Topic Modelling pada Sentimen Terhadap Headline Berita Online Berbahasa Indonesia Menggunakan LDA dan LSTM
DOI:
https://doi.org/10.30865/mib.v5i1.2556Keywords:
Sentiment Analysis, Long Short-Term Memory, Online News Headline, Topic Modelling, Latent Dirichlet AllocationAbstract
The online mass media is the source of the fastest and up-to-date information. A model that can provide mapping will help in sorting out information more precisely. In this study, the authors applied topic modeling to the results of sentiment analysis on online news headlines in Indonesian. Sources of data in this study were obtained from online mass media in Indonesian. The data collected were analyzed for sentiment using the Long Short-term Memory (LSTM) method, in order to obtain news headlines with positive, negative, and neutral sentiments. The classification obtained from the results of the sentiment analysis process is continued with the topic modeling process using the Latent Dirichlet Allocation (LDA) method and visualized in the form of wordcloud and intertopic distance map (pyLDAVis) to determine the relationship between one topic and another. The result of sentiment analysis is a model with 71.13% of accuracy level and the results of topic modeling are in the form of some topics that are easy to interpret.
References
Badan Pengembangan Bahasa dan Perbukuan, “Kamus Besar Bahasa Indonesia,†Kementerian Pendidikan dan Kebudayaan, 2016. https://kbbi.kemdikbud.go.id/.
M. Wandik, A. M.Golung, and H.Mulyono, “Proses Penentuan Headline Surat Kabar (Studi Pada Surat Kabar Harian Manado Post),†E-Journal Acta Diurna, vol. VI, no. 2, 2017.
M. Winiharti, “Analisis Diksi Pada Judul Berita Utama Surat Kabar yang Memberitakan Rapat Pansus DPR RI untuk Kasus Bank Century,†J. Penelit. Hum., vol. 12, no. 1, pp. 19–31, 2011.
C. C. Aggarwal and C. X. Zhai, Mining text data, vol. 9781461432. 2013.
C. Jacobi, W. Van Atteveldt, and K. Welbers, “Quantitative analysis of large amounts of journalistic texts using topic modelling,†Digit. Journal., vol. 4, no. 1, pp. 89–106, 2016, doi: 10.1080/21670811.2015.1093271.
S. Bergamaschi and L. Po, “Comparing LDA and LSA topic models for content-based movie recommendation systems,†Lect. Notes Bus. Inf. Process., vol. 226, pp. 247–263, 2015, doi: 10.1007/978-3-319-27030-2_16.
Y. Lu, Q. Mei, and C. X. Zhai, “Investigating task performance of probabilistic topic models: An empirical study of PLSA and LDA,†Inf. Retr. Boston., vol. 14, no. 2, pp. 178–203, 2011, doi: 10.1007/s10791-010-9141-9.
D. M. Blei, B. B. Edu, A. Y. Ng, A. S. Edu, M. I. Jordan, and J. B. Edu, “Latent Dirichlet Allocation,†CrossRef List. Deleted DOIs, vol. 1, pp. 993–1022, 2003, doi: 10.1162/jmlr.2003.3.4-5.993.
L. Hagen, “Content analysis of e-petitions with topic modeling: How to train and evaluate LDA models?,†Inf. Process. Manag., vol. 54, no. 6, pp. 1292–1307, 2018, doi: 10.1016/j.ipm.2018.05.006.
W. Medhat, A. Hassan, and H. Korashy, “Sentiment analysis algorithms and applications: A survey,†Ain Shams Eng. J., vol. 5, no. 4, pp. 1093–1113, 2014, doi: 10.1016/j.asej.2014.04.011.
K. Ivanedra and M. Mustikasari, “Implementasi Metode Recurrent Neural Network Pada Text Summarization Dengan Teknik Abstraktif the Implementation of Text Summarization With Abstractive Techniques Using Recurrent Neural Network Method,†vol. 6, no. 4, pp. 377–382, 2019, doi: 10.25126/jtiik.201961067.
R. Primartha, Belajar Machine Learning Teori dan Praktik. Bandung: Penerbit INFORMATIKA, 2018.
B. K. Wangsa, D. Utomo, and S. Nugroho, “Sistem Peringkas Berita Otomatis berbasis Text Mining menggunakan Generalized Vector Space Model: Studi Kasus Berita diambil dari Media Massa Online,†Techne J. Ilm. Elektrotek., vol. 13, pp. 231–241, 2014.
M. R. Pratiwi, “Peran ICT bagi Organisasi Media Massa dan Budaya Masyarakat,†Komunikator, vol. 6, no. 5, p. 21, 2014, [Online]. Available: http://journal.umy.ac.id/index.php/jkm/article/view/212/174.
Y. Yuniati, “Pengaruh Berita di Surat Kabar terhadap Persepsi Mahasiswa tentang Politik,†vol. 3, no. 1. pp. 1–17, 2002.
F. de Oliveira Capela and J. E. Ramirez-Marquez, “Detecting urban identity perception via newspaper topic modeling,†Cities, vol. 93, no. May, pp. 72–83, 2019, doi: 10.1016/j.cities.2019.04.009.
X. Li, P. Wu, and W. Wang, “Incorporating stock prices and news sentiments for stock market prediction: A case of Hong Kong,†Inf. Process. Manag., vol. 57, no. 5, p. 102212, 2020, doi: 10.1016/j.ipm.2020.102212.
C. C. Lai, T. P. Shih, W. C. Ko, H. J. Tang, and P. R. Hsueh, “Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease-2019 (COVID-19): The epidemic and the challenges,†Int. J. Antimicrob. Agents, vol. 55, no. 3, p. 105924, 2020, doi: 10.1016/j.ijantimicag.2020.105924.
WHO, “Coronavirus disease 2019,†World Heal. Organ., vol. 2019, no. March, p. 2633, 2020, doi: 10.1001/jama.2020.2633.
N. Reimers and I. Gurevych, “Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks,†2017, [Online]. Available: http://arxiv.org/abs/1707.06799.
A. F. Hidayatullah, A. M. Hakim, S. Cahyaningtyas, and W. P. Aulia, “TOPIC MODELING DATA TWITTER TERHADAP CALON PRESIDEN REPUBLIK INDONESIA 2019 MENGGUNAKAN METODE LATENT DIRICHLET ALLOCATION (LDA).â€
A. F. Hidayatullah, E. C. Pembrani, W. Kurniawan, G. Akbar, and R. Pranata, “Twitter Topic Modeling on Football News,†2018 3rd Int. Conf. Comput. Commun. Syst. ICCCS 2018, pp. 94–98, 2018, doi: 10.1109/CCOMS.2018.8463231.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
