Analisis Sentimen Identifikasi Opini Terhadap Produk, Layanan dan Kebijakan Perusahaan Menggunakan Algoritma TF-IDF dan SentiStrength

Abdul Aziz(1*), F Fauziah(2),

(1) Universitas Nasional
(2) Universitas Nasional
(*) Corresponding Author

Abstract


The need to analyze a product or policy becomes an important thing to measure the level of success. Twitter is currently one of the popular applications used by the public to give their impressions and opinions, both positive, negative and neutral opinions. Diverse public opinion on Twitter can be used as a reference material to get the level of community satisfaction on a product, service or policy. In this study, a sentiment analysis system was created using the TF-IDF and SentiStrength Algorithm. The steps in the research are, firstly, crawling Twitter data using the Twitter API, second preprocessing, thirdly doing spell correction, fourth Word weighting (TF-IDF) and lastly SentiStrength classification, where the results of the classification of tweets have positive, negative or neutral sentiments. In the test data taken using the keyword "child vaccines" as many as 1000 tweets, the results obtained were 54% positive sentiment, 20% negative sentiment and 26% neutral sentiment. Comparison with the same negative data analysis using a different algorithm, namely Naïve Bayes, results in positive sentiment of 55%, 16% and neutral 29%. Decision Tree got 61% positive results, 14% negative and 25% neutral.

Full Text:

PDF

References


Aziz Abdul, Fauziah, & Iskandar Fitri, “Analisis Sentimen Terhadap Kebijakan Pemerintah Tentang Larangan Mudik Hari Raya

Idulfitri di Indonesia Tahun 2021 Menggunakan Metode Naïve Bayes,” Jurnal Sains Komputer & Informatika (J-SAKTI), vol. 5, no. 2, pp. 842-851, September 2021.

Buntoro, G.A, “Sentiment Analysis Twitter dengan Kombinasi Lexicon Based and Double Propagation” Yogyakarta: Jurusan Teknik Elektro, Fakultas Teknik, Universitas Gajah Mada. 2014.

Sianipar Raisa, Erwin Budi S., “Pendeteksian Kekuatan Sentimen Pada Teks Tweet Berbahasa Indonesia Menggunakan SentiStrength,” e-Proceeding of Engineering: Vol.2, No.3 Desember 2015.

Sharifi, B.P., Hutton M.A & Kalita J.K., “Experiments in Microblog Summarization,” 2010 IEEE Second International Conference on Social Computing, 49-56, 2010.

Haryalesmana Devid W, Azhari SN, “Peringkasan Sentimen Ekstraksi di Twitter Menggunakan Hybrid TF-IDF dan Cosine Similarity,” IJCSS, Vol.10, No.2, pp. 207-218, Juli 2016.

Affandy, Oktania Nandiayati, “Sentimen Analysis Berbasis Algoritma Naïve Bayes Classifier Untuk Identifikasi Persepsi Masyarakat Terhadap Produk/Layanan Perusahaan,” Jurnal Of Information System, Vol.5, No.1, pp.126-135, Mei 2020.

Sarsam, S. M., Al-Samarraie, H., Alzahrani, A. I., Alnumay, W., & Smith, A. P., “A lexicon-based approach to detecting suicide-related messages on Twitter.” Biomedical Signal Processing and Control, 65, 102355, 2021.

Saif Hassan, He Yulan, Fernandez Miriam & Alani Harith, “Contextual semantics for sentiment analysis of Twitter,” Information Processing & Management, Januari 2015.

Nurjannah Musfiroh, Hamdani Hamdani dan Indah Fitri A, “Penerapan Algoritma Term Frequency-Inverse Document Frequency (Tf-Idf) Untuk Text Mining,” e-journals, Jurnal Ilmiah Ilmu Komputer, Vol 8, No 3 (2013).

Herwijayanti Bening, Dian Eka Ratnawati & Lailil Muflikhah, “Klasifikasi Berita Online dengan menggunakan Pembobotan TF-IDF dan Cosine Similarity,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, Vol. 2, No. 1, hlm. 306-312, Januari 2018.

Pertiwi Astri, “Analisis Sentimen Dampak Covid-19 Terhadap Perekonomian Indonesia Melalui Media Sosial Menggunakan Metode ANN. Jurnal Mantik”, Vol 4 No. 1, 608-611, 2020




DOI: http://dx.doi.org/10.30645/j-sakti.v6i1.430

Refbacks

  • There are currently no refbacks.


J-SAKTI (Jurnal Sains Komputer & Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan :

View My Stats