NEURAL NETWORK FOR TWITTER SENTIMENT ANALYSIS

SOFYAN, ARDIYANSYAH ARDHANA (2023) NEURAL NETWORK FOR TWITTER SENTIMENT ANALYSIS. Other thesis, Universitas Katholik Soegijapranata Semarang.

[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-COVER_a.pdf
Download (479kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB I_a.pdf
Download (180kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB II_a.pdf
Restricted to Registered users only
Download (192kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB III_a.pdf
Download (283kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB IV_a.pdf
Download (824kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB V_a.pdf
Download (346kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-BAB VI_a.pdf
Download (176kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-DAPUS_a.pdf
Download (177kB)
[img] Text
19.K1.0045-ARDIYANSYAH ARDHANA SOFYAN-LAMP_a.pdf
Download (703kB)

Abstract

Neural networks also known as Artificial neural networks are a subset of machine learning and the heart of deep learning algorithms. Their name and structure are inspired by the human brain, mimicking the way that biological neurons signal to one another. In this case, I tried to prove which neural networks models are better for textual sentiment analysis. Firstly, the step that needs to be considered is to mine the dataset that was needed or we can use the dataset that is ready to use, In, this research, the dataset was taken from twitter by myself using the snscrape python library. To implement the dataset into the models, the data needs to be processed and word embedding needs to be added so that the accuracy can produce the maximum results. The result of this project is to prove which neural network models are better between a Convolutional Neural Networks and Long Short Term Memory neural networks for textual sentiment analysis

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: mr AM. Pudja Adjie Sudoso
Date Deposited: 10 Apr 2023 01:06
Last Modified: 10 Apr 2023 01:06
URI: http://repository.unika.ac.id/id/eprint/31412

Actions (login required)

View Item View Item
Unika Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.