Permatasari, Rosy Indah (2018) Analisis sentimen film pada Twitter berbahasa Indonesia menggunakan Ensemble Features dan Naïve Bayes. Sarjana thesis, Universitas Brawijaya.
Abstract
Analisis sentimen atau opinion mining merupakan salah satu topik penelitian terkini di bidang pengolahan informasi yang bertujuan untuk mengetahui apakah polaritas sebuah data yang berbentuk teks (dokumen, kalimat, paragraf) akan mengarah pada bersifat positif, negatif, ataupun netral. Dokumen teks yang digunakan dalam penelitian berasal dari Twitter tentang opini film berbahasa Indonesia. Twitter memiliki banyak fitur yang mana salah satunya dapat dimanfaatkan sebagai sarana untuk mengetahui opini film dari seluruh pengguna secara umum tidak terbatas oleh pecinta film saja. Dalam hal ini analisis sentimen mempunyai peranan penting untuk menunjang sarana tersebut. Metode yang digunakan adalah Naïve Bayes dengan menggunakan Ensemble Features sebagai pembaharuan fitur selain Bag of Words Features. Jenis-jenis Ensemble Features antara lain Twitter specific features, textual features, part of speech features, dan lexicon based features. Data yang digunakan pada penelitian ini sebanyak 500 data yang dibagi menjadi dua jenis data dengan perbandingan 70% untuk data latih dan 30% untuk data uji. Hasil akurasi sistem diperoleh dari analisis sentimen dengan metode Naïve Bayes dan Ensemble Features tanpa bag of words features sebesar 61,33%, precision sebesar 0,6308, recall sebesar 0,5467 dan f-measure sebesar 0,5857. Sedangkan hasil akurasi sistem menggunakan Ensemble Features dan Bag of Words Features sebesar 88,67 %, precision sebesar 0,9143, recall sebesar 0,8583, dan f-measure sebesar 0,8828.
English Abstract
Sentiment analysis or opinion mining is one of the latest research topics in the field of information processing. It aims to know whether the polarity of a text-shaped data (document, sentence, paragraph) will lead to positive, negative, or neutral trait. This research used document text about Indonesian movie review which was obtained from Twitter. Twitter has many features in which one of it can be used as a media to know public opinion about movie, not only limited to movie lovers. In this case, sentiment analysis has an important role to support the media. The method used in this research was Naïve Bayes using Ensemble Features as a renewal feature beside Bag of Words Features. There are several types of Ensemble Features which are Twitter specific features, textual features, part of speech features, and lexicon based features. 500 data were used in this research, which were later divided into two types of data with the comparison of 70% for training data and 30% for testing data. The result of system accuracy obtained from sentiment analysis with Naïve Bayes and Ensemble Features without bag of words features is 61.33%, 0.6308 precision, 0.5467 recall, and 0.5857 f-measure. The result of system accuracy using Ensemble Features and Bag of Words Features is 88.67%, 0.9143 precision, 0.8533 recall, and 0.8828 fmeasure.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTIK/2018/441/051808046 |
| Uncontrolled Keywords: | Analisis Sentimen, Twitter, Naïve Bayes, Ensemble Features, Opini Film Sentiment Analysis, Twitter, Naïve Bayes, Ensemble Features, Movie Review |
| Subjects: | 000 Computer science, information and general works > 006 Special computer methods > 006.7 Multimedia systems > 006.75 Specific types of multimedia systems > 006.754 Online social networks |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 03 May 2019 01:52 |
| Last Modified: | 18 Oct 2021 06:54 |
| URI: | http://repository.ub.ac.id/id/eprint/162001 |
Preview |
Text
Rosy Indah Permatasari.pdf Download (5MB) | Preview |
Actions (login required)
 |
View Item |