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

Preview	Text Pendahuluan.pdf Download (1MB) | Preview
Preview	Text BAB I.pdf Download (407kB) | Preview
Preview	Text BAB II.pdf Download (561kB) | Preview
Preview	Text BAB III.pdf Download (1MB) | Preview
	Text BAB IV.pdf Restricted to Registered users only Download (1MB)
	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 (Undergraduate (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