Towards Search Engine Optimization: Feedback Collation

Available online at www.sciencedirect.com

ScienceDirect Procedia Computer Science 62 (2015) 395 – 402

,QWHUQDWLRQDO&RQIHUHQFHRQ6RIW&RPSXWLQJDQG6RIWZDUH(QJLQHHULQJ

7RZDUGV6HDUFK(QJLQH2SWLPL]DWLRQ)HHGEDFN&ROODWLRQ (LPDQ7DPDK$O6KDPPDUL &ROOHJHRI&RPSXWLQJ6FLHQFHVDQGHQJLQHHULQJ32%R[$O6KDPL\D=LSFRGH.XZDLW

$EVWUDFW 7KHVDPHTXHU\VXEPLWWHGWRGLIIHUHQWVHDUFKHQJLQHDJHQWVFDQOHDGWRGLVVLPLODUVXJJHVWLRQVDQGUHVXOWV&RPSDULQJWKHVH UHVXOWVFDQEHWLPHFRQVXPLQJHVSHFLDOO\ZLWKVRPHTXHULHVJHQHUDWLQJPLOOLRQVRI85/V7KXVDQHIILFLHQWWRROWRFRPSDUH WKH GLYHUVH VXJJHVWLRQV DQG GHWHUPLQH ZKLFK VHDUFK HQJLQH LV WKH EHVW IRU D SDUWLFXODU TXHU\ LV XVHIXO  ,Q WKLV VWXG\ ZH DSSOLHG IHHGEDFN FROODWLRQ $OJRULWKP WR FUHDWH D WRRO WKDW VKDOO DVVLVW WKH XVHU RQ ZKLFK VHDUFK HQJLQH WR GHSOR\ IRU D SDUWLFXODUTXHU\



©‹7KH$XWKRUV3XEOLVKHGE\(OVHYLHU%9 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 6HOHFWLRQDQGRUSHHUUHYLHZXQGHUUHVSRQVLELOLW\RIWKHRUJDQL]HUVRIWKH,QWHUQDWLRQDO&RQIHUHQFHRQ6RIW&RPSXWLQJ Peer-review under responsibility of organizing committee of The 2015 International Conference on Soft Computing and Software DQG6RIWZDUH(QJLQHHULQJ Engineering (SCSE 2015)



Keywords0HWDVHDUFKIHHGEDFNFROODWLRQ,QWHUQHWVHDUFK

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¶VPLQGVZKHQWKH\QHHGWRDFTXLUHLQIRUPDWLRQIURPWKH ZRUOG¶VODUJHVWGDWDVRXUFHWKH,QWHUQHW,QDGGLWLRQWR*RRJOHWKHUHDUHRWKHU6(VVXFKDV
1877-0509 © 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer-review under responsibility of organizing committee of The 2015 International Conference on Soft Computing and Software Engineering (SCSE 2015) doi:10.1016/j.procs.2015.08.432

396

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

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¶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¶VTXHU\$OWKRXJKWKHGDWD SURFHVVLQJ LV VHPDQWLFDOO\ EDVHG WKH SURSRVHG PHWKRG GRHV QRW LQYRNH H[SOLFLW RQWRORJLHV )XUWKHUPRUH UHVSRQGLQJ WR WKH XVHU¶V TXHU\ LQYROYHV DQ DQDO\VLV RI WKH FRQWHQW RI WKH GRFXPHQW ZKLFK FDQ EH H[WUHPHO\ UHVRXUFHLQWHQVLYH7KHUHIRUH/6,FDQEHDSSOLHGWRZHOOGHILQHGFROOHFWLRQVRIGRFXPHQWVVWRUHGLQDOLPLWHG QXPEHURIUHSRVLWRULHV 7KHQH[WDSSURDFKFDQEHUHODWHGWRWKHIRXQGDWLRQRIWKH6HPDQWLF:HE>@7KLVPHWKRGFRQVLGHUVWKH IXQGDPHQWDODVVXPSWLRQWKDWGDWDUHVRXUFHVDUHGHPDUFDWHG2QWRORJ\LVXVHGKHUHDVDJHQHULFVROXWLRQWRWKH SUREOHP 6HPDQWLFEDVHG PLQLQJ FDQ H[WUDFW ILQHJUDLQHG PHWDGDWD IURP DUWLFOHV FRQWDLQHG LQ GLJLWDO UHSRVLWRULHV 0RUHRYHU WKH FXUUHQW VHPDQWLFV LV IRFXVHG RQ D VSHFLILF GDWD VHW WKH 'LJLWDO %LEOLRJUDSK\  /LEUDU\ 3URMHFW '%/3  >@ DQG DQ DWWHPSW KDVEHHQ PDGH WR DQVZHUWKH TXHVWLRQ RI KRZ WRILQG WKH PRVW DSSURSULDWHLWHPZLWKLQWKH'%/37KHNH\REVHUYDWLRQWREHPDGHLQDSSURDFKHVVLPLODUWRWKHWKUHHDERYH

