Downloaded 201 times
Uploaded byBill Slawski
Keyword Research and Topic Modeling in a Semantic Web
The document discusses keyword research and topic modeling in the semantic web. It covers identifying named entities, adding schema markup to pages, and verifying listings on Google My Business. It also discusses using context and related phrases to improve search engine optimization, including looking at knowledge bases, disambiguations pages, and clustering related meanings. The document provides examples of using related words and phrases for semantic topic clustering and ranking documents based on included phrases.
Marketingā¦
More Related Content
![[LondonSEO 2020] BigQuery & SQL for SEOs](https://cdn.slidesharecdn.com/ss_thumbnails/abuali-londonseomeetup-200115205008-thumbnail.jpg?width=600ounds&width=560&fit=bounds)
Similar to Keyword Research and Topic Modeling in a Semantic Web
Keyword Research and Topic Modeling in a Semantic Web
- 1. #pubcon @bill_slawski Keyword Research and TopicModeling in a Semantic Web Presented by: Bill Slawski Director of SEO Research Go Fish Digital
- 2.
- 3.
- 4. #pubcon @bill_slawski Be Careful toRead All The Signs
- 5. #pubcon @bill_slawski An Entity AuditUncovers Surprises Named entities are specific people, places, and things, including products and brands.
- 6. #pubcon @bill_slawski Paul Haahr- HowGoogle Works
- 7. #pubcon @bill_slawski Schema Markup, Google MyBusinessVerification, Entry in Wikipedia can lead to Knowledge panels, but they are only the start of adding entity informationā¦
- 8. #pubcon @bill_slawski An elevator Ridefrom the DC Metro
- 9. #pubcon @bill_slawski There is noclear sign telling people
- 10. #pubcon @bill_slawski On the DCMetroline, you connect to: ā¢ 91 Stations in Md, Va, & DC ā¢ National Zoo ā¢ 19 Smithsonian Museums ā¢ National Gallery of Art ā¢ Capital One Arena ā¢ Fedex Field ā¢ Pentagon City Shopping Mall
- 11.
- 12. #pubcon @bill_slawski Knowing how Googleuses context and semantically related phrases can improve the content you create and how well you optimize pages for particular queries.
- 13. #pubcon @bill_slawski Keywords & ContextVectors āFor example, a horse to a rancher is an animal. A horse to a carpenter is an implement of work. A horse to a gymnast is an implement on which to perform certain exercises. User-context-based search engine
- 14. #pubcon @bill_slawski Look to KnowledgeBases https://en.wikipedia.org/wiki/Horse
- 15.
- 16.
- 17. #pubcon @bill_slawski Context Search Results Context-basedfiltering of search results
- 18. #pubcon @bill_slawski Map Keywords toPages, thenā¦ ā¢ Make sure you add words that indicate context ā¢ Look up the top pages that rank for those keywords ā¢ Find phrases that co-occur for that meaning ā¢ See: Improving semantic topic clustering for search Queries with word co-occurrence and biograph co- clustering
- 19. #pubcon @bill_slawski Phrase-Based Indexing ā¢ Lookfor co-occurring phrases on pages that rank highly for a query. ā¢ Using these related phrases on a page can boost how it ranks for that query (body hits) ā¢ Using those related phrases as anchors can boost how the page targeted ranks for that query (anchor hits)
- 20. #pubcon @bill_slawski Related Words/Phrases Thematic ModelingUsing Related Words in Documents and Anchor Text
- 21. #pubcon @bill_slawski Use Complete Phrases ā¢Incomplete Phraseā¦ āPresident of theā¦ā ā¢ Complete Phraseā¦ āPresident of the United States.ā
- 22. #pubcon @bill_slawski Use Meaningful Phrases ā¢Some phrases do not add meaning to a page: Pay the Piper Out of the Blue Top of the Morning
- 23. #pubcon @bill_slawski Predictive Aspects ofPhrases ā¢ Semantically, related phrases will be those that are commonly used to discuss or describe a given topic or concept, such as "President of the United States" and "White House." For a given phrase, the related phrases can be ordered according to their relevance or significance based on their respective prediction measures. ā¢ Integrated external related phrase information into a phrase-based indexing information retrieval system
- 24.
- 25. #pubcon @bill_slawski Clustered Meanings ā¢ Jaguars-Cats, Cars, NFL Football Team ā¢ Java ā Programming Language, Island in Indonesia, Drink ā¢ Bank ā A place to store money, a riverās side, to lean to a side
- 26. #pubcon @bill_slawski Ranking Documents Basedon Contained Phrases (Body Hits) āā¦a ranking stage in which the documents in the search results are ranked, using the phrase information in each document's related phrase bit vector, and the cluster bit vector for the query phrases. This approach ranks documents according to the phrases that are contained in the document, or informally ābody hits.āā Integrated external related phrase information into a phrase-based indexing information retrieval system
- 27. #pubcon @bill_slawski Anchor Hits āSorting thedocuments on the outbound score component makes documents that have many related phrases to the query as āanchor hits,ā rank most highly, thus representing these documents as āexpertā documentsā ā¢Integrated external related phrase information into a phrase-based indexing information retrieval system
- 28. #pubcon @bill_slawski Personalization & QueryClassifications ā¢ Depending upon results selected by a searcher, the results they see may fall into a specific category from a biased document set Personalizing Search Results at Google
- 29.
- 30. #pubcon @bill_slawski Look at KnowledgeBases ā¢ Abraham Lincoln
- 31. #pubcon @bill_slawski Look at TopSearch Results ā¢ Lincoln, Towncar
- 32. #pubcon @bill_slawski Look at OtherSearch Entities ā¢ Lincoln, Nebraska
- 33. #pubcon @bill_slawski Query Classifications Search forāLincolnā and click on the Person (Abe), the Place (Nebraska), or the thing (towncar). What you click on may determine what you see in the future on searches for āLincoln.ā ā¦determining whether to assign the classification to the first query based upon classifications for the identified search entities. ā¢Propagating query classifications
- 34. #pubcon @bill_slawski Searches are whatwe type, and what we say, but they will also be based upon what we see and take photos of in the future.
- 35. #pubcon @bill_slawski Google Lens Schema SmartCamera User Interface
- 36. #pubcon @bill_slawski Further Reading ā¢ Knowledge-BasedTrust: Estimating the Trustworthiness of Web Sources ā¢ A Review of Relational Machine Learning for Knowledge Graphs ā¢ Knowledge Curation and Knowledge Fusion: Challenges, Models, and Applications ā¢ Improving semantic topic clustering for search queries with word co-occurrence and bigraph co-clustering
- 37. #pubcon @bill_slawski Questions? Ask MeAt: ā¢ Twitter: https://twitter.com/bill_slawski ā¢ LinkedIn: https://www.linkedin.com/in/slawski/ ā¢ Facebook: https://www.facebook.com/bill.slawski ā¢ Google+: https://plus.google.com/+BillSlawski ā¢ SEO by the Sea: http://www.seobythesea.com/ ā¢ Go Fish Digital Blog: https://gofishdigital.com/blog/