This OCR feature allows images listed in the CSV to enrich sentiment information within the data. The results show that the SVM model is capable of predicting sentiments that are useful for consumers in comparing products and for manufacturers in improving product quality and marketing strategies. This study demonstrates the potential of utilizing multimodal data to produce more comprehensive sentiment analysis for smartphone products.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahyuni, Eka Dyar	NIDN0717037901	ekawahyuni.si@upnjatim.ac.id
Thesis advisor	Afandi, Mohamad Irwan	NIDN0718077605	3mohamadafandi.si@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Tegar Oktavianto Simbolon

Date Deposited:

19 Jun 2025 03:56

Last Modified:

19 Jun 2025 03:56

URI:

https://repository.upnjatim.ac.id/id/eprint/38496