2019 Tech SEO Boost Dawn Anderson Contextual Recommender Search
11 likes962 views
The document discusses the evolution of search technology, highlighting a shift from traditional query-based searches to more proactive and personalized search experiences, as exemplified by Google Discover. It emphasizes the challenges in understanding user intent due to the complexity of language and the necessity for search engines to adapt to changing user needs over time. Three significant shifts are identified: from answers to journeys, from queries to queryless interactions, and from text-based to visual information.
![[Four candles] + [fork handles]
interest over time](https://image.slidesharecdn.com/2019techseoboostppttemplate-191205195642/85/2019-Tech-SEO-Boost-Dawn-Anderson-Contextual-Recommender-Search-68-320.jpg)
![• Broder, A., 2002, September. A taxonomy of web search. In ACM Sigir forum (Vol. 36, No.
2, pp. 3-10). ACM.
• Chuklin, A., Severyn, A., Trippas, J., Alfonseca, E., Silen, H. and Spina, D., 2018. Prosody
Modifications for Question-Answering in Voice-Only Settings. arXiv preprint
arXiv:1806.03957.
• HigherVisibility. 2018. How Popular is Voice Search? | HigherVisibility. [ONLINE] Available
at: https://www.highervisibility.com/blog/how-popular-is-voice-search/
• Filippova, K., Alfonseca, E., Colmenares, C.A., Kaiser, L. and Vinyals, O., 2015. Sentence
compression by deletion with lstms. In Proceedings of the 2015 Conference on Empirical
Methods in Natural Language Processing (pp. 360-368).
• Filippova, K. and Alfonseca, E., 2015. Fast k-best sentence compression. arXiv preprint
arXiv:1510.08418.
• Google Developers. 2018. Content-based Actions | Actions on Google | Google
Developers. [ONLINE] Available at: https://developers.google.com/actions/content-
actions/. [Accessed 18 June 2018]](https://image.slidesharecdn.com/2019techseoboostppttemplate-191205195642/85/2019-Tech-SEO-Boost-Dawn-Anderson-Contextual-Recommender-Search-182-320.jpg)
![References
Radinsky, K., Svore, K.M., Dumais, S.T., Shokouhi, M., Teevan, J., Bocharov, A. and Horvitz, E.,
2013. Behavioral dynamics on the web: Learning, modeling, and prediction. ACM Transactions on
Information Systems (TOIS), 31(3), p.16
Sadikov, E., Madhavan, J. and Halevy, A., Google LLC, 2013. Clustering query refinements by
inferred user intent. U.S. Patent 8,423,538.
Official Google Webmaster Central Blog. 2019. Official Google Webmaster Central Blog: Rolling out
mobile-first indexing . [ONLINE] Available at: https://webmasters.googleblog.com/2018/03/rolling-out-
mobile-first-indexing.html. [Accessed 25 September 2019].
Zhou, S., Cheng, K. and Men, L., 2017, April. The survey of large-scale query classification. In AIP
Conference Proceedings (Vol. 1834, No. 1, p. 040045). AIP Publishing.](https://image.slidesharecdn.com/2019techseoboostppttemplate-191205195642/85/2019-Tech-SEO-Boost-Dawn-Anderson-Contextual-Recommender-Search-183-320.jpg)
![References
Search Engine Land. 2019. Starting July 1, all new sites will be indexed using Google's mobile-first indexing
- Search Engine Land. [ONLINE] Available at: https://searchengineland.com/july-1-new-sites-will-be-
indexed-using-googles-mobile-first-indexing-317490. [Accessed 25 September 2019].
Teevan, J., Dumais, S.T. and Horvitz, E., 2005, August. Personalizing search via automated analysis of
interests and activities. In Proceedings of the 28th annual international ACM SIGIR conference on Research
and development in information retrieval (pp. 449-456). ACM.
Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R. and Deng, L., 2016. MS MARCO: A
Human-Generated MAchine Reading COmprehension Dataset.](https://image.slidesharecdn.com/2019techseoboostppttemplate-191205195642/85/2019-Tech-SEO-Boost-Dawn-Anderson-Contextual-Recommender-Search-184-320.jpg)
2019 Tech SEO Boost Dawn Anderson Contextual Recommender Search
- 1. Dawn Anderson | @dawnieando | #TechSEOBoost The rise of predictive, proactive search TechSEO Boost 2019 The User is The Query
- 2. Dawn Anderson | @dawnieando | #TechSEOBoost “Today you are you! That is truer than true! There is no one alive who is you-er than you!” (Dr Seuss)
- 3. Dawn Anderson | @dawnieando | #TechSEOBoost Said Dr Seuss… and Google
- 4. When introducing Google Feed (now Discover)
- 5. Dawn Anderson | @dawnieando | #TechSEOBoost Today’s Topic: The User is the Query
- 6. Dawn Anderson | @dawnieando | #TechSEOBoost
- 7. Dawn Anderson | @dawnieando | #TechSEOBoost Also… Meet Bert and Ted
- 8. Dawn Anderson | @dawnieando | #TechSEOBoost There’s a problem with queries, content & users too
- 9. “In 1998 the web consisted of just 25 million pages…” (Ben Gomez, Google, 2018)
- 10. “… That’s roughly the equivalent number of those in a small library” (Ben Gomez, Google, 2018)
- 11. In 2019… we know the web is huge… billions of web pages (Netcraft, 2019)
- 12. App usage is huge too - By 2018 – App Store has 20 million registered developers. (Techcrunch, 2018)
- 13. 42% of the global population use social media (Emarsys, 2019)
- 14. We are competing with programmatic solutions spraying content & information EVERYWHERE
- 15. Over-choice: Too much choice often has negative impacts
- 16. Almost 98% of visits are people window shopping Average ecommerce conversion +/- 2% (Monetate)
- 17. Despite this… users are still seeking even more information
- 18. The number of Google searches increases year on year (Internetlivestat, 2018, curation from various sources)
- 19. Dawn Anderson | @dawnieando | #TechSEOBoost 15% of queries every day are new (Google)
- 20. Humans forage (like bears) all over the place seeking information… we are informavores
- 21. Dawn Anderson | @dawnieando | #TechSEOBoost Researching ALL THE THINGS… before making final decisions
- 22. We have become very good at filtering out things which are NOT interesting enough (8 second filter)
- 23. Dawn Anderson | @dawnieando | #TechSEOBoost It’s NOT a short attention span thing
- 24. Otherwise we would not binge on ‘Stranger Things’
- 25. Dawn Anderson | @dawnieando | #TechSEOBoost This is cognitive load management & information filtering
- 26. Dawn Anderson | @dawnieando | #TechSEOBoost AT THE SAME TIME words are problematic. Ambiguous… polysemous… synonymous
- 27. Often words have multiple meanings. Like “like” can be 5 possible parts of speech (POS)
- 28. Spoken word can be worse. Like “four candles” and “fork handles”
- 29. Which does not bode well for the likes of conversational search
- 30. In query understanding sometimes users don’t know what they want either
- 31. Sometimes exactly the same users express an information need in a different way
- 32. Sometimes different users use lots of different ways to mean exactly the same thing
- 33. 'The Vocabulary Problem’ Furnas, G.W., Landauer, T.K., Gomez, L.M. and Dumais, S.T., 1987. The vocabulary problem in human- system communication. Communications of the ACM, 30(11), pp.964-971. 1987
- 35. One of the inventors of ‘Latent Semantic Indexing’, created to solve ‘The Vocabulary Problem’ whilst researching at Bellcore (1990)
- 36. BTW… No-one said LSI was used by Google (aside)
- 37. Sometimes the searcher query is a ‘cold start’ query
- 38. Broad or cold start queries might call for result diversification due to lack of intent detection
- 39. Search engines may return a broad blend of results to match these queries Freshness Serendipity Novelty Diversity
- 41. The searcher has to click around to provide feedback on their intent or reformulate the query by entering something else (‘query refinement’)
- 42. To then deliver sequential queries with greater intent understanding
- 45. A kind of ‘probability- driven fork in the road’ http://delivery.acm.org/10.1145/1780000/1772776/p841-sadikov.pdf (Sadikov et al, 2010) CLUSTERING QUERY REFINEMENTS BY USER INTENT
- 46. BUT word’s meaning & user intent /context combined are still very hard to understand for search engines
- 47. Despite assistance from Google’s BERT & progress in NLP
- 50. Stanford Question And Answer Dataset 2.0 • Rajpurkar, P., Zhang, J., Lopyrev, K. and Liang, P., 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250.
- 51. MS MARCO Paper • Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R. and Deng, L., 2016. MS MARCO: A Human-Generated MAchine Reading COmprehension Dataset.
