IMPLEMENTASI TEXT MINING UNTUK ADVERTISING DENGAN MENGGUNAKAN METODE K-MEANS CLUSTERING PADA DATA TWEETS GOJEK INDONESIA

Azizah Nurfauziah Yusril, Inggrit Larasati, Qurrotul Aini

Abstract


ABSTRACT

In determining advertising, businesses use social media to find out the responses of their followers. Gojek Indonesia is one of the company in Indonesia who uses Twitter social media as a means to do advertising. The purpose of this research is to find out the type of tweet content that is mostly retweeted and favorite by Gojek Indonesian followers so that it can be used to do advertising to Twitter users. The collection of tweet data from Twitter is done by integrating Twitter API and R programming language using R Studio tools. The data analysis method uses text mining and for the clustering process uses K-means. The results of this study obtained a number of 2 cluster tweets. Based on the calculation of the average number of retweets in each cluster, it was found that the type of content with the most retweets was related to the quiz program and the introduction of Gojek Indonesia’s products. Gojek Indonesia business people can use the retweet and favorite features as a means of advertising Twitter users.

Keywords: advertising, gojek indonesia, text mining, k-means clustering, twitter

ABSTRAK

Dalam penentuan advertising, pelaku bisnis menggunakan media sosial untuk mengetahui respon dari para followers-nya. Gojek Indonesia merupakan salah satu pelaku bisnis di Indonesia yang menggunakan media sosial Twitter sebagai sarana untuk melakukan advertising. Tujuan dari penelitian ini yaitu untuk mengetahui jenis konten tweets yang banyak dilakukan retweet dan favorite oleh followers Gojek Indonesia sehingga dapat digunakan untuk melakukan advertising kepada pengguna Twitter. Pengumpulan data tweets dari Twitter dilakukan dengan mengintegrasikan Twitter API dan bahasa pemograman R menggunakan tools R Studio. Metode analisis data menggunakan text mining dan untuk klasterisasi menggunakan K-means. Hasil dari penelitian ini didapatkan sejumlah 2 klaster tweets. Berdasarkan perhitungan jumlah rata-rata retweet pada tiap klaster, didapatkan bahwa jenis konten dengan retweet terbanyak yaitu terkait program kuis dan perkenalan produk Gojek Indonesia. Pelaku bisnis Gojek Indonesia dapat menggunakan fitur retweet dan favorite sebagai sarana untuk melakukan advertising kepada pengguna Twitter.

Kata Kunci: advertising, gojek indonesia, text mining, k-means clustering, twitter


Full Text:

PDF

References


D. Mccorkle And J. Payan, “Using Twitter In The Marketing And Advertising Classroom To Develop Skills For Social Media Marketing And Personal Branding,” J. Advert. Educ., vol. 21, no. 1, pp. 33–43, May 2017, Doi: 10.1177/109804821702100107.

D. M. Carpenter, J. W. Robertson, M. E. Johnson, And S. Blum, “Social Media Analytics In Education: What Is It, How Is It Useful, And What Does It Tell Us About How Schools Are Discussed In Social Media?,” J. Sch. Public Relat., vol. 35, no. 1, pp. 7–43, Jan. 2014, Doi: 10.3138/Jspr.35.1.7.

"Leading Countries Based On Number Of Twitter Users As Of April 2020," available : https://www.statista.com/statistics/242606/number-of-active-Twitter-users-in-selected-countries/, [Diakses : 18 mei 2020].

D. S. Indraloka And B. Santosa, “Penerapan Text Mining Untuk Melakukan Clustering Data Tweet Shopee Indonesia,” J. Sains Dan Seni Its., vol. 6, no. 2, pp. a51–a56, Sep. 2017, Doi: 10.12962/J23373520.V6i2.24419.

R. K. Putri And B. Warsito, “Implementasi Algoritma Modified Gustafson-Kessel Untuk Clustering Tweet Pada Akun Twitter Lazada Indonesia,” vol. 8, no. 3, p. 11, 2019.

S. Dodi, and S. Iin, " Analisis Sentimen Masyarakat Terhadap data Tweet Lazada Menggunakan Text Mining Dan Algoritma Naive Bayes Classifier," Bina Darma Conference on Computer Science., e-ISSN: 2685-2683p-ISSN: 2685-2675.

Y. W. Syaifudin And R. A. Irawan, “Implementasi Analisis Clustering Dan Sentimen Data Twitter Pada Opini Wisata Pantai Menggunakan Metode K-Means,” J. Inform. Polinema., vol. 4, no. 3, p. 189, May 2018, Doi: 10.33795/Jip.V4i3.205.

I. Putri and Irhamah, "Text Clustering pada Akun Twitter Layanan Ekspedisi JNE, J&T, dan Pos Indonesia Menggunakan Metode Density-Based Spatial Clustering of Applications with Noise (DBSCAN) dan K-Means," Jurnal Sains Dan Seni ITS., vol. 8, no. 2, 2019.

B. Lantz, "Machine Learning With R: Learn How To Use R To Apply Powerful Machine Learning Methods And Gain An Insight Into Real-World Applications," Birmingham: Packt Publ., 2013.

R. Feldman And J. Sanger, "The Text Mining Handbook: Advanced Approaches In Analyzing Unstructured Data," Cambridge; New York: Cambridge University Press., 2007.

Hartanto, " Text Mining Dan Sentimen Analisis Twitter Pada Gerakan LGBT", 2017.

J. Kogan, M. Teboulle, And C. Nicholas, “Data Driven Similarity Measures For K-Means Like Clustering Algorithms,” Inf. Retr., vol. 8, no. 2, pp. 331–349, Apr. 2005, Doi: 10.1007/S10791-005-5666-8.

S. Ahuja And G. Dubey, “Clustering And Sentiment Analysis On Twitter Data,” p. 5, 2017.

J. Macqueen, “Some Methods For Classification And Analysis Of Multivariate Observations,” Multivar. Obs., p. 17.

L. Sahu And B. R. Mohan, “An Improved K-Means Algorithm Using Modified Cosine Distance Measure For Document Clustering Using Mahout With Hadoop,” In 2014 9th International Conference On Industrial And Information Systems (Iciis), Gwalior, India., pp.1-5, Dec. 2014, Doi: 10.1109/Iciinfs.2014.7036661.




DOI: https://doi.org/10.32520/stmsi.v9i3.924

Article Metrics

Abstract view : 128 times
PDF - 54 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.