2016 4th International Conference on Information and Communication Technology (ICoICT) 2016
DOI: 10.1109/icoict.2016.7571885
|View full text |Cite
|
Sign up to set email alerts
|

Combination of Latent Dirichlet Allocation (LDA) and Term Frequency-Inverse Cluster Frequency (TFxICF) in Indonesian text clustering with labeling

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0
3

Year Published

2018
2018
2024
2024

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(11 citation statements)
references
References 11 publications
0
8
0
3
Order By: Relevance
“…Term Frequency-Inverse Cluster Frequency (TF-ICF) [23] is one of the weighting terms based on information from documents on a cluster. It makes this method capable of knowing information about the value of a term in a term.…”
Section: Expanding Term List (Tf-icf)mentioning
confidence: 99%
“…Term Frequency-Inverse Cluster Frequency (TF-ICF) [23] is one of the weighting terms based on information from documents on a cluster. It makes this method capable of knowing information about the value of a term in a term.…”
Section: Expanding Term List (Tf-icf)mentioning
confidence: 99%
“…Term Frequency-Inverse Cluster Frequency (TF-ICF) [10] is the method of weighting terms based on information from document on cluster. In general, TF-ICF calculates term frequency from the document on each clusters.…”
Section: Keyword Extraction (Tf-icf)mentioning
confidence: 99%
“…The candidate aspects obtained are categorized with the aspect keywords using word similarity. These keywords are generated using TF-ICF [10] algorithm from Wikipedia.…”
Section: Introductionmentioning
confidence: 99%
“…Pemilihan frasa kandidat dapat menggunakan pendekatan statistik, berbasis graf, atau klasterisasi topik. Pemilihan frasa dengan pendekatan statistik antara lain dengan pembobotan Term Frequency -Inverse Cluster Frequency (TF-ICF) [27], menggunakan perhitungan Markov Chain [11], dan pemberian nilai frasa kandidat berdasarkan Pointwise Mutual Information (PMI) [28]. Pemilihan frasa kandidat berbasis graf sebagai representasi teks seperti TextRank [23]…”
Section: Pelabelan Klaster Dan Klasterisasi Topikunclassified
“…Pertama-tama, distribusi topik dari klaster artikel ilmiah didapatkan dengan metode Latent Dirchlet Allocation (LDA) pada kumpulan dokumen di klaster d [27]. Metode LDA menghasilkan model topik dengan merupakan topik ke-k. Model topik memiliki dua jenis probabilitas topik yang direpresentasikan dalam bentuk vektor, yaitu probabilitas kata terhadap topik dan probabilitas topik terhadap klaster dokumen seperti pada (5).…”
Section: E Ekstraksi Frasa Kunci Dengan Topicrankunclassified