Analisis Topik Modelling Terhadap Penggunaan Sosial Media Twitter oleh Pejabat Negara
Social media is experiencing rapid development until now. Social media makes it easy for humans to be able to connect with one another. One of the social media that is widely used is Twitter. The ease of use makes social media widely used among the public, including state officials. State officials use Twitter to convey policies, opinions and interact with the public. By conducting a topic analysis of tweets shared by state officials, we can find out the relevant topics discussed by state officials. We can find out the focus of attention of state officials through topic modeling. Latent Dirichlet Allocation (LDA) is a topic modeling method that finds certain patterns in documents and produces several different topics. Tweets from the @jokowi account are collected using a scraping technique. The results of the tweet collection are then preprocessed for further analysis using the Latent Dirichlet Allocation (LDA) method. The results of the analysis model are evaluated using perplexity calculations and coherence scores. The evaluation of the model resulted in a perplexity value of -8.069 and a coherence score of 0.375 for a total of 7. This shows that the model used is good for analyzing and finding topics in tweets of state officials.
S. R. I. Rezeki, “Penggunaan Sosial Media Twitter dalam Komunikasi Organisasi (Studi Kasus Pemerintah Provinsi Dki Jakarta Dalam Penanganan Covid-19),” J. Islam. Law Stud., vol. 04, no. 02, pp. 63–78, 2020.
J. C. Campbell, A. Hindle, and E. Stroulia, “Latent Dirichlet Allocation: Extracting Topics from Software Engineering Data,” Art Sci. Anal. Softw. Data, vol. 3, pp. 139–159, 2015, doi: 10.1016/B978-0-12-411519-4.00006-9.
P. Zambrano et al., “Technical mapping of the grooming anatomy using machine learning paradigms: An information security approach,” IEEE Access, vol. 7, pp. 142129–142146, 2019, doi: 10.1109/ACCESS.2019.2942805.
M. L. C. Chilmi, “Latent dirichlet allocation lda untuk mengetahui topik pembicaraan warganet twitter tentang omnibus law,” Repository.Uinjkt.Ac.Id, 2021, [Online]. Available: https://repository.uinjkt.ac.id/dspace/handle/123456789/56724%0Ahttps://repository.uinjkt.ac.id/dspace/bitstream/123456789/56724/1/M. LUVIAN CHISNI CHILMI-FST.pdf.
B. W. Arianto and G. Anuraga, “Topic Modeling for Twitter Users Regarding the ‘Ruanggguru’ Application,” J. ILMU DASAR, vol. 21, no. 2, p. 149, 2020, doi: 10.19184/jid.v21i2.17112.
S. A. Putri, P. D. Kusuma, C. Setianingsih, and U. Telkom, “Clustering Topik Pada Data Sentimen Bpjs Kesehatan Menggunakan Metode Latent Dirichlet Allocation Topic Clustering On Sentiment Data Of Bpjs Kesehatan,” vol. 8, no. 5, pp. 6097–6105, 2021.
Z. Tong and H. Zhang, “A Text Mining Research Based on LDA Topic Modelling,” pp. 201–210, 2016, doi: 10.5121/csit.2016.60616.
Y. Sahria and D. H. Fudholi, “Analisis Topik Penelitian Kesehatan di Indonesia Menggunakan Metode Topic Modeling LDA,” J. Rekayasa Sist. dan Teknol. Inf., vol. 4, no. 2, pp. 336–344, 2020.
D. Newman, J. H. Lau, K. Grieser, and T. Baldwin, “Automatic evaluation of topic coherence,” NAACL HLT 2010 - Hum. Lang. Technol. 2010 Annu. Conf. North Am. Chapter Assoc. Comput. Linguist. Proc. Main Conf., no. June, pp. 100–108, 2010.
T. Gonçalves and P. Quaresma, “Evaluating preprocessing techniques in a text classification problem,” Unisinos, pp. 841–850, 2005, [Online]. Available: http://www.research.att.com/.
F. Rashif, G. Ihza Perwira Nirvana, M. Alif Noor, and N. Aini Rakhmawati, “Implementasi LDA untuk Pengelompokan Topik Cuitan Akun Bot Twitter bertagar #Covid-19 LDA Implementation for Topic of Bot’s Tweets with #Covid-19 Hashtag,” Cogito Smart J. |, vol. 7, no. 1, pp. 170–181, 2021.
S. H. Mohammed and S. Al-Augby, “LSA & LDA topic modeling classification: Comparison study on E-books,” Indones. J. Electr. Eng. Comput. Sci., vol. 19, no. 1, pp. 353–362, 2020, doi: 10.11591/ijeecs.v19.i1.pp353-362.
A. I. Alfanzar and I. S. Rozas, “Topic Modelling Skripsi Menggunakan Metode Latent,” vol. 7, no. 1, pp. 7–13, 2020.
A. F. Hidayatullah and M. R. Ma’Arif, “Road traffic topic modeling on Twitter using latent dirichlet allocation,” Proc. - 2017 Int. Conf. Sustain. Inf. Eng. Technol. SIET 2017, vol. 2018-Janua, no. August, pp. 47–52, 2018, doi: 10.1109/SIET.2017.8304107.
T. Santika, Evaluasi Perplexity Untuk Pemodelan Topik Diskusi Agama Islam Di Media Sosial Twitter Indonesia Tahun 2006-2018 Menggunakan Latent Dirichlet Allocation Program Studi Matematika Uin Syarif Hidayatullah Jakarta. 2019.
H. S. Koh and M. Fienup, “Topic modeling as a tool for analyzing library chat transcripts,” Inf. Technol. Libr., vol. 40, no. 3, 2021, doi: 10.6017/ital.v40i3.13333.
D. Mimno, H. M. Wallach, E. Talley, M. Leenders, and A. McCallum, “Optimizing semantic coherence in topic models,” EMNLP 2011 - Conf. Empir. Methods Nat. Lang. Process. Proc. Conf., no. 2, pp. 262–272, 2011.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Topik Modelling Terhadap Penggunaan Sosial Media Twitter oleh Pejabat Negara
Copyright (c) 2021 Patmawati Patmawati, Muhammad Yusuf
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).