Keyword Generation for Search Engine Advertising

Keyword Generation for Search Engine Advertising

Keyword Generation for Search Engine Advertising Amruta Joshi*, Yahoo! Research Rajeev Motwani, Stanford University * This work was done at Stanford 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 1 Search Results Sponsore d Search Results 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 2 Long Tail Frequency in query-logs Expensive, high frequency keywords Target inexpensive, low frequency keywords instead

Queries 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 3 Keyword Pricing 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 4 Pick the right keywords Advantages Keywords should be

more focused audience lesser competition, easier to get #1 position cost-effective alternative Highly Relevant to base query Nonobviousness to guess from the base query E.g.: hawaii vacation $3 kona holidays $0.11 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 5 Objective To generate, with good precision and recall, a large number of keywords that are relevant to the input word, yet nonobvious in nature. 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 6

Whos doing all this? Large Advertisers SEO companies and small start-ups manage advertising profiles Eg: www.adchemy.com, www.wordtracker.com, http://www.globalpromoter.com Eventually every advertiser is interested in optimizing his portfolio 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 7 Other Techniques Meta-tag Spidering: Extract Keyword & Description tags from top

search hits Example of meta-tags for query hawaii travel Relevant: hawaii travel, hawaii vacation, hawaiian islands, hawaii tourism Off-topic: hawaii homes, moving to hawaii, hawaii living, hawaii news, living in hawaii, hawaii products, Irrelevant: sovereignty, volcanoes, sports, music 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 8 Other Techniques Proximity-based tools Pick phrases in the proximity of given word e.g.: family hawaii vacations, discount hawaii vacations

Query log Mining Suggest popular queries containing seed keywords 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 9 Other Techniques Advertiser log mining or Query Cooccurrence based mining Exploits co-occurrence in advertiser keyword search logs Increase competition! 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 10 Directed Relevance Relationships

Word A strongly suggests word B, but the reverse may not hold true A x B B y A xy Example: eurail 18 December 2006 25 railways railways Amruta Joshi and Rajeev Motwani, Stanford University 2

eurail 11 Building Context Characteristic Document Build context of the term using terms found in the proximity of seed term in the top 50 hits from search engine for that term europe europe 18 December 2006 . Search Engine Amruta Joshi and Rajeev Motwani, Stanford University . C 12 Building the Graph

TermsNet Nodes = terms Edges = directed relevance relationships Weights = strength of directed relationship, i.e., the frequency of destination term in characteristic document of source term 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 13 TermsNet railways 25 eurail 32 14 C euro 30 europe . 15 C

maps C C C 19 atlas schengen C C 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 14 Ranking Suggestions Quality Score Incorporates Edge-weights Normalization for common words x

wx,q q Quality Q(x, q) = wx,q / (1+log (1+wx,i)) where each i is an outneighbor of x 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 15 Ratings Relevance Indicates Relevance of suggested keyword to seed word Given by human editors e.g.: For query flights Relevance (flights, cathay pacific) = 1 Relevance (flights, cheap flight) = 1

Relevance (flights, magazines) = 0 Nonobviousness Indicates nonobviousness of suggested keyword relative to seed word Calculated as: If No base query word/stem present in suggested keyword, Nonobviousness = 1, else = 0 e.g.: For query flights Relevance (flights, cathay pacific) = 1 Relevance (flights, cheap flight) = 0 Relevance (flights, magazines) = 1 Used standard Porter stemmer for automating this rating 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 16 Evaluation

Evaluation Measures Average Precision: Ratio of number of relevant keywords retrieved to number of keywords retrieved. Indicates quality of results Average Recall The proportion of relevant keywords that are retrieved, out of all relevant keywords available. For our expts Recall (Ti) = # retrieved by Ti / # retrieved by (T1 U T2 UU Tn) Average Nonobviousness Average of all nonobviousness ratings of suggested keywords 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 17

Output for query flights Co-occurrence Based Query Log Meta-Tag Spidering Meta-Crawler Lists Query-log Mining TermsNet Airfare airfares airlines Cyprus goa flys holidays trains aer aeroflot aeromexico aircanada alicante bwia heathrow icelandair bookings

Consolidator Flights cheap flights airline flights cheap airline flights cheap international flights flights to europe business class flights flights new york australia flights cheap flights to europe cheap flights to orlando cheap flights las vegas track flights flights florida flights europe las flights cheap flights to australia real time flight arrivals airfare flights flight map delays cruises us flight arrivals flight arrivals

state map flight arrival flight cancellation s arrival times arrival delays flight departure vacation packages street map air travel airline discount tickets airline fares airline tickets airline tickets under 100 american airlines bargain flights bmibaby british airways british airways flights british airways home page british airways timetable british midland budget airline flight

cheap flight las vegas flight flight tracker flight to orlando flight to london flight to new york airline flight flight to los angeles flight 93 flight to fort lauderdale light of the phoenix flight to honolulu flight to chicago flight to miami cheap flights airline flights air newzealand flight prices bmibaby globespan low cost airlines united airlines airlineconsolidators charter flights airfare flight reservations cathay pacific british midland

airways discount airfare flight tickets jet2 travelocity 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 18 Avg. Precision, Recall, Nonobviousness 1.2 1 1 1 1 0.94 0.913793 0.788043 0.8 0.744681