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

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¶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¶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

397

398

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

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
Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

&RGH,2XU3VHXGR&RGH 5DQN6(VXVLQJGLIIHUHQWLDODOJRULWKPLFYDULDWLRQ Step 1 – Initialize algorithmic variations &KRRVHVFRULQJV\VWHPIRUHDFK85/GHSHQGLQJRQLWVGLVWDQFHIURPWKHPHDQVFRUHDFURVVDOO6( &KRRVHRUGHURISURFHVVLQJVHDUFKUHVXOWVHWV /RZWRKLJK +LJKWRORZ &KRRVHVFRULQJRI6( $ULWKPHWLF *HRPHWULF Step 2 – Read data ,QLWLDOL]HVHDUFKHQJLQHQDPHV 5HDGVHDUFKUHVXOWVIRUHDFK6( 8QLTXH85/V 6FRUHRIHDFK85/RQHDFK6(ELJJHULVZRUVH ,QLWLDOL]HQXPEHURI6(VWKDWUHWXUQHGHDFK85/ 7RWDOVFRUHIRUD6(ELJJHULVZRUVH $YHUDJHVFRUHIRUHDFK85/DFURVVHDFK6(ELJJHULVZRUVH Step 3 – Define URL scoring procedure 3URFHGXUHWRVFRUH85/EDVHGRQSHUFHLYHGFXUUHQWUHOLDELOLW\RI6( 2ULJLQDOVFRUHIRUWKLV85/ &XUUHQW6(UHOLDELOLW\VFRUHELJJHULVZRUVH $FWXDOVFRUHFRQVLGHULQJUHOLDELOLW\RI6( Step 4 – Initialize SE and URL scores ,QLWLDOL]HIURPUDZGDWD 6FRUHWKLV85/RQWKLV6( 6FRUH85/XVLQJ&+2,&(RI85/VFRULQJDOJRULWKP 1XPEHURI6(VWKDWUHWXUQHGWKLV85/ 6WDUWLQJVFRUHQRWDFKRLFHDVWKLVVFDOHVDOO6(VHTXDOO\ Step 5 – Score each URL partition 8SGDWH6(VFRUHIURPHDFKXUOSDUWLWLRQVHTXHQFHGE\&+2,&(RISDUWLWLRQRUGHULQJDOJRULWKP *LYHHDFK85/DQHZVFRUH &KRRVH85/VUHWXUQHGE\WKLVFRXQWRI6(V ,QLWLDOL]HDYHUDJHVFRUHIRUHDFK85/ Step 5.1 – Find average and maximum SE distance for each URL in partition (DFKVHDUFKHQJLQH 8UODFWLYHLQWKLVSDVV $FWXDOVFRUHFRQVLGHULQJUHOLDELOLW\RI6( 8SGDWHDYHUDJHVFRUH 1XPEHURI8UOVDFWLYHLQWKLVSDVVIRUWKLV6( $YHUDJHVFRUHIRUXUODFURVV6(V 0D[LPXPGLVWDQFHRYHUDOO6(VIRUWKLVXUO 8UODFWLYHLQWKLVSDVV $FWXDOVFRUHFRQVLGHULQJUHOLDELOLW\RI6( $YHUDJHUDWLQJE\6( 0D[LPXPGLVWDQFH Step 5.2 – Score each SE by partition (DFKXUOLQWKLVSDUWLWLRQ

399

400

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

(DFK6(WKDWUHWXUQHGWKLVXUO $FWXDOVFRUHFRQVLGHULQJUHOLDELOLW\RI6( 'LVWDQFHIURPDYHUDJH 'LVWDQFHVFDOHG 6FRUH6(E\&+2,&(RI6(VFRULQJDOJRULWKP Step 6 – Write results :ULWHUHVXOWV 3ULQWZKLFKDOJRULWKPVZHUHXVHG 3ULQWEHVWILUVWWUDQVIRUPVFRUHVRWKDWELJJHULVEHWWHU ([SHULPHQWDWLRQDQG5HVXOWV 7KH WRS  UHVXOWV H[WUDFWHG IURP UXQQLQJ WKH TXHU\ ³PDUKDED´ RQ HDFK RI WKH IRXU 6(V *RRJOH
4XDGUDWLFUDQNLQJ

 ,QGLFDWLQJ WKDW XVLQJ WKH TXDGUDWLF UDQNLQJ YDULDWLRQ HYDOXDWLQJ WKH 85/V IURP ORZ WR KLJK DQG XVLQJ DULWKPHWLFVFRULQJWKHQ
([S   

