2020
DOI: 10.1609/icwsm.v14i1.7345
|View full text |Cite
|
Sign up to set email alerts
|

Aggressive, Repetitive, Intentional, Visible, and Imbalanced: Refining Representations for Cyberbullying Classification

Abstract: Cyberbullying is a pervasive problem in online communities. To identify cyberbullying cases in large-scale social networks, content moderators depend on machine learning classifiers for automatic cyberbullying detection. However, existing models remain unfit for real-world applications, largely due to a shortage of publicly available training data and a lack of standard criteria for assigning ground truth labels. In this study, we address the need for reliable data using an original annotation framework. Inspi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2021
2021
2025
2025

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 24 publications
(3 citation statements)
references
References 28 publications
0
3
0
Order By: Relevance
“…For Neural Network models, GloVe (Global Vectors) has been used to perform these word transformations (Ziems et al, 2020 ). It is an established unsupervised learning approach for creating word embeddings, which are vector representations of words in a high-dimensional space and uses word co-occurrence data from a corpus to learn about the semantic and syntactic links between words (Wang et al, 2021 ).…”
Section: Proposed Frameworkmentioning
confidence: 99%
“…For Neural Network models, GloVe (Global Vectors) has been used to perform these word transformations (Ziems et al, 2020 ). It is an established unsupervised learning approach for creating word embeddings, which are vector representations of words in a high-dimensional space and uses word co-occurrence data from a corpus to learn about the semantic and syntactic links between words (Wang et al, 2021 ).…”
Section: Proposed Frameworkmentioning
confidence: 99%
“…Image deepfakes are often underrated but it is still as menacing as the rest [5]. In the first quarter of 2023, a picture of Pope Francis putting on an expensive Balenciaga cloth was all over social media [6]; the image generated a lot of traffic and criticism on Facebook and Twitter simultaneously.…”
Section: Introductionmentioning
confidence: 99%
“…Such systems can augment the abilities of content moderators of online platforms so that they can intervene and mitigate behaviors that may be deemed inappropriate per the norms of a community (Van Cleemput, Vandebosch, and Pabian 2014). However, recent work (Ziems, Vigfusson, and Morstatter 2020) points out key limitations, such as the lack of publicly available training data and a robust standard for determining ground truth, that have made existing cyberbullying detection algorithms unfit for real-world use. Notably, to date, most research on automated detection of cyberbullying has leveraged third-party annotators or "outsiders" (rather than victims or "insiders") to label training datasets for cyberbullying ground truth, e.g., (Singh, Ghosh, and Jose 2017;Kwak, Blackburn, and Han 2015), which may not be sensitive to the victims' narratives regarding their own experiences.…”
Section: Introductionmentioning
confidence: 99%