| 000 -LEADER |
|---|
| fixed length control field |
04332nam a2200361Ia 4500 |
| 001 - CONTROL NUMBER |
|---|
| control field |
90725 |
| 003 - CONTROL NUMBER IDENTIFIER |
|---|
| control field |
ft7865 |
| 005 - DATE AND TIME OF LATEST TRANSACTION |
|---|
| control field |
20251010150009.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
180324n 000 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Description conventions |
rda |
| 041 ## - LANGUAGE CODE |
|---|
| Language code of text/sound track or separate title |
engtag |
| 050 ## - LIBRARY OF CONGRESS CALL NUMBER |
|---|
| Classification number |
QA76.9 A43 B35 2024 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
. |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Jerry Luck S. Balut, Micah Therese T. Tabon. |
| 245 #0 - TITLE STATEMENT |
|---|
| Title |
Enhancing distilbert algorithm using CNN for image captioning and defending against adversarial attacks in online hate speech. |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE |
|---|
| Place of production, publication, distribution, manufacture |
Manila: |
| Name of producer, publisher, distributor, manufacturer |
PLM, |
| Date of production, publication, distribution, manufacture, or copyright notice |
2024 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
Undergraduate Thesis : (Bachelor of Science in Computer Science) - Pamantasan ng Lungsod ng Maynila, 2024. |
| 336 ## - CONTENT TYPE |
|---|
| Content type code |
text |
| Content type term |
text |
| Source |
text |
| 337 ## - MEDIA TYPE |
|---|
| Media type code |
unmediated |
| Media type term |
unmediated |
| Source |
unmediated |
| 338 ## - CARRIER TYPE |
|---|
| Carrier type code |
volume |
| Carrier type term |
volume |
| Source |
volume |
| 344 ## - SOUND CHARACTERISTICS |
|---|
| Type of recording |
0 |
| 347 ## - DIGITAL FILE CHARACTERISTICS |
|---|
| File type |
0 |
| 385 ## - AUDIENCE CHARACTERISTICS |
|---|
| Audience term |
2 |
| 505 ## - FORMATTED CONTENTS NOTE |
|---|
| Formatted contents note |
ABSTRACT: The task of hate speech detection has garnered significant attention in the research community, employing machine learning algorithms and natural language processing (NLP) for classification. As hate speech proliferates, its profound influence on society can lead to negative consequences. As such, it is crucial to establish mechanisms to detect hate speech accurately to minimize its presence on social media. Through this research, the researchers could discern three main points of interest to improve the hate speech detection of the DistilBERT algorithm. DistilBERT is limited to textual data, which poses a challenge for hate speech detection that extends to diverse data formats like images and videos. The model’s limitations also encompass its inability to detect hate speech written in leetspeak and its susceptibility to false predictions caused by beningn word insertions, presenting a gap in comprehensive hate speech identification. The enhancement by the researcher, hate speech detection in images, is made possible using convolutional neural networks (CNN). In addition to this, hate speech containing leetspeak and benign word insertion can now be detected correctly. An optical character recognition (OCR) engine was used to decode the text to address the limitation of hate speech detection in leetspeak. Contextual understanding and polarity scores were established to deal with false predictions due to benign word insertions. Based on the results, the proposed DistilBERT algorithm presents notable advancements over the existing algorithm in terms ofprecision, F1 score, and accuracy while maintaining a competitive level of recall. |
| 506 ## - RESTRICTIONS ON ACCESS NOTE |
|---|
| Terms governing access |
5 |
| 520 ## - SUMMARY, ETC. |
|---|
| Summary, etc. |
ABSTRACT: The task of hate speech detection has garnered significant attention in the research community, employing machine learning algorithms and natural language processing (NLP) for classification. As hate speech proliferates, its profound influence on society can lead to negative consequences. As such, it is crucial to establish mechanisms to detect hate speech accurately to minimize its presence on social media. Through this research, the researchers could discern three main points of interest to improve the hate speech detection of the DistilBERT algorithm. DistilBERT is limited to textual data, which poses a challenge for hate speech detection that extends to diverse data formats like images and videos. The model's limitations also encompass its inability to detect hate speech written in leetspeak and its susceptibility to false predictions caused by beningn word insertions, presenting a gap in comprehensive hate speech identification. The enhancement by the researcher, hate speech detection in images, is made possible using convolutional neural networks (CNN). In addition to this, hate speech containing leetspeak and benign word insertion can now be detected correctly. An optical character recognition (OCR) engine was used to decode the text to address the limitation of hate speech detection in leetspeak. Contextual understanding and polarity scores were established to deal with false predictions due to benign word insertions. Based on the results, the proposed DistilBERT algorithm presents notable advancements over the existing algorithm in terms ofprecision, F1 score, and accuracy while maintaining a competitive level of recall. |
| 526 ## - STUDY PROGRAM INFORMATION NOTE |
|---|
| Classification |
Fiction |
| 540 ## - TERMS GOVERNING USE AND REPRODUCTION NOTE |
|---|
| Terms governing use and reproduction |
5 |
| 655 ## - INDEX TERM--GENRE/FORM |
|---|
| Genre/form data or focus term |
academic writing |
| 800 ## - SERIES ADDED ENTRY--PERSONAL NAME |
|---|
| Title of a work |
0 |
| 830 ## - SERIES ADDED ENTRY--UNIFORM TITLE |
|---|
| Language of a work |
0 |
| 942 ## - ADDED ENTRY ELEMENTS |
|---|
| Item type |
Thesis/Dissertation |
| Source of classification or shelving scheme |
|