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

Cyberbullying Classification: Analys...

Gomez, Christopher.

FindBook

Google Book

Amazon

博客來

Cyberbullying Classification: Analysis of Text in Social Media Memes.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Cyberbullying Classification: Analysis of Text in Social Media Memes./
作者:	Gomez, Christopher.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	107 p.
附註:	Source: Masters Abstracts International, Volume: 82-06.
Contained By:	Masters Abstracts International82-06.
標題:	Artificial intelligence. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28257835
ISBN:	9798557001595

Cyberbullying Classification: Analysis of Text in Social Media Memes.
Gomez, Christopher.

Cyberbullying Classification: Analysis of Text in Social Media Memes. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 107 p.

Source: Masters Abstracts International, Volume: 82-06.

Thesis (M.S.)--Northeastern Illinois University, 2020.

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

Cyberbullying, or online bullying, is a form of harassment that occurs through the use of digital communication devices and social networking platforms, and ultimately leads to physical or mental harm or distress to the intended target. While the widespread use of social media sites has generated the power for individuals to communicate easily and quickly, it has also caused an increase in cyberbullying incidfents, with offenders experiencing minimal or no consequences. Additionally, cyberbullying can manifest itself in multiple forms, such as harmful text comments and emoticons, as well as negative images or images containing bullying text. Given the increase in cyberbullying and its varying presentation, our goal is to develop a machine learning classification schema to minimize occurrences specifically involving image memes containing text. We describe the methodology for the collection and annotation of an English short text-subjective corpus (~19,000 text comments) created from data extracted from the YouTube API. This corpus consists of current controversial and divisive topics such as politics, religion, gender, and sexual orientation. Based on previous research, several different algorithms will be compared for classifying: a Naive Bayes algorithm, Support Vector Machine (SVM) and a convolutional neural network (CNN). Additionally, we investigate classification accuracy for each of these algorithms on the entire dataset and when placing comments into topic-based groups. Finally, we discuss the limitations of the dataset and explore a set of unsupervised classification techniques for identifying and relabeling incorrectly annotated comments.

ISBN: 9798557001595Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Cyberbullying

Cyberbullying Classification: Analysis of Text in Social Media Memes.
LDR:03075nmm a2200481 4500 001 2279638
005 20210823080304.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798557001595
035 $a (MiAaPQ)AAI28257835
035 $a AAI28257835
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gomez, Christopher. $3 3558101
245 1 0 $a Cyberbullying Classification: Analysis of Text in Social Media Memes.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 107 p.
500 $a Source: Masters Abstracts International, Volume: 82-06.
500 $a Advisor: Trana, Rachel E.;Adler, Rachel F.
502 $a Thesis (M.S.)--Northeastern Illinois University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Cyberbullying, or online bullying, is a form of harassment that occurs through the use of digital communication devices and social networking platforms, and ultimately leads to physical or mental harm or distress to the intended target. While the widespread use of social media sites has generated the power for individuals to communicate easily and quickly, it has also caused an increase in cyberbullying incidfents, with offenders experiencing minimal or no consequences. Additionally, cyberbullying can manifest itself in multiple forms, such as harmful text comments and emoticons, as well as negative images or images containing bullying text. Given the increase in cyberbullying and its varying presentation, our goal is to develop a machine learning classification schema to minimize occurrences specifically involving image memes containing text. We describe the methodology for the collection and annotation of an English short text-subjective corpus (~19,000 text comments) created from data extracted from the YouTube API. This corpus consists of current controversial and divisive topics such as politics, religion, gender, and sexual orientation. Based on previous research, several different algorithms will be compared for classifying: a Naive Bayes algorithm, Support Vector Machine (SVM) and a convolutional neural network (CNN). Additionally, we investigate classification accuracy for each of these algorithms on the entire dataset and when placing comments into topic-based groups. Finally, we discuss the limitations of the dataset and explore a set of unsupervised classification techniques for identifying and relabeling incorrectly annotated comments.
590 $a School code: 1696.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Web studies. $3 2122754
650 4 $a Mental health. $3 534751
650 4 $a Information technology. $3 532993
650 4 $a Social research. $3 2122687
650 4 $a Multimedia communications. $3 590562
653 $a Cyberbullying
653 $a Machine learning
653 $a Social media memes
653 $a Digital communication
653 $a Social media
653 $a Bullying online
653 $a Sexual orientation
653 $a Negative images
653 $a Social networking
653 $a YouTube
690 $a 0800
690 $a 0984
690 $a 0489
690 $a 0344
690 $a 0558
690 $a 0646
690 $a 0347
710 2 $a Northeastern Illinois University. $b MS Computer Science. $3 3558102
773 0 $t Masters Abstracts International $g 82-06.
790 $a 1696
791 $a M.S.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28257835