JOURNAL

COMPLETE LINK METHOD FOR IMPROVED RANKING WEBSITE

FINAL PROJECT

By :
Abdul Aris
G.231.09.0211

S1-ENGINEERING STUDY PROGRAM INFORMATION

DEPARTMENT OF INFORMATION TECHNOLOGY
FACULTY OF INFORMATION AND COMMUNICATION TECHNOLOGY
UNIVERSITY SEMARANG
2014

COMPLETE LINK METHOD FOR IMPROVED RANKING WEBSITE

 Abdul Aris 1)
ABSTRAK
The index page acces log pages grouping known as search engine keyword information , the
presence of acces log data can provide some information as well as briefly explaining the information
about a search engine keywords entered into a website .
 In this research , a system designed for the application with keyword search engines classify
Complete Link method in this case involves the activity of a user in accessing the index page . then
implement and classify these keywords with Complete Link method .
Complete link clustering is a method that can be used to categorize the keywords or content that
goes into a website . Complete the link included in the hierarchical method clastering so that the output
from this method or content keywords are grouped in the form of a hierarchy or tree view . The results of
this clustering analysis can be made in reference to business owners online store for promotional segment
for the website administrator prodak and can be used as a reference to improve the content ..

Keyword : Search engine keyword ,Metode Complete Link,clastering.