- 52. The exact same queries have different intent at different times & different locations
- 53. What did you really mean when you searched for ‘Easter’? • Radinsky, K., Svore, K.M., Dumais, S.T., Shokouhi, M., Teevan, J., Bocharov, A. and Horvitz, E., 2013. Behavioral dynamics on the web: Learning, modeling, and prediction. ACM Transactions on Information Systems (TOIS), 31(3), p.16. When did you search for ‘Easter’? A few weeks before Easter A few days before Easter During Easter What you mostly meant When is Easter? Things to do at Easter What is the meaning of Easter?
- 54. Modeling & Predicting Behavioural Dynamics on The Web (Radinsky et al, 2012)
- 55. “When users’ information needs change over time, the ranking of results should also change to accommodate these needs.” (Radinsky, 2013)
- 60. The intent of queries changes over time
- 61. The passage of time adds new meaning to queries sometimes too
- 62. The rise and fall of the Blackberry?
- 64. Temporal Dynamic Intent (Burstiness) is a huge factor for intent
- 65. At certain times far more intents will be transactional
- 66. “dresses”, “shoes”, “bags” “buy dresses”, “buy shoes”, “buy bags”, “dress sales”, “shoe sales” Really means
- 67. And sometimes only reasons a particular audience would understand spike temporal queries
- 68. [Four candles] + [fork handles] interest over time
- 69. Sometimes it is other events which trigger unexpected queries
- 70. Your ranking flux might well be shifting query intents at scale
- 71. Dawn Anderson | @dawnieando | #TechSEOBoost What a nightmare queries are
- 72. Maybe It’s Time For A Change?
- 73. Enter… The Next 20 Years of Search
- 74. Hmm… That sounds big Google… This is HUGE
- 75. Dawn Anderson | @dawnieando | #TechSEOBoost Three FUNDAMENTAL shifts in search
- 76. Dawn Anderson | @dawnieando | #TechSEOBoost Fundamental: “forming a necessary base or core; of central importance.”
- 77. Dawn Anderson | @dawnieando | #TechSEOBoost Three Fundamental Shifts • The shift from answers to journeys • The shift from queries to queryless • The shift from text to visual information
- 78. Dawn Anderson | @dawnieando | #TechSEOBoost The shift from text to more visual information
- 79. This feels like a huge UX / accessibility shift… Hoorah
- 80. Images are much easier to mentally consume than text & audio
- 81. Images & video engage… Images & video entertain Images & video provoke emotion
- 82. Photography app usage had a 210% increase between 2016 and 2018 according to App Annie
- 83. People spend on average 2.6x more time on pages with video
- 84. Image search is curation. Totally different to text-based search
- 85. Dawn Anderson | @dawnieando | #TechSEOBoost This is cognitive load management & information filtering
- 86. Go nuts with quality images & video
- 87. Dawn Anderson | @dawnieando | #TechSEOBoost The shift from queries to queryless
- 88. “Queries Are Difficult To Understand in Isolation” (Susan Dumais, Microsoft Research, 2016)
- 89. “Easier if we can model: who is asking, what they have done in the past, where they are, when it is, etc.” (Susan Dumais, CIKM, 2016)
- 90. Better still… what about predicting the user’s informational needs to proactively make suggestions?
