Matches in SemOpenAlex for { <https://semopenalex.org/work/W97886192> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W97886192 abstract "This thesis considers di erent methods of utilising the contextual information on webpagesand ads in order to improve the tting of a Bayesian Poisson model to historicdata using L-BFGS. The data and optimization algorithm is provided by Admeta, anadvertising optimization company that uses the model for click-rate predictions. Thedi erent methods tried to get added contextual information include categorization anddeveloping di erent similarity measures between web-pages and ads using keywords.The similarity measures are based on WordNet, a large lexical database, and Word2Vecan open source tool that represents words as vectors. The categorization of web-pagesgives good results as does some of the similarity measures. As WordNet is limited to thewords found in its databaseWord2Vec is deemed more exible and a superior source. Forcertain similarity measures it is shown that the click rate increases with the similarity.In the end using the average of the cosine distance between all keyword's vector pairsseams to give the best results among the di erent similarities tried for Word2Vec." @default.
- W97886192 created "2016-06-24" @default.
- W97886192 creator A5012832640 @default.
- W97886192 date "2014-01-01" @default.
- W97886192 modified "2023-09-27" @default.
- W97886192 title "Machine Learning for On-line Advertising Using Contextual Information" @default.
- W97886192 cites W1566018662 @default.
- W97886192 hasPublicationYear "2014" @default.
- W97886192 type Work @default.
- W97886192 sameAs 97886192 @default.
- W97886192 citedByCount "0" @default.
- W97886192 crossrefType "dissertation" @default.
- W97886192 hasAuthorship W97886192A5012832640 @default.
- W97886192 hasConcept C103278499 @default.
- W97886192 hasConcept C115961682 @default.
- W97886192 hasConcept C119857082 @default.
- W97886192 hasConcept C124101348 @default.
- W97886192 hasConcept C136764020 @default.
- W97886192 hasConcept C154945302 @default.
- W97886192 hasConcept C157659113 @default.
- W97886192 hasConcept C162324750 @default.
- W97886192 hasConcept C176217482 @default.
- W97886192 hasConcept C21547014 @default.
- W97886192 hasConcept C21959979 @default.
- W97886192 hasConcept C23123220 @default.
- W97886192 hasConcept C2776461190 @default.
- W97886192 hasConcept C2780762811 @default.
- W97886192 hasConcept C41008148 @default.
- W97886192 hasConcept C41608201 @default.
- W97886192 hasConcept C73555534 @default.
- W97886192 hasConcept C94124525 @default.
- W97886192 hasConceptScore W97886192C103278499 @default.
- W97886192 hasConceptScore W97886192C115961682 @default.
- W97886192 hasConceptScore W97886192C119857082 @default.
- W97886192 hasConceptScore W97886192C124101348 @default.
- W97886192 hasConceptScore W97886192C136764020 @default.
- W97886192 hasConceptScore W97886192C154945302 @default.
- W97886192 hasConceptScore W97886192C157659113 @default.
- W97886192 hasConceptScore W97886192C162324750 @default.
- W97886192 hasConceptScore W97886192C176217482 @default.
- W97886192 hasConceptScore W97886192C21547014 @default.
- W97886192 hasConceptScore W97886192C21959979 @default.
- W97886192 hasConceptScore W97886192C23123220 @default.
- W97886192 hasConceptScore W97886192C2776461190 @default.
- W97886192 hasConceptScore W97886192C2780762811 @default.
- W97886192 hasConceptScore W97886192C41008148 @default.
- W97886192 hasConceptScore W97886192C41608201 @default.
- W97886192 hasConceptScore W97886192C73555534 @default.
- W97886192 hasConceptScore W97886192C94124525 @default.
- W97886192 hasLocation W978861921 @default.
- W97886192 hasOpenAccess W97886192 @default.
- W97886192 hasPrimaryLocation W978861921 @default.
- W97886192 hasRelatedWork W2291376828 @default.
- W97886192 hasRelatedWork W2373476341 @default.
- W97886192 hasRelatedWork W2613830894 @default.
- W97886192 hasRelatedWork W2755266740 @default.
- W97886192 hasRelatedWork W2783279235 @default.
- W97886192 hasRelatedWork W2784864529 @default.
- W97886192 hasRelatedWork W2796055497 @default.
- W97886192 hasRelatedWork W2937960099 @default.
- W97886192 hasRelatedWork W2964279163 @default.
- W97886192 hasRelatedWork W2969916858 @default.
- W97886192 hasRelatedWork W2981981753 @default.
- W97886192 hasRelatedWork W3000535534 @default.
- W97886192 hasRelatedWork W3025337893 @default.
- W97886192 hasRelatedWork W3042691758 @default.
- W97886192 hasRelatedWork W3135281810 @default.
- W97886192 hasRelatedWork W31399744 @default.
- W97886192 hasRelatedWork W57243399 @default.
- W97886192 hasRelatedWork W2100621574 @default.
- W97886192 hasRelatedWork W2112167375 @default.
- W97886192 hasRelatedWork W2962594426 @default.
- W97886192 isParatext "false" @default.
- W97886192 isRetracted "false" @default.
- W97886192 magId "97886192" @default.
- W97886192 workType "dissertation" @default.