0.636364 0.6 0.58 0.559322 0.479675 0.4 0.254 0.2 0.118 0 0 Query Cooccurrence Avg. Precision 0.201 0.196 Query-Log Mining 18 December 2006 Avg. Recall

0.094 0 Meta-Tag Spidering MetaCrawler Query Logs Lists with recency Amruta Joshi and Rajeev Motwani, Stanford University TermsNet Avg. Nonobviousness 19 Evaluation Measures F-measures Measure of overall performance Harmonic mean of

F(PR) Avg. Precision & Avg. Recall F(RN) Avg. Recall & Avg. Nonobviousness F(PN) Avg. Precision & Avg. Nonobviousness F(PRN) Avg. Precision, Avg. Recall & Avg. Nonobviousness 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 20 F-Measures 0.45 0.4 0.35 0.3 0.25 0.2 0.15 0.1 0.05 F(PR) 0 F(RN) Query Cooccurrence Query-Log Mining

Meta-Tag Spidering MetaCrawler Lists Query Logs with recency TermsNet F(PN) F(PRN) 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 21 Quality of Suggestions over different intervals of ranked results Avg. Precision & Avg. Nonobviousness over Number of Top Suggestions 1 0.8 0.6 0.4

Avg. Nonobviousness 0.2 Avg. Precision 0 0 100 200 300 400 Top n keyw ord suggestions 500 600 Figure 2: Quality of keywords over different ranked intervals 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 22 Future Directions

Incorporate keyword frequency in ranking suggestions Incorporate keyword pricing information in ranking suggestions Applications to other domains Find related movies, papers, people 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 23 Thank You! Questions? [email protected] 18 December 2006 Amruta Joshi and Rajeev Motwani, Stanford University 24

Recently Viewed Presentations

  • LEARN Information - Oklahoma Office of Management and ...

    LEARN Information - Oklahoma Office of Management and ...

    ODOT Learn Center. DHS Learn Center. ODOC Learn Center. Group Administrators. ... This is their chance to "sign off" on the system and make any last minute changes that might help them in the future. ... That will depend on...
  • FITNESS REPORT CDR Brenda Metzler, NC, USN LT

    FITNESS REPORT CDR Brenda Metzler, NC, USN LT

    Train and prepare for deployment in support of operational and peacetime support missions. Support medical and dental needs of Naval Hospital Bremerton and Navy Medicine West and provide expert healthcare support to Reserve Component Commands Northwest and Southwest. *HQ Standard...
  • International Helicopter Safety Team

    International Helicopter Safety Team

    Goal To reduce helicopter accidents by 80% By 2016 Executive Committee IHST JHSAT JHSIT Subcommittees Subcommittees Secretariat JHSAT - Joint Helicopter Safety Advisory Team JHSIT - Joint Helicopter Safety Implementation Team Influence Safety Enhancements - Worldwide Data Analysis Set Safety...
  • Marcus Tullius Cicero

    Marcus Tullius Cicero

    This made Cicero the first in his family to serve in the Roman Senate. Ergo he was a "novus homo". His quaestorship in Sicily proved to be successful when the Sicilians begged Cicero to prosecute their governor Verres for extortion...
  • REGISTRATION - tgct.gov.in

    REGISTRATION - tgct.gov.in

    Registration -Who. Supplies > INR 20L ... How to Login in GST Portal * GSTN Provisional ID and Temporary password.(All the Existing Registered dealers of Telangana will receive an E-Mail with GSTN Provisional ID and Temporary password. Mandatory fields to...
  • Introduction to Maya - James Tedder

    Introduction to Maya - James Tedder

    Modelling techniques, constraints and 3D development software. ... Real time:Typically using a Graphics processing unit (GPU), with video games the most notable users. The 3D image is created in real time on the fly. 3D development software.
  • PowerPoint-Präsentation

    PowerPoint-Präsentation

    R (review) Das Gelesene wiederholen 3. Gliederung erstellen Aufbau der Arbeit festhalten: chronologisch, Ursache-Wirkung, vom Allgemeinen zum Besonderen, vergleichend oder gegenüberstellend, induktiv (vom Beispiel zur Theorie), deduktiv (von der Theorie zum Beispiel) Inhalt der einzelnen Kapitel grob festhalten Vorläufige Gliederung...
  • Agenda - GSSD Blogs

    Agenda - GSSD Blogs

    VB-MAPP (Verbal Behavior Milestones Assessment and Placement Program) Barriers assessment . PEAK (The PEAK: Relational Training System) evaluation and curriculum guide for basic and advanced language skills