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

FindBook

Google Book

Amazon

博客來

Understanding Political Communication with Contextualized Methods from Natural Language Processing.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Understanding Political Communication with Contextualized Methods from Natural Language Processing./
作者:	Huang, Leslie.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	271 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
Contained By:	Dissertations Abstracts International83-02B.
標題:	Artificial intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28317377
ISBN:	9798534676105

Understanding Political Communication with Contextualized Methods from Natural Language Processing.
Huang, Leslie.

Understanding Political Communication with Contextualized Methods from Natural Language Processing. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 271 p.

Source: Dissertations Abstracts International, Volume: 83-02, Section: B.

Thesis (Ph.D.)--New York University, 2021.

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

This dissertation is comprised of three projects demonstrating new contextualized natural language processing methods that provide insights about political communication. The first project introduces a measure to better understand political polarization: "contextual polarity," the divergence in contextual usage of a given word by Republicans versus Democrats. Our analysis of tweets from members of Congress finds that ideologically extreme legislators are generally more likely to use contextually polarizing words in a manner consistent with their party, although there is notable intrapersonal variation across topics and across personal versus official Twitter accounts. The second project presents a framework for optimally clustering questions and answers using the Question Typology model. Our case studies of the Leveson public inquiry on media ethics and the war crimes trial of Charles Taylor identify clusters of questions which are consistent with patterns in how different types of witnesses are treated in cross-examination. The last project augments the stylest model of speaker distinctiveness with a new measure of word dissimilarity. In our study of rebellious behavior in the UK House of Commons (1935-2018), we find that government backbenchers are more distinctive than their opposition counterparts, and that distinctiveness is associated with future promotion.

ISBN: 9798534676105Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Natural language processing

Understanding Political Communication with Contextualized Methods from Natural Language Processing.
LDR:02573nmm a2200373 4500 001 2347421
005 20220801062154.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798534676105
035 $a (MiAaPQ)AAI28317377
035 $a AAI28317377
040 $a MiAaPQ $c MiAaPQ
100 1 $a Huang, Leslie. $3 3686662
245 1 0 $a Understanding Political Communication with Contextualized Methods from Natural Language Processing.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 271 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
500 $a Advisor: Spirling, Arthur.
502 $a Thesis (Ph.D.)--New York University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a This dissertation is comprised of three projects demonstrating new contextualized natural language processing methods that provide insights about political communication. The first project introduces a measure to better understand political polarization: "contextual polarity," the divergence in contextual usage of a given word by Republicans versus Democrats. Our analysis of tweets from members of Congress finds that ideologically extreme legislators are generally more likely to use contextually polarizing words in a manner consistent with their party, although there is notable intrapersonal variation across topics and across personal versus official Twitter accounts. The second project presents a framework for optimally clustering questions and answers using the Question Typology model. Our case studies of the Leveson public inquiry on media ethics and the war crimes trial of Charles Taylor identify clusters of questions which are consistent with patterns in how different types of witnesses are treated in cross-examination. The last project augments the stylest model of speaker distinctiveness with a new measure of word dissimilarity. In our study of rebellious behavior in the UK House of Commons (1935-2018), we find that government backbenchers are more distinctive than their opposition counterparts, and that distinctiveness is associated with future promotion.
590 $a School code: 0146.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Political science. $3 528916
650 4 $a Computer science. $3 523869
650 4 $a Language. $3 643551
650 4 $a Nominations. $3 3564149
650 4 $a Accuracy. $3 3559958
650 4 $a Hypotheses. $3 3560118
650 4 $a Immigration. $2 lcstt $3 3267320
650 4 $a Semantics. $3 520060
650 4 $a Case studies. $2 itrt $3 996239
653 $a Natural language processing
653 $a Political communication
653 $a Political science
653 $a Text analysis
690 $a 0800
690 $a 0615
690 $a 0984
690 $a 0679
710 2 $a New York University. $b Center for Data Science. $3 3686663
773 0 $t Dissertations Abstracts International $g 83-02B.
790 $a 0146
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28317377