Identify User Behavior Based on The Type of Tweet on Twitter Platform Using Gaussian Mixture Model Clustering
-
Ridha Novia
*
Telkom University, Bandung,
Indonesia
- Sri Suryani Prasetyowati Telkom University, Bandung, Indonesia
- Yuliant Sibaroni Telkom University, Bandung, Indonesia (*) Corresponding Author
Abstract
Social media has now become a place for social interaction to exchange information about business, politic, and many other. Twitter is one of the social media platforms that provides services for their users to share information and opinions on certain topics. The topic that will be discussed in this study is about politic by collecting tweet data about the student demonstration movement and SemuaBisaKena campaign. By using the word weighting method TF-IDF Vectorizer and Gaussian Mixture Model Clustering, it is possible to identify whether the user behavior is positive (support) or negative (blasphemy). To achieve the final result, there are several stages that must be passed. Such as data preprocessing, feature extraction using TF-IDF Vectorizer, Gaussian Mixture Model Clustering algorithm and data visualization. The results are there is 1 cluster identified as positive behavior and there are 2 clusters identified as negative behavior.
Downloads
References
G. K. Jha dan T. Ramakhrisnudu, “User Behavior Pattern and Deeper Intention,” International Conference for Convergence in Technology (I2CT), 2019.
N. Garg dan R. Rani, “Analysis and Visualization of Twitter Data using,” International Conference on Intelligent Computing and Control Systems (ICICCS) , 2017.
S. Pradha, M. N. Halgamuge dan N. T. Q. Vinh, “Effective Text Data Preprocessing Technique for Sentiment Analysis in Social Media Data,” IEEE, 2019.
Z. Z. Alp dan S. G. Ögüdücü, “Identifying topical influencers on twitter based on user behavior and,” Elsevier Knowledge-Based Systems, pp. 211 - 221, 2017.
S. R. A. Ahmed, I. Al_Barazanchi, Z. A. Jaaz dan H. R. Abdulshaheed, “Clustering algorithms subjected to K-mean and gaussian mixture,” Periodicals of Engineering and Natural Sciences , vol. 7, no. 2, pp. 448 - 457, 2019.
C. Maklin. [Online]. Available: https://towardsdatascience.com/gaussian-mixture-models-d13a5e915c8e.
E. P. dan D. S. K. , “Clustering Cloud Workloads: K-Means vs Gaussian Mixture Model,” Third International Conference on Computing and Network Communication (CoCoNet'19), 2020.
V.-E. N. dan V. C.-B. , “IMPROVED GAUSSIAN MIXTURE MODEL WITH EXPECTATION-MAXIMIZATION,” IGARSS, 2016.
T. Tang, M. Hämäläinen dan A. Virolainen, “Understanding User Behavior in a Local Social Media,” OtaSizzle Research Project, 2011.
A. Mogadala dan V. Varma, “Twitter User Behavior Understanding with Mood Transition,” pp. 31 - 34, 2012.
Z. He dan C.-H. Ho, “An improved clustering algorithm based on finite Gaussian,” Springer, 2018.
S. Husein. [Online]. Available: https://geospasialis.com/visualisasi-data/.
Z. A. L. M. W. T. dan A. W. T. , “Analisis Cluster dengan Menggunakan Metode K-MEANS Untuk Pengelompokkan Kabupataen/Kota Di Provinsi Maluku Berdasarkan Indikator Indeks Pembangunan Manusia Tahun 2014,” Jurnal Ilmu Matematika dan Terapan, 2017.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Identify User Behavior Based on The Type of Tweet on Twitter Platform Using Gaussian Mixture Model Clustering
Pages: 502-506
Copyright (c) 2022 Ridha Novia, Sri Suryani Prasetyowati, Yuliant Sibaroni
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).
