sigir’13 debrief
DESCRIPTION
28 th July - 1 st August Trinity College Dublin (TCD), Dublin, Ireland. SIGIR’13 Debrief. WING Monthly Meeting (Nov 2013) Jovian Lin. Full Paper Acceptance (20%). Top 5 Countries (according to author affiliation). - PowerPoint PPT PresentationTRANSCRIPT
SIGIR’13 Debrief28th July - 1st August
Trinity College Dublin (TCD), Dublin, Ireland
WING Monthly Meeting (Nov 2013)Jovian Lin
Full Paper Acceptance(20%)
Total Accepted0
50100150200250300350400 366
73Num
ber o
f pap
ers
U.S.A. China Netherlands Singapore U.K.0
5
10
15
20
25
30 28
9
5 5 5
Num
ber o
f ind
ivid
uals
Top 5 Countries (according to author affiliation)
Top 5 Technical Areas(based on primary keyword assigned by accepted papers)
users
and i
nterac
tive I
R
search
engin
e arch
itectu
re an
d scal
ability
queri
es an
d que
ry an
alysis
evalu
ation
retrie
val m
odels
and r
ankin
g048
1216 16 15 15
11 11
Perc
enta
ge
Short Paper Acceptance(34%)
Total Accepted0
50
100
150
200
250
300255
85
Tota
l Num
ber o
f pap
ers
Demonstrations Acceptance(50%)
Total Accepted05
101520253035404550
46
23
Num
ber o
f dem
os
Additional Stats
• 7 workshops• 10 tutorials• Doctoral Consortium hosted 11 students
(from 10 countries and 11 institutions)
PHOTOS
Trinity College Dublin (TCD)
• Founded in 1592.
• One of the oldest universities in Europe.
• 35 acre campus located in the heart (<3) of Dublin city.
Select an interesting paper in SIGIR’13
• “Opportunity model for e-commerce recommendation: right product; right time”
• By Jian Wang & Yi Zhang (UC Santa Cruz)
“Opportunity model for e-commerce recommendation: right product; right time” – Jian
Wang & Zhang Yi
• Most of existing e-commerce recommender systems aim to recommend the right product to a user;
• based on whether the user is likely to purchase or like a product.
• But the authors say:• “the effectiveness of recommendations also depends
on the time of the recommendation.”
• Example:• User purchases e a replacement battery after 2
years;• and purchases a new laptop in another 2 years.• Thus it’s not a good idea to recommend a new laptop
or a replacement battery right after the user purchased the new laptop.
“Opportunity model for e-commerce recommendation: right product; right time” – Jian
Wang & Zhang Yi
• What their work does:• Model that estimates the joint probability of a user
making a follow-up purchase of a particular product at a particular time.
• i.e., calculate the probability of a user buying item i at time x
• Why I chose this work:• They analyze the recommendation process at a
deeper level – a quality that I focus on as well.
“Opportunity model for e-commerce recommendation: right product; right time” – Jian
Wang & Zhang Yi
THANK YOU