EVAN, FABIANUS HENDY (2014) PEMBANGUNAN PERANGKAT LUNAK PERINGKAS DOKUMEN DARI BANYAK SUMBER BERBASIS WEB MENGGUNAKAN SENTENCE SCORING DENGAN METODE TF-IDF. S2 thesis, UAJY.
|
Text (Halaman Judul)
0MTF01915.pdf Download (473kB) | Preview |
|
|
Text (Bab I)
1MTF01915.pdf Download (60kB) | Preview |
|
|
Text (Bab II)
2MTF01915.pdf Download (355kB) | Preview |
|
![]() |
Text (Bab III)
3MTF01915.pdf Restricted to Registered users only Download (153kB) |
|
![]() |
Text (Bab IV)
4MTF01915.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (Bab V)
5MTF01915.pdf Download (1MB) | Preview |
Abstract
The need to summarize document is very important as we enter an era where there is a lot of information presented. This thesis presents an automatic document summarization from various sources based on the identification and extraction of important sentences from the source document information using sentence scoring with TF-IDF method. This application was built based website that allows users to access applications anywhere and anytime. This application was built using PHP programming language. The use of PHP intended to sentence scoring proses can be done fairly easy in the server and PHP can also be used to create a web service. TF-IDF method gives value to each word according to their frequency across documents. Sentence scoring is done by adding up the value of each word to obtain the final value of each sentence. Sentence to be used as a summary are selected according to their rank in each document. Sentence scoring using TF-IDF method generate summaries of documents that are extractive and its allows users to understand the gist of a document.
Item Type: | Thesis (S2) |
---|---|
Uncontrolled Keywords: | TF-IDF, document summarization, sentence scoring |
Subjects: | Magister Teknik Informatika > Mobile Computing |
Divisions: | Pasca Sarjana > Magister Teknik Informatika |
Depositing User: | Editor UAJY |
Date Deposited: | 17 Jun 2014 11:56 |
Last Modified: | 17 Jun 2014 11:56 |
URI: | http://e-journal.uajy.ac.id/id/eprint/5278 |
Actions (login required)
![]() |
View Item |