1. INTRODUCTION COMPLETE LINK METHOD FOR

1.1 Background IMPROVED RANKING WEBSITE
Today the search for information through
search engines is a vital and so on . Typing 1.2 Problem Formulation
keywords in the search engines can interpret Based on the background of the problem, the
user interest to a user informasi. when visiting problem to be addressed is "How to build an
the website then the user data will be recorded application to group search engine keywords to
include IP , protocol , including the site of Complete Link method".
origin if the user comes from the search engines 1.3 Destination
look for keywords that are also recorded in The results of this study aims to establish the
log.Keyword acces very useful in the application of search engine Optimization
development of the website because he is a user Method Using Complete Link
interest . If the numbers are still a little 1.4 Complete linkage
keyword analysis can be done manually , but as Complete linkage (furthest neighbor). In this
the number of keyword analysis manually then method, the distance between the clusters is
it will take time and effort very much . It is determined by the greatest distance between
necessary in the wake of an application that can two objects in different clusters this method is
group interests so that the analysis becomes quite good in cases when objects actually form
easier . naturally (Liu, Bing)
Complite link clustering is a method that can be the steps to the formation of clusters with
used to group keywords website . Complete the complete link method is as follows:
link included in the hierarchical method 1. Started by assigning each a document so that
clastering so that the output of this method in the if there is a cluster of N documents, the
form of keywords are grouped in the form of a number of clusters that have as many pairs
hierarchy or tree view so that website N.Cari clusters with large distances (most
administrators can analyze interest in the sub similar) and merge into a single cluster, so
interest , so that a referral can be made online the number of existing clusters is reduced by
shop for business owners to perform one.
segmentation and promotion prodak the 2. Update the distance matrix by calculating the
administrator of the website can be used as a distance (similarity) between the new cluster
reference to improve the content so that visitors with the old cluster, use the largest distance
feel comfortable in visiting the website . Based 3. Repeat steps two and three until all
on these descriptions , the authors would like to documents into a single cluster. For
achieve this goal in the final with the
1)
Program Studi S1-Teknik Informatika, Universitas Semarang
 example, the distance between the unknown by a space character, so the tokenizing process
matrix object 5 as follows: relying on the document for a space character to
a b c d e separate words. whole series of sentences, each
D= { d ik }= 11 ¿ b ¿ 9 ¿ 0 ¿ 7 ¿5 ¿ 10 ¿ c ¿3 ¿ 7 ¿ 0 ¿ 9 ¿ 2 ¿ d ¿ 6 ¿ 5 ¿ 9 ¿ 0 ¿ 8 ¿ e ¿ 11¿ 10 ¿ 2 ¿ 8 ¿ 0¿
a 0 9 3 ¿ separated by a space he said, after going through
the process of tokenizing the sentence into a set
From the distance matrix can be in the know of arrays which each cell contains the words that
min (d_ (ik)) = d_ (ec) = 2 then the document e exist in the sentence. In the tokenizing process
and c combined to form clusters {e, c} with the usually also added information on the number of
document a, b, d is the largest distance: d_ occurrences of each word of the sentence.
((ce ), a) = max {d_ca, d_ea} = max {3,11} = 1.6 Filtering
11d_ ((ce), b) = max {d_cb, d_eb} = max Filtering is the process of making the words
{7,10} = 10d_ ((ce), d) = max {d_cd, d_ed} = that are considered important or has meaning
max {9,8} = 9 Remove rows and columns only. In this process the words are considered
corresponding to the document D e and c and to have no meaning as the conjunction will be
adding rows and columns to cluster {c, e} in removed. In this process typically used
order to obtain a distance matrix stopwords or stop word list stored in a database
{c , e } a b d table, which then is used as a reference for the
9¿ a¿ 11 ¿ 0 ¿ 9 ¿ 6 ¿ b ¿ 10¿ 9 ¿ 0 ¿ 5 ¿removal d ¿ 6 ¿ 6 ¿5 ¿ 0 ¿word. overview of the results of
of the
{c , e } 0 11 ¿
the filtering process, the word is shown as 'in',
The smallest distance between pairs of
'is' and a, through the removal process.
clusters are nowd bd = 5 so that the cluster {b}
1.7 Stemming
and cluster {d} combined into cluster {b,d} Steming process is a process to find the root
with {c,e} and a of a word results from the filtering process.
d ( bd) a = max {d ba , d da } = max{9,6}= 9 Search the root of a word or so-called basic
d ( bd) (ce) = max {d b (ce ) , d d (ce) } = words can reduce the index results without
min{10,9}=10 having to remove the meaning. Filtering is the
The new distance matrix now is : process of making the words that are considered
{b , d } {c , e } a important or has meaning. There are two
9 ¿ {c , e }¿ 10 ¿ 0 ¿ 11¿ a¿ 9¿ 11to¿ 0stemming
approaches ¿ the dictionary approach
{b , d } 0 ¿
and the approach that is the rule. Several studies
have also been conducted for both Indonesian
The smallest distance between pairs of
stemmer dictionary approach, or pure rule
clusters are now d ( bd) a = 9 combined cluster approach. Algorithms with such rules approach
{b,d} and cluster {a} combined into {a,b,d}. introduced by Vega (2001) and Tala (2003) they
The number of clusters now there are two each have different algorithms in the process of
clusters {c,e} and cluster {a,b,d}, the greatest stemming the Indonesian language document.
distance from the second cluster is: Stemming in the English language, is derived
d ( ce)(abd) = max {d (ce) a , d (ce) (bd) } = from the word origins learning basic word is
max{11,10}=11 The final distance matrix is : changed to learn. Then returned to form words
{c , e } {a , b , d } using the base into use. But the text says is that
11 ¿ {c , e }¿ 11¿ 0 ¿ the basic word is not changed
{b , d } ¿
1.8 Planning System
the last step is to combine the cluster {a, c, e}
and cluster {b, d} to form a cluster.
1.5 Tokenizing
Tokenizing process is the process of cutting
the string input by every word that has put them
together. In principle this process is to separate
each word that make up a document. In general,
each said identified or separated by other words

1)
Program Studi S1-Teknik Informatika, Universitas Semarang
 b. Software
The software used in the making of the
program are as follows::
a. Sistem Operasi Windows 7
b.PHP
c. Apache webserver
d.Notepad ++
e. Browser
f. MySQL Database Server

1.8.4 System Design

The system being designed, developed
using modeling diagrams in UML
(Unified Model Language). The following
diagram images:

a.Use Case Diagram

Planning is an attempt to determine the In the use case described above that the system
activities to be carried out in future by drafting is user friendly. Where the user can access the
and outlining those goals in order to achieve the menu system
goal, so that all activities be focused and
efficient ( Mulyanto, A, 2009). Tutorial

1.8.1 Analysis System Design Home

Pre-proses

1.8.2 Description of System <<extended>>

Application development search engine <<extended>> Proses 1

optimization by using the complete link method Upload acces log

<<etended>>
Proses2
aims to assist and support the promotion of user
<<extended>>

segmentation products of an online store that Cluster Complete

will be thrown into the market due keywords or Hasil Clastering

content grouped in the form of a hierarchy or

tree view, so that the decision making process in Gambar 3. Use Case Diagram
the promotion of a product store online. This
application helps a website administrator can b. Squence Diagram Upload
analyze the content or keyword optimally. For
the criteria used by the highest number of : Upload Acces Log : Pilih File
: Upload

keywords are entered into acces logs.In making : User

the new system is the desired list of

1 : Pilih Menu Upload Acces Log()

2 : Tampilan Menu Upload()

requirements:
a. Setting up a website www.obatkuat-paten.com
3 : Klik Menu Pilih File()

b. Downloading the data acces logs.

