國立虎尾科技大學 |

Natural Language Processing: Distinguishing Employee Views Toward Leadership.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Natural Language Processing: Distinguishing Employee Views Toward Leadership./
作者:	Deopersaud, Eric.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	49 p.
附註:	Source: Masters Abstracts International, Volume: 84-02.
Contained By:	Masters Abstracts International84-02.
標題:	Language. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29391883
ISBN:	9798841799580

Natural Language Processing: Distinguishing Employee Views Toward Leadership.
Deopersaud, Eric.

Natural Language Processing: Distinguishing Employee Views Toward Leadership. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 49 p.

Source: Masters Abstracts International, Volume: 84-02.

Thesis (M.S.)--Utica University, 2022.

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

A US-based survey company saught to enhance their already successful platform through the use of natural language processing by distinguishing if an employee’s gender contributes to the views they may have on their leader. Employees’ comments, an unstructured form of data, were collected by the US-based company as part of its standard workplace experience survey. The employee comments were answers to the following questions:●Question 30013: What about the leader of this company inspires your confidence?●Question 30014: What can the leader of this company do to gain your full confidence?The comments, an unstructured data type known as a string, were tokenized, lemmatized and refined through stop word removal as part of natural language processing. The data was also repeatedly condensed through the use of dimensionality reduction. Once adequately set up for implementation into a model, the unsupervised machine learning model of latent dirichlet allocation was utilized. This model was able to produce defining topics based on the comments for each gender and question.This model produced no distinction of those genders who answered question 30013 as the attributes of a leader were found to be similar across the gender categories and included topics such as growth for the future and being personable. In contrast, a distinction was found between genders answering question 30014 and included topics such as company politics, future growth, and informativeness.

ISBN: 9798841799580Subjects--Topical Terms:

571568
Language.
Subjects--Index Terms:

Bigrams

Natural Language Processing: Distinguishing Employee Views Toward Leadership.
LDR:02736nam a2200433 4500 001 1104664
005 20230619080114.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798841799580
035 $a (MiAaPQ)AAI29391883
035 $a AAI29391883
040 $a MiAaPQ $c MiAaPQ
100 1 $a Deopersaud, Eric. $3 1413605
245 1 0 $a Natural Language Processing: Distinguishing Employee Views Toward Leadership.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 49 p.
500 $a Source: Masters Abstracts International, Volume: 84-02.
500 $a Advisor: McCarthy, Michael.
502 $a Thesis (M.S.)--Utica University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a A US-based survey company saught to enhance their already successful platform through the use of natural language processing by distinguishing if an employee’s gender contributes to the views they may have on their leader. Employees’ comments, an unstructured form of data, were collected by the US-based company as part of its standard workplace experience survey. The employee comments were answers to the following questions:●Question 30013: What about the leader of this company inspires your confidence?●Question 30014: What can the leader of this company do to gain your full confidence?The comments, an unstructured data type known as a string, were tokenized, lemmatized and refined through stop word removal as part of natural language processing. The data was also repeatedly condensed through the use of dimensionality reduction. Once adequately set up for implementation into a model, the unsupervised machine learning model of latent dirichlet allocation was utilized. This model was able to produce defining topics based on the comments for each gender and question.This model produced no distinction of those genders who answered question 30013 as the attributes of a leader were found to be similar across the gender categories and included topics such as growth for the future and being personable. In contrast, a distinction was found between genders answering question 30014 and included topics such as company politics, future growth, and informativeness.
590 $a School code: 4133.
650 4 $a Language. $3 571568
650 4 $a Computer science. $3 573171
653 $a Bigrams
653 $a Latent dirichlet allocation
653 $a Lemmatization
653 $a Text mining
653 $a Tokenization
653 $a Topic modeling
690 $a 0984
690 $a 0679
690 $a 0454
690 $a 0800
690 $a 0629
710 2 $a Utica University. $b Data Science. $3 1413606
773 0 $t Masters Abstracts International $g 84-02.
790 $a 4133
791 $a M.S.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29391883