CLASSIFICATION OF RADICALISM SENTIMENT IN INDONESIAN DA'WAH RADICAL CONTENT THROUGH THE SOCIAL MEDIA TWITTER USING SENTIMENT ANALYSIS AND TEXT MINING METHODS IN THE COVID-19 ERA

Aulia Aziza, Munsyi Munsyi

Abstract


The Ministry of Communication and Information (Kemenkominfo) Indonesian declare the number of internet users in Indonesian country on 2019-2020 reached 196,7 million people. the total number of them, 95% of the users use the internet for accessing the social media networks such twitter, instagram, facebook, and many other things. This increase was also influenced by the pandemic period that was experienced throughout the world, especially in Indonesia, where the Government of President Jokowi set social rules in society. Almost all activities are carried out at home, especially in the field of education. this has led to a tremendous increase in internet access. the massive activity in internet access, especially social media, makes it easy for users to access information and share this information with anyone at any time. all of this can make irresponsible parties to use the opportunity to spread information that can lead to negative things and even provocations against other users on social media, especially Twitter social media. On Twitter social media there is a phenomenon known as a buzzer, namely social media users who have an impact on other users. platforms such as social media twitter are used by certain parties to form hate groups, racist communities that spread extremist ideas and incite anger or violence, promote radicalization, recruit members and create virtual organizations to carry out acts of terror organized through the virtual world. Regarding of the content in online media that has received enough attention along with various incidents that lead to intolerance in people's lives, it is a problem of radical content that gives birth to radicalism in society. in this research we try the Text Mining method using Sentiment Analysis for detecting of the direction radicalism sentiment in order to classify and detect content that contains radicalism. The classification of radical content with the method in this reearch can run very well, most of the content data classified according to the classification system produces an accuracy value of 66.37%.

Full Text:

PDF

References


Agama, Institut, Islam Negeri, and Iain Mataram. 2012. “Islam Fundamentalis Sebagai Fenomena Politik” 15: 264–74.

Chaurasia, Nisha, and Akhilesh Tiwari. 2013. “Efficient Algorithm for Destabilization of Terrorist Networks.” International Journal of Information Technology and Computer Science 5 (12): 21–30. https://doi.org/10.5815/ijitcs.2013.12.03.

Kaplan, Andreas M., and Michael Haenlein. 2009. “The Fairyland of Second Life: Virtual Social Worlds and How to Use Them.” Business Horizons 52 (6): 563–72. https://doi.org/10.1016/j.bushor.2009.07.002.

Saritha, K. 2020. “Block Chain Authentication Using Elliptic Curve Digital Signature Algorithm” 3 (2): 71–75.

Setianto, Widodo Agus. 2019. “Literasi Konten Radikal Di Media Online.” Jurnal Ilmu Komunikasi 16 (1): 75. https://doi.org/10.31315/jik.v16i1.2684.

Suryandari, Nikmah, and Vivi Lutviana. 2020. “Impression Management of Buzzer in Social Media Twitter.” Jurnal Studi Komunikasi (Indonesian Journal of Communications Studies). https://doi.org/10.25139/jsk.v4i3.2665.


Refbacks

  • There are currently no refbacks.