$ULWKPHWLFVFRULQJRIVHDUFKHQJLQH /LQHDUUDQNLQJ


([SRQHQWLDO UDQNLQJ






 $VN 

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

401

7DEOH+LJKWRORZVHDUFKHQJLQHFRXQWXVLQJDULWKPHWLFVFRULQJRIVHDUFKHQJLQH 

([S    

$ULWKPHWLFVFRULQJRIVHDUFKHQJLQH /LQHDUUDQNLQJ *RRJOH %LQJ
$VN  $VN  $VN  $VN 

  7DEOH/RZWRKLJKVHDUFKHQJLQHFRXQWXVLQJ*HRPHWULFVFRULQJRIVHDUFKHQJLQH 

([S    

$ULWKPHWLFVFRULQJRIVHDUFKHQJLQH /LQHDUUDQNLQJ
%LQJ  %LQJ  %LQJ  *RRJOH 

$VN  $VN  $VN  $VN 

 7DEOH+LJKWRORZVHDUFKHQJLQHFRXQWXVLQJ*HRPHWULFVFRULQJRIVHDUFKHQJLQH 

([S    

$ULWKPHWLFVFRULQJRIVHDUFKHQJLQH /LQHDUUDQNLQJ
%LQJ  %LQJ  %LQJ  %LQJ 

$VN  $VN  $VN  $VN 



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¶VUHTXLUHPHQWV

402

Eiman Tamah Al-Shammari / Procedia Computer Science 62 (2015) 395 – 402

5HIHUHQFHV >@6HDUFK(QJLQH8VDJH6WDWLVWLFVKWWSZZZDKI[QHWZHEORJDVRQWK$XJXVW,67 >@'$66+(2DQG.8/'((36,1*+5$*+8:$16+,6HDUFK(QJLQH6HOHFWLRQ$SSURDFKLQ0HWDVHDUFK8VLQJ3DVW 4XHULHV  >@$PLQ*KRODP5$OL(PURX]QHMDGDQG+DPLG6DGHJKL0HWDVHDUFKLQIRUPDWLRQIXVLRQXVLQJOLQHDUSURJUDPPLQJRairo-Operatio ns Research  >@0\VSLGHUKWWS0\VSLGHUVLQIRUPDWLFVLQGLDQDHGXDVRQWK-XO\,67 >@/)LQNHOVWHLQ(*DEULORYLFK<0DWLDV(5LYOLQ*:ROIPDQ(5XSSLQ3ODFLQJVHDUFKLQFRQWH[WWKHFRQWH[WUHYLVLWHGLQ :::¶3URFHHGLQJVRIWKHWKLQWHUQDWLRQDOFRQIHUHQFHRIZRUOGZLGHZHE$&01HZ@)R[6WHYH.XOGHHS.DUQDZDW0DUN0\GODQG6XVDQ'XPDLVDQG7KRPDV:KLWH(YDOXDWLQJLPSOLFLWPHDVXUHVWRLPSURYH ZHEVHDUFKACM Transactions on Information Systems (TOIS)QR  >@)UH\QH-LOO5RVWD)DU]DQ3HWHU%UXVLORYVN\%DUU\6P\WKDQG0DXULFH&R\OH&ROOHFWLQJFRPPXQLW\ZLVGRPLQWHJUDWLQJ VRFLDOVHDUFK VRFLDOQDYLJDWLRQ,QProceedings of the 12th international conference on Intelligent user interfacesSS $&0 >@'HHUZHVWHU6FRWW&HWDO,QGH[LQJE\ODWHQWVHPDQWLFDQDO\VLVJAsIs  >@/HWVFKH7RGG$DQG0LFKDHO:%HUU\/DUJHVFDOHLQIRUPDWLRQUHWULHYDOZLWKODWHQWVHPDQWLFLQGH[LQJInformation sciences   >@7KHGEOSFRPSXWHUVFLHQFHELEOLRJUDSK\KWWSZZZLQIRUPDWLNXQLWULHUGHOHEGE$FFHVVHGWK$XJXVW,67 >@=KRX4LHWDOSPARK: adapting keyword query to semantic search6SULQJHU%HUOLQ+HLGHOEHUJ >@:DQJ+DRIHQ7KDQK7UDQDQG&KDQJ/LX&HWRZDUGVDODUJHVFDOHK\EULGVHDUFKHQJLQHZLWKLQWHJUDWHGUDQNLQJVXSSRUWProce edings of the 17th ACM conference on Information and knowledge management$&0 >@:DQJ+DRIHQHWDOQ2semantic: A lightweight keyword interface to semantic search6SULQJHU%HUOLQ+HLGHOEHUJ