ANALYSING TWITTER TRENDING HASHTAG SENTIMENT ABOUT RACISM AND BIGOTRY USING k-NEAREST NEIGHBOUR (k-NN) ALGORITHM

Danisaputra, Revival (2020) ANALYSING TWITTER TRENDING HASHTAG SENTIMENT ABOUT RACISM AND BIGOTRY USING k-NEAREST NEIGHBOUR (k-NN) ALGORITHM. Other thesis, UNIKA SOEGIJAPRANATA SEMARANG.

	Text (COVER) 15.K1.0065 REVIVAL DANISAPUTRA_COVER_a.pdf Download (1MB)
	Text (BAB I) 15.K1.0065 REVIVAL DANISAPUTRA_BAB 1_a.pdf Download (342kB)
	Text (BAB II) 15.K1.0065 REVIVAL DANISAPUTRA_BAB II_a.pdf Restricted to Registered users only Download (646kB)
	Text (BAB III) 15.K1.0065 REVIVAL DANISAPUTRA_BAB III_a.pdf Download (254kB)
	Text (BAB IV) 15.K1.0065 REVIVAL DANISAPUTRA_BAB IV_a.pdf Download (483kB)
	Text (BAB V) 15.K1.0065 REVIVAL DANISAPUTRA_BAB V_a.pdf Download (922kB)
	Text (BAB VI) 15.K1.0065 REVIVAL DANISAPUTRA_BAB VI_a.pdf Download (251kB)
	Text (DAFTAR PUSTAKA) 15.K1.0065 REVIVAL DANISAPUTRA_DAPUS_a.pdf Download (309kB)
	Text (LAMPIRAN) 15.K1.0065 REVIVAL DANISAPUTRA_LAMPIRAN_a.pdf Download (855kB)

Abstract

Racism, bigotry, and fascism are now a big deal around the world especially on social media. Begin when religion blasphemy from fascists and race humiliation were a perfect subject to put down people personally on social media. Overall, this project can analysed and classified whether it is the negative tweet or not by using k-NN implementation. The project use python as its programming language. The first thing came with scrapping tweets by #hashtag trending from twitter, data will be saved in csv form and its title has # symbol on the front. The next step is pre-processing which is tokenize, stopwords, and stemming. Afterwards, the document is calculated with Tf-Idf and compared with data training which also had been calculated with Tf-Idf. The Final step is all the result input into k-NN algorithm to find out the nearest neighbour of negative words which is the lowest score. Final conclusion of this project is the result which has less point has the nearest score on negative text. The document which declared negative is the document which has more than 40% negative texts inside. The accuracy of this calculation is 82.3%.

Item Type:	Thesis (Other)
Subjects:	000 Computer Science, Information and General Works > 005 Computer programming, programs & data
Divisions:	Faculty of Computer Science > Department of Informatics Engineering
Depositing User:	Ms Agustin Hesti Pertiwi
Date Deposited:	23 Jun 2020 04:18
Last Modified:	23 Sep 2020 02:11
URI:	http://repository.unika.ac.id/id/eprint/21432

Actions (login required)

View Item