- 91. QueryLess: Next Gen Proactive Search And Recommender Engines (2016)
- 92. “Nevertheless, as the world is becoming more mobile-centric, this old-fashioned query-driven search scenario and clickbased evaluation mechanism can no longer catch up with the rapid evolution of user demand on mobile devices.” (Song and Guo,2016 (Microsoft Research))
- 93. “Therefore,a more user- friendly, mobile-centric and scenario driven search paradigm that requires minimal user inputs is ready to come out” (Song and Guo,2016 (Microsoft Research))
- 94. It kind of sounds like Google Discover
- 95. At last announcement Google Discover had 800 million users (May, 2018)
- 96. It’s now on mobile home page. It knows you… and the things you do… where you’ve been… where you’re going
- 97. “In many cases predicting informational needs removes the need for the query & reactive search engine” (Song & Guo, 2016)
- 98. Zero-Query Queries – No Query Required
- 101. QueryLess: Next Gen Proactive Search And Recommender Engines
- 102. Google Scholar is now a Recommender System Too
- 103. YouTube is a Recommender System
- 104. YouTube Feedback Controls is ‘The Human in The Loop’
- 105. Reinforcement learning thrives from rewards (implicit feedback)
- 107. Dawn Anderson | @dawnieando | #TechSEOBoost The User (needs) is ‘The Query’
- 108. Dawn Anderson | @dawnieando | #TechSEOBoost The shift from answers to journeys
- 109. An information need is rarely a task with a single finite item
- 110. It’s more like a series of little chunks (sub-tasks)
- 111. People are creatures of habit it seems
- 112. “Patterns were spotted about repetitive task driven search behaviours – predictable” (Song & Guo, 2016)
- 113. Tasks & timelines go hand in hand… it seems
- 114. “Predictable task timeline patterns are more prevalent on mobile devices” (Song & Guo, 2016)
- 115. Like e.g. ‘checking the stock market’ every morning if you’re interested in stocks and shares
- 116. Mobile Device Sensors (14 sensors or more) Proximity sensors GPS sensor Ambient light sensor Accelerometer Compass Gyroscope Back illuminated sensor
- 117. Many tasks & intents can be modelled according to predicted patterns
- 118. Personalising Search via Interests & Activities 2005 paper awarded the 2017 SIGIR Test of Time Award. Cited 1029 times to date Teevan, J., Dumais, S.T. and Horvitz, E., 2005, August. Personalizing search via automated analysis of interests and activities. In Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 449-456). ACM.
- 119. Google Discover looks to be focusing on hobbies, interests, news and social activities
- 120. Very Recent Microsoft Research
- 121. The Ideal is Personalisation • Not easy to achieve fully • Sparsity of data • Privacy concerns • Broken sequences
- 122. In the absence of personalization… collaborative Filtering
- 123. There are other people nearly like you
- 124. You (and me) are unique… but may be similar
- 125. Matrix Factorisation (Netflix Recommendation System) + Matrix Factorisation (WALS Algorithm, Tensorflow)
- 127. Based on users liking the same things (with hidden common preferences)
- 128. Those sharing similar interests likely share other hidden interests too (i.e. the system does not know of them yet)
- 130. Modelling cohorts
- 131. Understand the user, understand their cohort… Understand other similar informational needs
- 133. The two sides of assistant will both be proactive Provide answers / search Conversation Search Help with activities / tasks Conversation Actions
- 134. Extend Actions on Google using Machine Learning
- 135. Understand your customers to assist with AI Perceived Information need Micro-task Micro-task Micro-task Micro-task Micro-task Task Micro-task Micro-task Micro-task Micro-task Task Micro-task Micro-task Task Micro-task Micro-task Micro-task Task Micro-task Micro-task Task Micro-task Task We can identify the user’s probable top tasks & subtasks Identify their needs & what info they need along the way
- 136. Tell us about the tasks, order and steps involved in booking a hotel
- 137. Many built-in intents & many ‘coming soon’
- 138. Connecting Tasks Across Devices & Applications
- 139. Multi- platforming • Switching between search and video • Between search and a recommender system
- 141. Building a Personal Knowledge Graph
- 142. A Recent Microsoft Personal Knowledge Graph Patent
- 143. Dawn Anderson | @dawnieando | #TechSEOBoost This is ’Task- driven’ Search & Recommender Systems
- 144. Where the user is truly ‘the query’
- 145. Dawn Anderson | @dawnieando | #TechSEOBoost Toward a Personal Knowledge Graph
- 146. Truly PERSONAL AI is not possible without a PERSONAL KNOWLEDGE GRAPH (Krisztian Balog, ECIR 2019)
- 147. Dawn Anderson | @dawnieando | #TechSEOBoost But where will users be reached?
- 148. By 2022 PCs will account for only 19 percent of IP traffic (Comscore, 2019)
- 149. Interest over time for Google Home & Amazon Alexa
- 150. Assistant + Home + Discover + Search App + Desktop + Location Tracker + Calendar + Gmail + YouTube
- 151. In your car
- 152. In your console
- 154. Toward An Audience of One
- 155. What Can SEOs Do About This?
