%0 Book Section %1 haruechaiyasak2008article %A Haruechaiyasak, Choochart %A Damrongrat, Chaianun %B Digital Libraries: Universal and Ubiquitous Access to Information %D 2008 %E Buchanan, George %E Masoodian, Masood %E Cunningham, SallyJo %I Springer Berlin Heidelberg %K article linkRecommender model recommendation topic wikipedia %P 339-342 %R 10.1007/978-3-540-89533-6_39 %T Article Recommendation Based on a Topic Model for Wikipedia Selection for Schools %U http://dx.doi.org/10.1007/978-3-540-89533-6_39 %V 5362 %X The 2007 Wikipedia Selection for Schools is a collection of 4,625 selected articles from Wikipedia as educational for children. Users can currently access articles within the collection via two different methods: (1) by browsing on either a subject index or a title index sorted alphabetically, and (2) by following hyperlinks embedded within article pages. These two retrieval methods are considered static and subjected to human editors. In this paper, we apply the Latent Dirichlet Allocation (LDA) algorithm to generate a topic model from articles in the collection. Each article can be expressed by a probability distribution on the topic model. We can recommend related articles by calculating the similarity measures among the articles’ topic distribution profiles. Our initial experimental results showed that the proposed approach could generate many highly relevant articles, some of which are not covered by the hyperlinks in a given article. %@ 978-3-540-89532-9

@incollection{haruechaiyasak2008article, abstract = {The 2007 Wikipedia Selection for Schools is a collection of 4,625 selected articles from Wikipedia as educational for children. Users can currently access articles within the collection via two different methods: (1) by browsing on either a subject index or a title index sorted alphabetically, and (2) by following hyperlinks embedded within article pages. These two retrieval methods are considered static and subjected to human editors. In this paper, we apply the Latent Dirichlet Allocation (LDA) algorithm to generate a topic model from articles in the collection. Each article can be expressed by a probability distribution on the topic model. We can recommend related articles by calculating the similarity measures among the articles’ topic distribution profiles. Our initial experimental results showed that the proposed approach could generate many highly relevant articles, some of which are not covered by the hyperlinks in a given article.}, added-at = {2013-02-25T00:29:58.000+0100}, author = {Haruechaiyasak, Choochart and Damrongrat, Chaianun}, biburl = {https://www.bibsonomy.org/bibtex/2d91432e77be86134d06c24860ba91f7b/asmelash}, booktitle = {Digital Libraries: Universal and Ubiquitous Access to Information}, description = {Article Recommendation Based on a Topic Model for Wikipedia Selection for Schools - Springer}, doi = {10.1007/978-3-540-89533-6_39}, editor = {Buchanan, George and Masoodian, Masood and Cunningham, SallyJo}, interhash = {fb7560b927b722513dd87f825ca32086}, intrahash = {d91432e77be86134d06c24860ba91f7b}, isbn = {978-3-540-89532-9}, keywords = {article linkRecommender model recommendation topic wikipedia}, pages = {339-342}, publisher = {Springer Berlin Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2013-02-25T00:29:58.000+0100}, title = {Article Recommendation Based on a Topic Model for Wikipedia Selection for Schools}, url = {http://dx.doi.org/10.1007/978-3-540-89533-6_39}, volume = 5362, year = 2008 }