Evaluation Web Search and Mining Lecture 9: Evaluation
Evaluation Lecture 9: Evaluation Web Search and Mining
Evaluation This lecture How do we know if our results are good? Evaluating a search engine Benchmarks Precision and recall Results summaries. Making our good results usable to a user
Evaluation 2 This lecture ▪ How do we know if our results are good? ▪ Evaluating a search engine ▪ Benchmarks ▪ Precision and recall ▪ Results summaries: ▪ Making our good results usable to a user
Evaluation Measures easures for a search engine How fast does it index Number of documents/hour (Average document size) How fast does it search Latency as a function of index size Expressiveness of query language ability to express complex information needs Speed on complex queries Uncluttered U Is it free?
Evaluation 4 Measures for a search engine ▪ How fast does it index ▪ Number of documents/hour ▪ (Average document size) ▪ How fast does it search ▪ Latency as a function of index size ▪ Expressiveness of query language ▪ Ability to express complex information needs ▪ Speed on complex queries ▪ Uncluttered UI ▪ Is it free? Measures
Evaluation Measures easures for a search engine All of the preceding criteria are measurable: we can quantify speed /size we can make expressiveness precise The key measure: user happiness What is this? Speed of response size of index are factors But blindingly fast, useless answers wont make a user happy Need a way of quantifying user happiness
Evaluation 5 Measures for a search engine ▪ All of the preceding criteria are measurable: we can quantify speed/size ▪ we can make expressiveness precise ▪ The key measure: user happiness ▪ What is this? ▪ Speed of response/size of index are factors ▪ But blindingly fast, useless answers won’t make a user happy ▪ Need a way of quantifying user happiness Measures
Evaluation Measures easuring user happiness Issue: who is the user we are trying to make happy? Depends on the setting Web engine User finds what they want and return to the engine Can measure rate of return users a User completes their task -search as a means, not end SeeRussellhttp://dmrussellgooglepages.com/jcdl-talk- June-2007-short. pdf e Commerce site: user finds what they want and buy Is it the end-user, or the e Commerce site, whose happiness we measure? Measure time to purchase, or fraction of searchers who become buyers?
Evaluation 6 Measuring user happiness ▪ Issue: who is the user we are trying to make happy? ▪ Depends on the setting ▪ Web engine: ▪ User finds what they want and return to the engine ▪ Can measure rate of return users ▪ User completes their task – search as a means, not end ▪ See Russell http://dmrussell.googlepages.com/JCDL-talkJune-2007-short.pdf ▪ eCommerce site: user finds what they want and buy ▪ Is it the end-user, or the eCommerce site, whose happiness we measure? ▪ Measure time to purchase, or fraction of searchers who become buyers? Measures
Evaluation Measures easuring user happiness Enterprise( company/govt/academic): Care about user productivity How much time do my users save when looking for information lany other criteria having to do with breadth of access secure access, etc
Evaluation 7 Measuring user happiness ▪ Enterprise (company/govt/academic): Care about “user productivity” ▪ How much time do my users save when looking for information? ▪ Many other criteria having to do with breadth of access, secure access, etc. Measures
Evaluation Measures Happiness: elusive to measure Most common proxy: relevance of search results But how do you measure relevance? We will detail a methodology here then examine Its IsSues Relevance measurement requires 3 elements: 1. a benchmark document collection 2. a benchmark suite of queries 3. a usually binary assessment of either relevant or Nonrelevant for each query and each document Some work on more-than- binary, but not the standard 8
Evaluation 8 Happiness: elusive to measure ▪ Most common proxy: relevance of search results ▪ But how do you measure relevance? ▪ We will detail a methodology here, then examine its issues ▪ Relevance measurement requires 3 elements: 1. A benchmark document collection 2. A benchmark suite of queries 3. A usually binary assessment of either Relevant or Nonrelevant for each query and each document ▪ Some work on more-than-binary, but not the standard Measures
Evaluation Measures Evaluating an iR system Note: the information need is translated into a quer Relevance is assessed relative to the information need not the query E. g. Information need /'m looking for information on whether drinking red wine is more effective at reducing your risk of heart attacks than white wine Query: wine red white heart attack effective You evaluate whether the doc addresses the information need not whether it has these words
Evaluation 9 Evaluating an IR system ▪ Note: the information need is translated into a query ▪ Relevance is assessed relative to the information need not the query ▪ E.g., Information need: I'm looking for information on whether drinking red wine is more effective at reducing your risk of heart attacks than white wine. ▪ Query: wine red white heart attack effective ▪ You evaluate whether the doc addresses the information need, not whether it has these words Measures
Evaluation Benchmarks Standard relevance benchmarks TREC -National Institute of standards and Technology nist) has run a large ir test bed for many years Reuters and other benchmark doc collections used Retrieval tasks" specified sometimes as queries Human experts mark, for each query and for each doc, Relevant or nonrelevant or at least for subset of docs that some system returned for that query
Evaluation 10 Standard relevance benchmarks ▪ TREC - National Institute of Standards and Technology (NIST) has run a large IR test bed for many years ▪ Reuters and other benchmark doc collections used ▪ “Retrieval tasks” specified ▪ sometimes as queries ▪ Human experts mark, for each query and for each doc, Relevant or Nonrelevant ▪ or at least for subset of docs that some system returned for that query Benchmarks