Eugene Agichtein g g Emory University Eugene Agichtein RuSSIR - PowerPoint PPT Presentation

Modeling User Behavior and Interactions Lecture 1: Modeling Searcher Behavior Eugene Agichtein g g Emory University Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions Emory University

Overview of the Course • Lecture 1: Modeling searcher behavior • Lecture 2: Interpreting behavior � relevance • Lecture 3: Using behavior data � ranking • Lecture 4: Personalizing search with behavior • Lecture 5: Search user interfaces Lecture 5: Search user interfaces Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 2 Emory University

Lecture 1: Models of Search Behavior • Understanding user behavior at micro-, meso-, and macro- levels macro levels • Theoretical models of information seeking Theoretical models of information seeking • Web search behavior: Web search behavior: – Levels of detail – Search Intent – Variations in web searcher behavior – Click models Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 3 Emory University

Levels of Understanding User Behavior [Daniel M. Russell, 2007] [ ] • Micro (eye tracking): lowest level of detail, milliseconds , • Meso (field studies): mid-level, minutes to days • Macro (session analysis): • Macro (session analysis): millions of observations, days to months Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 4 Emory University

Models of Information Seeking • “Information-seeking … includes recognizing … the information g g problem, establishing a plan of search, conducting the search, evaluating the results and evaluating the results, and … iterating through the process.”- Marchionini, 1989 – Query formulation – Action (query) – Review results – Refine query Adapted from: M. Hearst, SUI, 2009 Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 5 Emory University

Key Concept: Relevance • Intuitively well understood – same perception globally – “y’know” ti l b ll “ ’k ” – a “to” and context always present • Relevance: R l – a relation between objects P & Q along property R – may also include a measure S of the strength of l i l d S f th t th f connection • Example: topical relevance (document on the • Example: topical relevance (document on the correct topic) Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 6 Emory University

Relevance clues • What makes information or information objects relevant? What do people look for in order to infer relevant? What do people look for in order to infer relevance? – Topicality (subject relevance) T i li ( bj l ) – Extrinsic (task-, goal- specific) • Information Science “clues research”: – uncover and classify attributes or criteria used for making relevance inferences Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 7 Emory University

IR Relevance Models • All IR and information seeking models have relevance at their base relevance at their base • Traditional IR model has most simplified (topic) version of relevance ( topical ) version of relevance ( topical ) – Enough to make progress • Variety of integrative models have been • Variety of integrative models have been proposed – more complex models = increased challenge to more complex models = increased challenge to evaluation and implementation in practice Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 8 Emory University

Cognitive Model of Information Seeking • Static Info Need – Goal G l – Execution – Evaluation Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 9 Emory University

Relevance dynamics • Do relevance inferences and criteria change over time for the same user and task and if so how? time for the same user and task, and if so, how? • As user progresses through stages of a task: – the user’s cognitive state changes – the task changes as well Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 10 Emory University

Dynamic “Berry Picking” Model • Information needs change during interactions [Bates, 1989] M.J. Bates. The design of browsing and berrypicking techniques for the on- li line search interface. Online Review , 13(5):407–431, 1989. h i f O li i 3( ) 0 3 989 Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 11 Emory University

Information Foraging Theory Goal: maximize rate of information gain. Patches of information � websites Basic Problem: should I continue in the current patch continue in the current patch or look for another patch? Expected gain from continuing in Expected gain from continuing in current patch, how long to continue searching in that patch searching in that patch Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 12 Emory University

Hotel Search Goal: Find cheapest 4-star h 4 hotel in Paris. Step 1: pick hotel search site search site Step 2: scan list Step 2: scan list Step 3: goto 1 Step 3: goto 1 Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 13 Emory University

Example: Hotel Search (cont’d) Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 14 Emory University

- Charnov’s Marginal Value Theorem Diminishing Returns Curve; 80% of users don’t scan past the 3 rd page of search results R* = steepest slope from origin = tangent from origin If t b is low, then people tend to switch more easily. (web snacking) Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 15 Emory University

Browsing vs. Search • Recognition over recall (I know it when I see it) • Browsing hierarchies/facets more effective than h h /f ff h querying Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 16 Emory University

Orienteering • Searcher issues a quick, imprecise to get to approximately the right information space region approximately the right information space region • Searchers follow known paths that require small steps that move them closer to their goal h h l h l • Expert searchers starting to issue longer queries Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 17 Emory University

Information Scent for Navigation • Examine clues where to find useful information Search results listings must provide the user with clues about which h i h l b hi h results to click Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 18 Emory University

Summary of Models • Many cognitive models proposed • Classical IR Systems research mainly uses the simplest form of relevance ( topicality ) • Open questions: – How people recognize other kinds of relevance – How people recognize other kinds of relevance – How to incorporating other forms of relevance (e.g., user goals/needs/tasks) into IR systems user goals/needs/tasks) into IR systems Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 19 Emory University

Lecture 1: Models of Search Behavior • Understanding user behavior at micro-, meso-, and macro- levels macro levels � Theoretical models of information seeking � Theoretical models of information seeking � Web search behavior: � Web search behavior: – Levels of detail – Search Intent – Variations in web searcher behavior – Click models Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 20 Emory University

Web Searcher Behavior • Meso-level: query, intent, and session characteristics characteristics • Micro-level: how searchers interact with result pages • Macro-level: patterns trends and interests Macro level: patterns, trends, and interests Eugene Agichtein RuSSIR 2009: Modeling User Behavior and Interactions 21 Emory University

Web Search Architecture [from Baeza-Yates and Jones, WWW 2008 tutorial] [ , ] Example centralized parallel architecture Web Crawlers RuSSIR 2009: Modeling User Behavior and Interactions Eugene Agichtein, Emory University, IR Lab

Information Retrieval Process (User view) Source Selection Resource Query Query Formulation Ranked List Search Selection Documents query reformulation, vocabulary learning, relevance feedback Examination E i ti Documents source reselection Delivery Eugene Agichtein, Emory RuSSIR 2009: Modeling User Behavior and Interactions 23 University, IR Lab

Some Key Challenges for Web Search • Query interpretation (infer intent) • Ranking (high dimensionality) • Evaluation (system improvement) Evaluation (system improvement) • Result presentation (information visualization) l i (i f i i li i ) Eugene Agichtein, Emory RuSSIR 2009: Modeling User Behavior and Interactions 24 University, IR Lab

Intent Classes (top level only) [from SIGIR 2008 Tutorial, Baeza-Yates and Jones] User intent taxonomy (Broder 2002) – Informational – want to learn about something (~40% / 65%) History nonya food – Navigational – want to go to that page (~25% / 15%) Singapore Airlines – Transactional – want to do something (web-mediated) (~35% / 20%) Jakarta weather • Access a serviceDownloads Access a serviceDownloads Kalimantan satellite images • Shop Nikon Finepix – Gray areas y • Find a good hub Car rental Kuala Lumpur • Exploratory search “see what’s there” Eugene Agichtein, Emory RuSSIR 2009: Modeling User Behavior and Interactions 25 University, IR Lab