- 156. Realise… your ranking tools are mostly wrong
- 157. Dawn Anderson | @dawnieando | #TechSEOBoost Think CRM for SEO
- 158. Dawn Anderson | @dawnieando | #TechSEOBoost Identify interests & affinity groups
- 159. Map every single informational need sub-task you can think of to the sections of a model like the RACE model
- 160. Build task timeline clusters
- 161. Map & cluster ‘Related’ content by task & temporal type. Categories are too broad, and topics may be too
- 162. Dawn Anderson | @dawnieando | #TechSEOBoost Continually improve and update solid URL seasonal & temporal content
- 164. Dawn Anderson | @dawnieando | #TechSEOBoost Continually improve and update solid URL evergreen content
- 165. Dawn Anderson | @dawnieando | #TechSEOBoost Map content clearly to tasks and task timelines
- 167. Identify predictable patterns of user behavior
- 168. Understand the shared preferences, learn the hidden preferences
- 170. Go • Go big on evergreen content & keep updated Optimise • Optimise images well – think curation / collections Map • Map user journeys to content plans Optimise • video well – enhance with markup / transcription Get • Get personal – keep refining segments / personas Identify • Identify & cluster content around task timelines Use • Use relatedness across content, tasks & temporality
- 171. Dawn Anderson | @dawnieando | #TechSEOBoost Bias and reproducibility is a challenge
- 172. Reproducibility problems in research & RecSys (very high)
- 173. Bias on the web and recommender systems
- 174. Bias Considerations Presentation Bias Programming Bias Audience Manipulated Bias (e.g fake reviews) Machine Learning / AI Bias (Black box algorithms) Matthew’s Law Zipfian Distribution of Web Content
- 175. NoBIAS Project
- 176. Spotify add novelty items to home page to avoid biased personalisation
- 177. Do yourself a favour and follow Mounia Lalmas @mounialalmas
- 178. And this polar bear
- 181. Dawn Anderson | @dawnieando | #TechSEOBoost References
- 182. • Broder, A., 2002, September. A taxonomy of web search. In ACM Sigir forum (Vol. 36, No. 2, pp. 3-10). ACM. • Chuklin, A., Severyn, A., Trippas, J., Alfonseca, E., Silen, H. and Spina, D., 2018. Prosody Modifications for Question-Answering in Voice-Only Settings. arXiv preprint arXiv:1806.03957. • HigherVisibility. 2018. How Popular is Voice Search? | HigherVisibility. [ONLINE] Available at: https://www.highervisibility.com/blog/how-popular-is-voice-search/ • Filippova, K., Alfonseca, E., Colmenares, C.A., Kaiser, L. and Vinyals, O., 2015. Sentence compression by deletion with lstms. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (pp. 360-368). • Filippova, K. and Alfonseca, E., 2015. Fast k-best sentence compression. arXiv preprint arXiv:1510.08418. • Google Developers. 2018. Content-based Actions | Actions on Google | Google Developers. [ONLINE] Available at: https://developers.google.com/actions/content- actions/. [Accessed 18 June 2018]
- 183. References Radinsky, K., Svore, K.M., Dumais, S.T., Shokouhi, M., Teevan, J., Bocharov, A. and Horvitz, E., 2013. Behavioral dynamics on the web: Learning, modeling, and prediction. ACM Transactions on Information Systems (TOIS), 31(3), p.16 Sadikov, E., Madhavan, J. and Halevy, A., Google LLC, 2013. Clustering query refinements by inferred user intent. U.S. Patent 8,423,538. Official Google Webmaster Central Blog. 2019. Official Google Webmaster Central Blog: Rolling out mobile-first indexing . [ONLINE] Available at: https://webmasters.googleblog.com/2018/03/rolling-out- mobile-first-indexing.html. [Accessed 25 September 2019]. Zhou, S., Cheng, K. and Men, L., 2017, April. The survey of large-scale query classification. In AIP Conference Proceedings (Vol. 1834, No. 1, p. 040045). AIP Publishing.
- 184. References Search Engine Land. 2019. Starting July 1, all new sites will be indexed using Google's mobile-first indexing - Search Engine Land. [ONLINE] Available at: https://searchengineland.com/july-1-new-sites-will-be- indexed-using-googles-mobile-first-indexing-317490. [Accessed 25 September 2019]. Teevan, J., Dumais, S.T. and Horvitz, E., 2005, August. Personalizing search via automated analysis of interests and activities. In Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 449-456). ACM. Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R. and Deng, L., 2016. MS MARCO: A Human-Generated MAchine Reading COmprehension Dataset.
- 185. Dawn Anderson | @dawnieando | #TechSEOBoost Keep in touch @dawnieando