東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Linking Wikipedia and the Directory ...

Huffaker, Christina.

FindBook

Google Book

Amazon

博客來

Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation./
作者:	Huffaker, Christina.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	154 p.
附註:	Source: Masters Abstracts International, Volume: 82-12.
Contained By:	Masters Abstracts International82-12.
標題:	Library science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28497319
ISBN:	9798516069420

Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation.
Huffaker, Christina.

Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 154 p.

Source: Masters Abstracts International, Volume: 82-12.

Thesis (M.S.)--Utica College, 2021.

This item must not be sold to any third party vendors.

The vast amount of digital information, or "information overload," has created challenges for information seekers, causing many users to unknowingly employ search strategies that compromise their ability to locate the best, most relevant information. One particular search behavior is called "satisficing." Previous attempts to aid users' searches have implemented various machine learning methods to link library records with Wikipedia articles to aid in the discovery of library items. These solutions provide important groundwork for this analysis, which aims to address issues of access users may encounter with library items, while identifying a method to generate keywords from one text dataset to serve as an index to describe a new text dataset. Specifically, the ultimate goal is to link openly-published, digitally available works with open-collaborative works, like Wikipedia. Item description and classification, traditionally known as "cataloging," in the library field, is the manual means of accomplishing this type of task. The latent Dirichlet allocation, a natural language processing algorithm for topic modeling, holds potential for automating these types of cataloging methods. Applying the latent Dirichlet allocation to a dataset composed of 10,000 randomly sampled full-text articles from Wikipedia and another dataset composed of 10,000 article abstracts from the Directory of Open Access Journals (DOAJ) revealed that the full-text Wikipedia articles generated more coherent topics and that the extracted, weighted Wikipedia keywords, when applied to a new dataset composed of DOAJ abstracts, accurately described the primary topics within the abstracts. This finding indicates the strong potential for successful application of latent Dirichlet to link openly-published works to Wikipedia articles.

ISBN: 9798516069420Subjects--Topical Terms:

539284
Library science.
Subjects--Index Terms:

Directory of Open Access Journals

Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation.
LDR:03084nmm a2200385 4500 001 2284297
005 20211115072427.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798516069420
035 $a (MiAaPQ)AAI28497319
035 $a AAI28497319
040 $a MiAaPQ $c MiAaPQ
100 1 $a Huffaker, Christina. $3 3563460
245 1 0 $a Linking Wikipedia and the Directory of Open Access Journals with Extracted, Weighted Keywords Using the Latent Dirichlet Allocation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 154 p.
500 $a Source: Masters Abstracts International, Volume: 82-12.
500 $a Advisor: McCarthy, Michael.
502 $a Thesis (M.S.)--Utica College, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a The vast amount of digital information, or "information overload," has created challenges for information seekers, causing many users to unknowingly employ search strategies that compromise their ability to locate the best, most relevant information. One particular search behavior is called "satisficing." Previous attempts to aid users' searches have implemented various machine learning methods to link library records with Wikipedia articles to aid in the discovery of library items. These solutions provide important groundwork for this analysis, which aims to address issues of access users may encounter with library items, while identifying a method to generate keywords from one text dataset to serve as an index to describe a new text dataset. Specifically, the ultimate goal is to link openly-published, digitally available works with open-collaborative works, like Wikipedia. Item description and classification, traditionally known as "cataloging," in the library field, is the manual means of accomplishing this type of task. The latent Dirichlet allocation, a natural language processing algorithm for topic modeling, holds potential for automating these types of cataloging methods. Applying the latent Dirichlet allocation to a dataset composed of 10,000 randomly sampled full-text articles from Wikipedia and another dataset composed of 10,000 article abstracts from the Directory of Open Access Journals (DOAJ) revealed that the full-text Wikipedia articles generated more coherent topics and that the extracted, weighted Wikipedia keywords, when applied to a new dataset composed of DOAJ abstracts, accurately described the primary topics within the abstracts. This finding indicates the strong potential for successful application of latent Dirichlet to link openly-published works to Wikipedia articles.
590 $a School code: 1754.
650 4 $a Library science. $3 539284
650 4 $a Artificial intelligence. $3 516317
650 4 $a Web studies. $3 2122754
653 $a Directory of Open Access Journals
653 $a Information science
653 $a Library science
653 $a Machine learning
653 $a Natural language processing
653 $a Open educational resources
690 $a 0399
690 $a 0800
690 $a 0646
710 2 $a Utica College. $b Data Science. $3 3433220
773 0 $t Masters Abstracts International $g 82-12.
790 $a 1754
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28497319