Computational User Intent Modeling Hongning Wang March 6

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] 11/4/2020 2

Understanding User Intent is Important • “Apple Company” @ Oct. 4, 2011 Release of i. Phone 4 S

Understanding User Intent is Important • “Apple Company” @ Oct. 5, 2011 Steve Jobs passed away Release of i. Phone 4 S

Relevance v. s. Freshness • Relevance – Topical relatedness – Metric: tf*idf, BM 25, 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 S 1 5/29/2012 5: 26 bank of america 5/29/2012 S 2 5/29/2012 11: 11 macy's sale 5/29/2012 11: 12 sas shoes 5/30/2012 S 1 5/30/2012 10: 19 credit union 5/30/2012 S 2 5/30/2012 12: 25 6 pm. com 5/30/2012 12: 49 coupon for 6 pm 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 2 amazon. com international sites 2. 1 amazon. com international 3 pottery barn warehouse clearance sale 4 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 19 th birthday plans 6. 1 piero barone family 6. 1. 1 piero barone family 6. 2 piero barone's 19 th birthday plans 6. 2. 1 +piero barone's 19 th 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), p 579 -588. Hongning Wang, Cheng. Xiang Zhai, Anlei Dong and Yi Chang. Content-Aware Click Modeling. The 23 rd 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 23 rd 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 23 rd 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 23 rd 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 29 th IEEE International Conference on Data Engineering (ICDE'2013) Yue Lu, Hongning Wang, Cheng. Xiang Zhai and Dan Roth. Unsupervised Discovery of Opposing Opinion Networks From Forum Discussions. The 21 st ACM International Conference on Information and Knowledge Management (CIKM'2012), p 1642 -1646.

Thank you! • Q&A 11/4/2020 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 ÞMore clicks ÞNot 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