310 likes | 318 Views
A Structured Approach to Query Recommendation With Social Annotation Data. 童薇. Outline. Motivation Challenges Approach Experimental Results Conclusions. Outline. Motivation Challenges Approach Experimental Results Conclusions. Motivation. Query Recommendation Help users search
E N D
A Structured Approach to Query Recommendation With Social Annotation Data 童薇
Outline • Motivation • Challenges • Approach • Experimental Results • Conclusions
Outline • Motivation • Challenges • Approach • Experimental Results • Conclusions
Motivation • Query Recommendation • Help users search • Improve the usability of search engines
Recommend what? • Existing Work • Search interests: stick to user’s search intent • Anything Missing? • Exploratory Interests: some vague or delitescent interests • Unaware of until users are faced with one • May be provoked within a search session equivalent or highly related queries apple iphone smartphones nexus one apple products ipod touch mobileme
Is the existence of exploratory interest commonand significant? • Identified from search user behavior analysis • Make use of one-week log search data • Verified by Statistical Tests(Log-likehood Ratio Test) • Analyze the causality between initial queries and consequ-ent queries • Results • In 80.9% of cases: Clicks on search results indeed affect the formulation of the next queries • In 43.1% of cases: Users would issue different next queries if they clicked on different results
Two different heading directions of Query Recommendation • Emphasize search interests: • Help users easily refine their queries and find what they • need more quickly • Enhance the “search-click-leave” behavior equivalent or highly related queries apple iphone • Focus on exploratory interests: • Attract more user clicks and make search and browse more closely integrated • Increase the staying time and advertisement revenue nexus one Recommend queries to satisfy both search and exploratory interests of users simultaneously ipod touch mobileme
Outline • Motivation • Challenges • Our Approach • Experimental Results • Conclusions
Challenges • To leverage what kind of data resource? Search logs: Interactions between search users and search engines Social annotation data: Keywords according to the content of the pages “wisdom of crowds”
Challenges • To leverage what kind of data resource? • How to present such recommendations to users? Refine queries Stimulate exploratory interests A Structured Approach to Query Recommendation With Social Annotation Data
Outline • Motivation • Challenges • Approach • Experimental Results • Conclusions
Approach • Query Relation Graph • A one-mode graph with the nodes representing all the unique queries and the edges capturing relationships between queries • Structured Query Recommendation • Ranking using Expected Hitting Time • Clustering with Modularity • Labeling each cluster with social tags
Query Relation Graph • Query Formulation Model
Query Relation Graph • Query Formulation Model 2 3 5 3 4 1 2
Query Relation Graph • Query Formulation Model • Construction of Query Relation Graph 2 3 3 2 5 1 3 3 4 1 2 1 1 2
Ranking with Hitting Time • Apply a Markov random walk on the graph • Employ hitting time as a measure to rank queries • The expected number of steps before node j is visited starting from node i • The hiting time T is the first time that the random walk is at node j from the start node i: • The mean hitting time h(j|i) is the expectation of T under the condition
Ranking with Hitting Time • Apply a Markov random walk on the graph • Employ hitting time as a measure to rank queries • The expected number of steps before node j is visited starting from node i • Satisfies the following linear system
Clustering with Modularity • Group the top k recommendations into clusters • It is natural to apply a graph clustering approach • Modularity function Note: In a network in which edges fall between vertices without regard for the communities they belong to ,we would have
Clustering with Modularity • Group the top k recommendations into clusters • It is natural to apply a graph clustering approach • Modularity function • Employ the fast unfolding algorithm to perform clustering
Clustering with Modularity • Group the top k recommendations into clusters • It is natural to apply a graph clustering approach • Modularity function • Employ the fast unfolding algorithm to perform clustering • Label each cluster explicitly with social tags The expected tag distribution given a query: The expected tag distribution under a cluster:
Outline • Motivation • Challenges • Approach • Experimental Results • Conclusions
Experimental Results • Data set • Query Logs: Spring 2006 Data Asset (Microsoft Research) • 15 million records (from US users) sampled over one month in May, 2006 • 2.7 million unique queries and 4.2 million unique URLs • Social Annotation Data: Delicious data • Over 167 million taggings sampled during October and November, 2008 • 0.83 million unique users, 57.8 unique URLs and 5.9 million unique tags • Query Relation Graph: 538, 547 query nodes • Baseline Methods • BiHit: Hitting Time approach based on query logs (Mei et al. CIKM ’08) • TriList: list-based approach to query recommendation considering both search and exploratory interests • TriStrucutre: Our approach
Examples of Recommendation Results Query = espn
Examples of Recommendation Results Query = 24
Manual Evaluation • Comparison based on users’click behavior • A label tool to simulate the real search scenario • Label how likelihood the user would like to click (6-point scale) • Randomly sampled 300 queries, 9 human judges
Experimental Results (cont.) • Overall Performance non-zero label score ➡ click Clicked Recommendation Number (CRN) Clicked Recommendation Score (CRS) Total Recommendation Score (TRS) Click Performance Comparison Distributions of Labeled Score over Recommendations
Experimental Results (cont.) • How Structure Helps • How the structured approach affects users’ click willingness • Click Entropy The Average Click Entropy over Queries under the TriList and TriStructure Methods.
Experimental Results (cont.) • How Structure Helps • How the structured approach affects users’ click patterns • Label Score Correlation Correlation between the Average Label Scores on Same Recommendations for Queries.
Outline • Motivation • Challenges • Approach • Experimental Results • Conclusions
Conclusions • Recommend queries in a structured way for better satisfying both search and exploratory interests of users • Introduce the social annotation data as an important resource for recommendation • Better satisfy users interests and significantly enhance user’s click behavior on recommendations • Future work • Trade-off between diversity and concentration • Tag propagation