Indonesia Conference Directory


<< Back

Text Mining Pre-processing Using Gata Framework and Rapidminer for Indonesian Sentiment Analysis
Sigit Kurniawan (a*), Dewi Ayu Puspitawati (a), Windu Gata (a), I Ketut Sakho Parthama (b), Hendra Setiawan (c), Sari Hartini (a)

a) Sekolah Tinggi Manajemen Informatika dan Komputer Nusa Mandiri
Jl. Kramat Raya No.18, RT.5/RW.7, Kwitang, Senen, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta 10450
*kurniawan.sgt[at]gmail.com
b) Universitas Pramita Indonesia
Jl. Raya Kampus Pramita, Binong Curug Tangerang 15810 Banten.
c) Sekolah Tinggi Manajemen dan Komputer Bani Saleh
Jl Mayor M. Hasibuan No 68, Margahayu Bekasi Timur, Bekasi Timur, Kota Bekasi 17113, Jawa Barat


Abstract

Indonesian text preprocessing is still very limited and requires tools that can help Indonesian researchers to conduct research in the field of text mining in Indonesian, especially on Twitter. Preprocessing needed for text mining processes such as deleting @ notation; Http; stop words; normalize acronym words, slang words, emoticons; and Indonesian stemming. Gataframework besides providing an OPP-based PHP framework, it also provides text mining preprocessing tools to support those needs. The results of Gataframework text mining preprocessing output can be combined with other tools, one of which is Rapidminer. Gataframework also features a web services API that can be connected with other applications. Since 2018, many studies related to Text Mining have begun to use Gataframework as an alternative tool in the preprocessing stage. The results of the use or quality of this tool are assessed by the Likert evaluation model and the Functionality, Usability, Reliability, Performance, Supportability (FURPS) is known as a model for classifying method which has the parameters Functionality, Usability, Reality, Performance, and Supportability. Based on Gataframework users assessment of 21 respondents, the results were Functionality (87.62%), Usability (85.71%), Reality (85.71%), Performance (80.95%), and Supportability (85.71%) while the average value of the overall parameters was 85.14 %, which means very good.

Keywords: Text mining; Pre-processing; Stemming; Indonesian stemming; Gata framework; Likert; FURPS

Topic: International Symposium of Engineering, Technology, and Health Sciences

Link: https://ifory.id/abstract/btdfFqYZcEDP

Conference: The 3rd International Conference on Sustainability and Innovation (ICoSI 2019)

Plain Format | Corresponding Author (Sigit Kurniawan)

Featured Events

<< Swipe >>
<< Swipe >>

Embed Logo

If your conference is listed in our system, please put our logo somewhere in your website. Simply copy-paste the HTML code below to your website (ask your web admin):

<a target="_blank" href="https://ifory.id"><img src="https://ifory.id/ifory.png" title="Ifory - Indonesia Conference Directory" width="150" height="" border="0"></a>

Site Stats