4 : Tampilan File yang akan di upload()

1.8.3 Analisis Hardware dan Software 5 : Kilik Menu Upload()

a. Hardware 6 : File di upload()

Hardware specifications are used in the

implementation of the system / application, Gambar 4. Squence DiagramUpload
include:
1. Processor Intel Core i3 c. Squence Diagram Pre-proses
2. Memori 2 Gb
3. Harddisk 320 Gb : Pre-proses

4. Monitor LCD : User

5. Keyboard dan Mouse 1 : Pilih Menu Pre-proses()

6. Printer
2 : Tampilan file acceslog yang berhasil di upload()

1)
Program Studi S1-Teknik Informatika, Universitas Semarang
 d. Squence Diagram Proses 1
Gambar 5. Class Diagram

i. Activity Diagram Home

Pilih menu home

Menu home

e. Squence Diagram Proses 2

j. Activity Diagram Tutorial
: Proses2

: User

1 : Pilih Menu Proses2() Pilih menu tutorial

2 : Tampilan langkah lanjutan proses 1()

Tutorial

f. Squence Diagram Claster Complete Link

: Claster Complete Link

k. Activity Upload Acces log
: User

1 : Pilih Menu Claster Complete Link() Pilih Menu upload

2 : Tampilan proses claster() Pilih file

Upload f ile

g. Squence Diagram Hasil Claster

Tampilan f ile berhasil di upload

Complete Link

l. Activity Pre-proses

Pilih preproses

Preproses

h. Class Diagram

Keyphrase Similaritas
Indek
+Frase +Pk_id

m. Activity Proses1
+PK_id +r
+Jumlah +PK_kata
+Status +s
+Jumlah +drs
+Clastered
+Pre-proses() +m
+Baca _acceslog()
+similaritas()

1..*
1..*

Claster
Stopword Step
Pilih proses 1 +PK-id
+PK-id +PK_id +m
+Kata +m +r
+i +s
+PK_stopword()
+PK_Step() +PK-Clater()
1)
Program Studi S1-Teknik Informatika, Universitas Semarang
Proses 1
 Analysis of system design has been done in
detail, then the next step is towards the
implementation phase. The purpose of the
implementation phase is to explain about the
manual module to all users who will use the
system. So that the user can respond to what is
n. Activity Proses2 displayed by the system and provide input to
system maker to be repaired in order to be a
better system.

1.9.1 Testing Methods of implementation

Pilih proses 2
System testing is the cornerstone that aims
to discover faults or deficiencies in the software
Proses 2 being tested. The test aims to determine which
software meets the criteria were made in
accordance with the purpose of designing such
software.

1.10 Implementasi Program

o. Activity Cluster Complete Link a. Form Home
Home menu function to view the
applications menu system.
Pilih Claster Complete Link

Coloumn Data Type Allaw

Claster Complite Link Name Nulls
Frase Varchar (255)
Jumlah Tinyint (4)
Status Tinyint (4)
Id Int (11)

b. Form Menu Pre-proses

p. Activity Hasil Cluster Complete Link Upon successful entry of the Home Menu,
3.2.5. Designing Database
The design of the database used in this
system is as this database is an information
system that integrates a collection of data that Pilih Hasil Cluster

are interconnected to each other and make it

available to multiple applications. The design of Hasil Cluster Complete Link

the database used for data processing

applications can be described as follows:
* : Primary Key
** : Foreign Key
a. Tabel Keyphrase it will immediately appear Menu Pre-process.
Function : input data, store data
File Name : TBKeyphare

