LONG SHORT-TERM MEMORY APPROACH IN SENTIMENT ANALYSIS USING YELP DATASET

FAUZAN, ABI (2021) LONG SHORT-TERM MEMORY APPROACH IN SENTIMENT ANALYSIS USING YELP DATASET. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 Cover.pdf Download (1MB) | Preview
	Text (BAB I) 02 Bab 1.pdf Restricted to Registered users only Download (176kB)
	Text (BAB II) 03 Bab 2.pdf Restricted to Registered users only Download (290kB)
	Text (BAB III) 04 Bab 3.pdf Restricted to Registered users only Download (194kB)
	Text (BAB IV) 05 Bab 4.pdf Restricted to Registered users only Download (332kB)
	Text (BAB V) 06 Bab 5.pdf Restricted to Registered users only Download (486kB)
	Text (BAB VI) 07 Bab 6.pdf Restricted to Registered users only Download (297kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (242kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (489kB)

Abstract

Deep learning algorithms have been used to achieve great results in Natural Language Processing (NLP) applications. Sentiment Analysis is a part of NLP application that extracts emotional information from the texts. This research aims to generate deep learning models which can predict a particular restaurant review using a Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) Neural Network. The dataset used in this research is a restaurant review taken from Yelp website. The dataset is trained using Word2vec word embedding to generate word vector representation which will be used as deep learning input. In the experiment process, the MLP model will be compared with the LSTM model to get the best accuracy. Based on the experiment results shows that the LSTM model is outperformed the MLP model with 91% accuracy compared to the result of MLP model with 76% accuracy. Keywords: LSTM, MLP, NLP, sentiment analysis, Algoritma deep learning telah digunakan untuk mencapai hasil yang luar biasa dalam aplikasi Natural Language Processing (NLP). Analisa Sentimen adalah salah satu bagian daru aplikasi NLP yang mengekstraksi informasi emosional dari sebuah teks. Penelitian ini bertujuan untuk menghasilkan model deep learning yang dapat memprediksi data review restaurant menggunakan Multi-Layer Perceptron (MLP) dan Long Short-Term Memory (LSTM). Dataset dilatih menggunakan Word2vec untuk menghasilkan representasi kata berupa vektor yang akan digunakan sebagai input pada model deep learning. Dalam proses eksperimen, model MLP akan dibandingkan dengan model LSTM untuk mendapatkan akurasi terbaik. Berdasarkan hasil percobaan menunjukkan bahwa model LSTM mengungguli model MLP dengan nilai akurasi 91% dibandingkan dengan hasil model MLP dengan nilai akurasi 76%. Kata kunci: LSTM, MLP, NLP, sentiment analysis, wo

Actions (login required)

View Item