What is a user search task? - University of Illinois at

Download Report

Transcript What is a user search task? - University of Illinois at

Computational User Intent
Modeling
Hongning Wang
March 6, 2013
Research Summary
 Joint relevance and freshness learning [WWW’12]
 Content-Aware Click Modeling [WWW’13]
 Cross-Session Search Task Extraction [WWW’13]
7/18/2015
2
Understanding User Intent is Important
• “Apple Company” @ Oct. 4, 2011
Release of iPhone 4S
Understanding User Intent is Important
• “Apple Company” @ Oct. 5, 2011
Steve Jobs passed away
Release of iPhone 4S
Relevance v.s. Freshness
• Relevance
– Topical relatedness
– Metric: tf*idf, BM25, Language
Model
• Freshness
– Temporal closeness
– Metric: age, elapsed time
• Trade-off
– Query specific
– To meet user’s information need
Our Contribution
Joint Relevance and Freshness Learning
• JRFL: (Relevance, Freshness) -> Click
Query => trade-off
URL => relevance/freshness
Click => overall impression
Quantitative Comparison
• Ranking performance
– Random bucket clicks
Content-Aware Click Modeling
• Study the underlying mechanism of user clicks
Freshness weight=0.8
R=0.39
F=2.34
Y=1.95
R=1.72
F=2.18
Y=2.01
R=2.41
F=1.76
Y=2.09
Modeling User Clicks
Match my
query?
Redundant
doc?
Shall I
move on?
Our Contribution
Content-Aware Click Modeling
• Encode rich dependency within user browsing
behaviors via descriptive features
Chance to further examine the result
documents: e.g., position, # clicks,
distance to last click
Chance to click on an examined
and relevant document: e.g.,
clicked/skipped content
similarity
Relevance quality of a document:
e.g., ranking features
Experimental Results
• Take advantage of both counting-based and
feature-based methods
Learning to Extract Search Tasks
• An atomic information need that may result in
one or more queries
5/29/2012 S1
5/29/2012 5:26
bank of america
5/29/2012 S2
5/29/2012 11:11
macy's sale
5/29/2012 11:12
sas shoes
5/30/2012 S1
5/30/2012 10:19
credit union
5/30/2012 S2
5/30/2012 12:25
6pm.com
5/30/2012 12:49
coupon for 6pm shoes
12
Our Contribution
Solution
Heuristic constraints
Structural knowledge
• Identical queries
• Sub-queries
• Identical clicked URLs
• Same task => tasks sharing
related queries
• Latent
Semi-supervised Structural Learning
13
Our Contribution
Semi-supervised Structural Learning
• Structural inference
– Hierarchical clustering on best links
• Flexibility
• Exact inference exists
14
Experimental Results
plausible explanation of task structure
1 il volo singing tous les visages de l'amour
1.1 french version of album by il volo
1.1.1 french version of album by il volo
1.1.1.1 french version of album by il volo
2 amazon.com international sites
2.1 amazon.com international
3 pottery barn warehouse clearance sale
4 amazon.com phone number
4.1 amazon.com phone number
4.1.1 amazon customer service phone number
4.1.1.1 amazon customer service phone number
5 condo rentals in salter path, n.c.
6 piero barone's 19th birthday plans
6.1 piero barone family
6.1.1 piero barone family
6.2 piero barone's 19th birthday plans
6.2.1 +piero barone's 19th birthday plans
6.2.2 piero barone's 19th birthday plans
6.2.2.1 piero barone singing piove
6.2.2.1.1 piero barone singing piove
16
Publications
1.
2.
3.
4.
5.
6.
7.
8.
9.
Hongning Wang, Anlei Dong, Lihong Li, Yi Chang and Evgeniy Gabrilovich. Joint Relevance and Freshness
Learning From Clickthroughs for News Search. The 2012 World Wide Web Conference (WWW'2012), p579588.
Hongning Wang, ChengXiang Zhai, Anlei Dong and Yi Chang. Content-Aware Click Modeling. The 23rd
International World-Wide Web Conference (WWW'2013) (To Appear)
Hongning Wang, Yang Song, Ming-Wei Chang, Xiaodong He, Ryen White and Wei Chu. Learning to Extract
Cross-Session Search Tasks. The 23rd International World-Wide Web Conference (WWW'2013) (To Appear)
Yang Song, Hao Ma, Hongning Wang and Kuansan Wang. Exploring and Exploiting User Search Behaviors on
Mobile and Tablet Devices to Improve Search Relevance. The 23rd International World-Wide Web Conference
(WWW'2013) (To Appear)
Ryen White, Wei Chu, Ahmed Hassan, Xiaodong He, Yang Song and Hongning Wang. Enhancing Personalized
Search by Mining and Modeling Task Behavior. The 23rd International World-Wide Web Conference
(WWW'2013) (To Appear)
Chi Wang, Hongning Wang, Jialu Liu, Ming Ji, Lu Su, Yuguo Chen, Jiawei Han. On the Detectability of Node
Grouping in Networks. SIAM International Conference on Data Mining (SDM'2013) (To Appear)
Hongbo Deng, Jiawei Han, Hao Li, Heng Ji, Hongning Wang and Yue Lu. Exploring and Inferring User-User
Pseudo-Friendship for Sentiment Analysis with Heterogeneous Networks. SIAM International Conference on
Data Mining (SDM'2013) (To Appear)
Mianwei Zhou, Hongning Wang and Kevin Chen-Chuan Chang. Learning to Rank from Distant Supervision:
Exploiting Noisy Redundancy for Relational Entity Search. The 29th IEEE International Conference on Data
Engineering (ICDE'2013)
Yue Lu, Hongning Wang, ChengXiang Zhai and Dan Roth. Unsupervised Discovery of Opposing Opinion
Networks From Forum Discussions. The 21st ACM International Conference on Information and Knowledge
Management (CIKM'2012), p1642-1646.
Thank you!
• Q&A
7/18/2015
18
User’s Judgment on Relevance and Freshness
• User’s searching behavior
Freshness
v.s.
Relevance
Freshness weight=0.8
R=0.39
F=2.34
Y=1.95
R=1.72
F=2.18
Y=2.01
R=2.41
F=1.76
Y=2.09
User Clicks Are Biased
• Position-bias
– Higher position
More clicks
Not necessarily relevant
Modeling Clicks
=> Decompose relevance-driven
clicks from position-driven clicks
Learning to Extract Search Tasks
• An atomic information need that may result in
one or more queries
An impression
tѱ = 30 minutes
21