1.9 IMPLEMENTASI SISTEM

1)
Program Studi S1-Teknik Informatika, Universitas Semarang
 2.CONCLUSION
Based on a case study that has been
done, then the author can take some conclusions
c. Form Menu Proses 1 as follows:
In this form is used to process the file a) Application Optimization Search Engines
successfully uploaded. Complete Link Method Using built can be
used as a means to improve the segmentation
promotion prodak online store.
b) Application Optimization Search Engines
Complete Link Method Using built to
increase the number of penggunjung website
thereby increasing the number of purchases at
online stores prodak.
c) Application Optimization Search Engines
d. Form Menu Proses 2 Complete Method Using these links can
This form is used to continue the process 1 provide convenience in managing a product
or item that has not been touched by the
search engines.
d) Application Optimization Search Engines
Complete Method Using these links to search
engine optimize a website to the online store.
e) Complete Application Linked To Increased
Website Ranking can improve the ranking of
a website on the first page ranks in the search
engines

e. Form Menu Claster Complete Link REFERENCES

This form is used to perform the complete Abdurrahman1, Bambang Riyanto, T.2, Rila
link cluster. Mandala3, Rajesri Govindaraju4, 2009,
Klasifikasi Pengguna WEB Dalam
Usage Mining Untuk Business
Intelegence Dengan Algoritma Ant
colony optimization, Jurnal Penelitian
dan Pengembangan
TELEKOMUNIKASI, Vol. 14, No. 1,
Juni.

Bernard Renaldy Suteja, Ahmad Ashari, 2008,

f. Form Menu Result Claster Complete Ontology e-Learning Content berbasis
Link Web Semantic, Seminar Nasional
This form is used to display the results of Aplikasi Teknologi Informasi
complete link clusters. Yogyakarta.

Baeza,R.,dan Ribeiro,B,1999, Modern

Information Retrieval,ACM Press New
York,USA.
Eirinaki,M.,dan Vazirgiannis,M.,2003,web
mining for web Personalization,

1)
Program Studi S1-Teknik Informatika, Universitas Semarang
 Journal of ACM Transaction on and Computation , Universiti van
Internet Technology (TOIT) 1-27. Amsterdam,The Netherlands.

Kadir, Abdul, 2002, Pemrograman Web Tyagi,N.K., Solanki, A.K., dan Wadhwa,M.,
mencakup HTML, CSS, Javascript 2010. Analysis of Server Log by web
dan PHP, Penerbit Andi, Yogyakarta Usage Mining for Website
Improvement, Eirinaki,M.,dan
Kadir, Abdul, 2008, Dasar Perancangan dan Vazirgiannis,M.,2003,web mining for
Implementasi Database Relasional, web Personalization, Journal of ACM
Penerbit Andi, Yogyakarta Transaction on Internet Technology
L.Fausett, 1994, Fundamentals of Neural (TOIT) 1-27.
Networks: Architectures, Algorithms,
and Applications, Prentice-Hall Inc., IJCSI International Journal of Computer
USA. Science Issues, Vol.7,Issues 4,No
Liu,Bing, 2010, Web DataMining Exploring 8,July 2010
Hyperlinks,Contents, and Usage Data
Vijayalakshmi, S., Mohan,V., dan Raja,SS.,
Liu,B., 2007, Web Data Mining: Exploring 2009.Mining Constrain-Based
Hyperlinks,Contents, and Usage Data, Multidimension Frequent Sequential
Department of Computer Science Pattern in Web Logs,European Journal
University Of Illinois,Chicago,IL. of Scientific Research 36(3),480-490.
Nugroho, Bunafit, 2010, Latihan Membangun Xie,Y., dan Phoha,V.V.,2001,Web User
Aplikasi WEB PHP dan MYSQL Clustering from Acces Log Using Belief
dengan Dreamweaver MX, Gava Function, Proceedings of the 1st
Media. International conference on Knowledge
capture,vol.1, Britis Columbia,Oktober
Otsuka,S.,dan Kitsuregawa,M.,2006, Clustering 22-23,202-208.
Of Search engine Keywords Using
Acces Logs,Proceeding of the 17th
International conference on Database
and Expert System Applications,
Krakow, September 4-8,842-854.

Pudjo,Prabowo 2011, Menggunakan UML,

Informatika, Bandung
Prasetio ,Adhi , 2012, Buku Pintar
Pemrograman WEB, Mediakita,Jakarta.
Mulyanto ,Agus, 2009, Sistem Informasi
Konsep dan Aplikasi, Jakarta.
R.C. Gonzalez, R.E. Woods, 1992, Digital
Image Processing, Addison-Wesley
Publishing Company, USA.

Salton,G.,1989,Automatic Text Processing,

Addison-Wesley,Reading,Mass.

Tala,Z.,2003,A Study of Stemming Effects on

Information Retrieval in Bahasa
Indonesia,Institute for Logic, Laguage

1)
Program Studi S1-Teknik Informatika, Universitas Semarang