UMM Institutional Repository

SENTIMENT ANALYSIS PADA REVIEW RESTORAN MENGGUNAKAN NAÏVE BAYES DAN STANFORD NER

Fadhil, Mohammad (2018) SENTIMENT ANALYSIS PADA REVIEW RESTORAN MENGGUNAKAN NAÏVE BAYES DAN STANFORD NER. Bachelors Degree (S1) thesis, University of Muhammadiyah Malang.

[img]
Preview
Text
Pendahuluan.pdf

Download (1MB) | Preview
[img]
Preview
Text
BAB I.pdf

Download (407kB) | Preview
[img]
Preview
Text
BAB II.pdf

Download (561kB) | Preview
[img]
Preview
Text
BAB III.pdf

Download (1MB) | Preview
[img] Text
BAB IV.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
BAB V.pdf
Restricted to Registered users only

Download (190kB)

Abstract

Sentiment analysis is a computational study based on public comments or opinions, sentiments and emotions through entities and attributes possessed that are expressed in text form (Liu, 2012). The sentiment analysis will classify the polarity of the text present in the sentence or document whether it is positive or negative. Along with the appearance of subjectivity on words, sentences or documents, a new form of aspect-oriented aspect sentiment analysis is required. Sentiment analysis identifies sentiments on documents in various classes. While the oriented aspect identifies the most relevant part of a document or multiple documents and then creates representative summaries, so aspx-based sentiment is done by classifying the polarity of the sentence into positive and negative groups and then determining which aspect is most important to the final summary, since the number of aspects contained in each review so that the parties to the difficulties in conducting a review of goods or services marketed, therefore from the review of this study (restaurant) will be summarized based on sentiment on the aspects that exist in the review in this research we get 97% accuracy for Testing supplied testnya and 86% for 10 fold cross validation test which classification using naive bayes method, and for testing program get 78% recall value and 80% precision

Item Type: Thesis (Bachelors Degree (S1))
Student ID: 201210370311190
Keywords: Analysis Sentiment, Naïve Bayes, StanFord NER
Subjects: Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions: Faculty of Engineering > Department of Informatics (55201)
Depositing User: Sulistyaningsih Sulistyaningsih
Date Deposited: 15 Nov 2018 03:49
Last Modified: 15 Nov 2018 03:49
URI : http://eprints.umm.ac.id/id/eprint/40062

Actions (login required)

View Item View Item
UMM Official

© 2008 UMM Library. All Rights Reserved.
Jl. Raya Tlogomas No 246 Malang East Java Indonesia - Phone +62341464318 ext. 150, 151 - Fax +62341464101
E-Mail : infopus[at]umm.ac.id - Website : http://lib.umm.ac.id - Online Catalog : http://laser.umm.ac.id - Repository : http://eprints.umm.ac.id

Web Analytics

UMM Institutional Repository is powered by :
EPrints Logo