How do users interact with search engines? What can we learn from this behavior? How can we make search engines better? How do we measure quality of search results and what are the key metrics? Do you even measure the quality of your search? Let's take a walk standing on the shoulders of giants like Google, Yahoo or Yandex and learn about the recent advances in search research.
2. About me
● researcher and teacher at
Slovak University of Technology in
Bratislava
● developer @ synopsi.tv, searchd.co
● co-owner of minio, s.r.o.
○ otvorenezmluvy.sk, govdata.sk
3. Search
as seen by developers
{
"query": {
"query_string": {
"query": "elasticsearch book"
}
}
}
return response.hits.hits
4. Search
as experienced by users
query: elasticsarch
Typo in query.
No results.
query: elasticsearch
Too many hits.
Not relevant.
query: elasticsearch book
Click!
Success! Or?
7. Accurately interpreting clickthrough
data as implicit feedback
Thorsten Joachims, Laura Granka, Bing Pan, Helene Hembrooke, and Geri
Gay. Accurately interpreting clickthrough data as implicit feedback. In
Proceedings of the 28th annual international ACM SIGIR conference on
Research and development in Information retrieval, SIGIR ’05, pages 154–161,
New York, NY, USA, 2005. ACM.
9. Search quality metrics
● Mean Average Precision @ N
○ probability of target result being in top N items
● Mean Reciprocal Rank
○ 1 / rank of target result
● Normalized Discounted Cumulative Gain
● Expected Reciprocal Rank
10. Search KPIs
● CTR trend
● # of queries w/o results or clicks
● # of searches per session
● Search engine latency
12. Optimizing search engines using
clickthrough data
Thorsten Joachims. Optimizing search engines using clickthrough data. In
Proceedings of the eighth ACM SIGKDD international conference on
Knowledge discovery and data mining, KDD ’02, pages 133–142, New York,
NY, USA, 2002. ACM.
14. Query chains: learning to rank from
implicit feedback
Filip Radlinski and Thorsten
Joachims. Query chains: learning
to rank from implicit feedback. In
KDD ’05: Proceeding of the eleventh
ACM SIGKDD international
conference on Knowledge discovery
in data mining, pages 239–248,
New York, NY, USA, 2005. ACM.
15. Fighting Search Engine Amnesia:
Reranking Repeated Results
Milad Shokouhi, Ryen W. White, Paul Bennett, and Filip Radlinski. Fighting
search engine amnesia: reranking repeated results. In Proceedings of the
36th international ACM SIGIR conference on Research and development in
information retrieval, SIGIR ’13, pages 273–282, New York, NY, USA, 2013.
ACM.
In this paper, we observed that the same results are often shown to
users multiple times during search sessions. We showed that there are
a number of effects at play, which can be leveraged to improve information
retrieval performance. In particular, previously skipped results are much
less likely to be clicked, and previously clicked results may or may not
be re-clicked depending on other factors of the session.
21. searchd.co
Search Analytics
● Identify and fix key search problems
● KPIs for site search
● Actionable tips for search tuning
● Easy setup
a. Add our hosted JavaScript
b. Annotate search results with HTML5 tags
c. Done.
● Currently in private beta
22. Bad search experience is a lost
opportunity. Let's fix it.
searchd.co
Search Analytics
www.searchd.co
info@searchd.co