暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
舆情场景下基于层次知识的话题推荐方法 - 史存会, 胡耀康, 冯彬, 张瑾, 俞晓明, 刘悦, 程学旗.pdf
90
9页
0次
2021-11-16
免费下载
DOI
:
issn
JournalofCom
p
uterResearchandDevelo
p
ment
(
):
,
 
稿
:
;
:
 
:
(
);
(
);
(
ts
)
Thisworkwassu
pp
ortedb
y
theNationalNaturalScienceFoundationofChinaforDistin
g
uishedYoun
g
Scholars
(
),
the
Ma
j
orPro
g
ramofNationalNaturalScienceFoundationofChina
(
),
andtheTaishanScholarsPro
g
ram ofShandon
g
ProvinceofChina
(
ts
)
,
 
耀
,
 
 
,
 
 
 
 
 
 
(
 
 
)
(
(
)
 
 
)
(
 
 
)
(
 
 
)
(
shicunhuiictaccn
)
A HierarchicalKnowled
g
eBasedTo
p
icRecommendation MethodinPublic
O
p
inionScenario
ShiCunhui
,
,
HuYaokan
g
,
,
Fen
g
Bin
,
,
Zhan
g
Jin
,
YuXiaomin
g
,
LiuYue
,
andChen
g
Xue
q
i
(
DataIntelli
g
enceS
y
stem ResearchCenter
,
Instituteo
f
Com
p
utin
g
Technolo
gy
,
ChineseAcadem
y
o
f
Sciences
,
Bei
j
in
g
)
(
CAS Ke
y
Laborator
y
o
f
NetworkDataScienceand Technolo
gy
(
Instituteo
f
Com
p
utin
g
Technolo
gy
,
ChineseAcadem
y
o
f
Sciences
),
Bei
j
in
g
)
(
Universit
y
o
f
ChineseAcadem
y
o
f
Sciences
,
Bei
j
in
g
)
(
Instituteo
f
NetworkTechnolo
gy
ICT
(
YANTAI
),
ChineseAcadem
y
o
f
Sciences
,
Yantai
,
Shandon
g
)
Abstract  Withthera
p
iddevelo
p
mentofinformationtechnolo
gy
,
Internethasbecomethe main
carrierof
p
ublico
p
inions
p
readin
g
Allkindsof
p
ublico
p
inioneventscomeoutoneaftertheother
,
whichcanbe
q
uickl
y
s
p
readondifferentmediainashorttimeandreceiveextensiveattentionand
p
artici
p
ationfromlar
g
escaleInternetusersItma
y
alsotri
gg
erastron
g
reactionintheInternets
p
ace
andtherealsociet
y
,
andeveninducelar
g
escale massincidentsTherefore
,
q
uick monitorin
g
and
effectiveearl
y
warnin
g
ofonline
p
ublico
p
inioneventsbecomemoreandmoreim
p
ortantInres
p
onse
tothe
g
rowin
g
scaleofInternetinformationandtheex
p
andin
g
sco
p
eofitsdissemination
,
howto
discoveronline
p
ublico
p
inioneventsand
p
ushthe
p
recise
p
ersonalized monitorin
g
informationhas
becomethefocusofcurrent
p
ublico
p
iniona
pp
licationsAimin
g
atthe
p
roblemthattheinterestis
hardtoca
p
tureincaseofthes
p
arsit
y
ofuserinteraction
,
ato
p
icrecommendation modelbasedon
HKN
(
hierarchicalknowled
g
enetwork
)
is
p
ro
p
osedThemodelex
p
andsthesemanticsandincreases
p
otentialinformation association betweento
p
ics b
y
usin
g
hierarchicalknowled
g
eIt modelsthe
hierarchical knowled
g
e
,
to
p
ics
,
and users to obtain corres
p
ondin
g
embeddin
g
s With those
embeddin
g
s
,
weuseamultila
y
er
p
erce
p
tronmatchin
g
modelto
p
redicttheCTR
(
clickthrou
g
hrate
)
Ex
p
erimentalresultsshowthatthe HKN modelout
p
erformsmulti
p
lebaselineal
g
orithmsb
y
and ontheavera
g
eof
F
(
thebalanced
F
score
)
andAUC
(
theareaundercurve
)
metricsCTR
valueres
p
ectivel
y
Ke
y
words to
p
icrecommendation
;
hierarchicalknowled
g
e
;
p
ublico
p
inionscenario
;
recommendation
s
y
stem
;
knowled
g
eembeddin
g
 
 
,
,
广
,
,
,
,
,
,
,
线
,
F
(
thebalanced
F
score
)
AUC
(
theareaundercurve
)
 
;
;
;
;
 TP
  htt
p
:
y
u
q
in
g
p
eo
p
lecom.cnGBnchtml
  
,
,
,
,
(
),
使
,
,
,
,
,
,
,
,
,
,
,
广
,
,
,
广
 
,
,
,
,
 
(
to
p
icdetectiontask
,
TDT
)
[
]
,
,
,
使
,
K
Means
,
BIRCH
(
balancediterativereducin
g
andclusterin
g
usin
g
hierarchies
),
Sin
g
lePass
,
p
LSA
(
p
robabilisticlatentsemanticanal
y
sis
)
[
]
LDA
(
latentDirichletallocation
)
[
]
,
 
,
,
,
,
使
,
[
]
[
]
使
(
)
,
,
,
 
,
(
)
of 9
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。

评论

关注
最新上传
暂无内容,敬请期待...
下载排行榜
Top250 周榜 月榜