Identification of cyberbullying: A deep learning based multimodal approach
- PDF / 1,778,782 Bytes
- 20 Pages / 439.642 x 666.49 pts Page_size
- 53 Downloads / 295 Views
Identification of cyberbullying: A deep learning based multimodal approach Sayanta Paul1 · Sriparna Saha1
· Mohammed Hasanuzzaman2
Received: 4 April 2020 / Revised: 3 July 2020 / Accepted: 13 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Cyberbullying can be delineated as a purposive and recurrent act, which is aggressive in nature, done via different social media platforms such as Facebook, Twitter, Instagram and others. While existing approaches for detecting cyberbullying concentrate on unimodal approaches, e.g., text or visual based methods, we proposed a deep learning based early identification framework which is a multimodal (textual and visual) approach (inspired by the informal nature of social media data) and performed a broad analysis on vine dataset. Early identification framework predicts a post or a media session as bully or non-bully as early as possible as we have processed information for each of the modalities (both independently and fusion-based) chronologically. Our multimodal feature-fusion based experimental analysis achieved 0.75 F-measure using ResidualBiLSTM-RCNN architecture, which clearly reflects the effectiveness of our proposed framework. All the codes of this study are made publicly available on paper’s companion repository. Keywords Cyberbullying · Multimodal information fusion · Deep learning
1 Introduction With the exponential growth of digitization, e.g., use of different forms of social media platforms, where people can share and express their insights and feelings freely and publicly with others, which may come in different modalities, e.g., text, audios, videos, gestures and https://github.com/sayantapaul/Multimodal-Cyberbullying-Identification Sayanta Paul
[email protected] Sriparna Saha [email protected] Mohammed Hasanuzzaman [email protected] 1
Indian Institute of Technology Patna, Bihta, India
2
Cork Institute of Technology Cork, Cork, Ireland
Multimedia Tools and Applications
Fig. 1 Utterances from both textual and visual content of a post are fused to capture meaningful multimodal information
so on - misuse of this medium to promote offensive and hateful language, which may include harassment of regular users in the form of stalking, affects business of online companies, and may even have severe real-life consequences. Due to this unrestricted nature of viability of internet, all these activities can be appeared as an assortment of tech-empowered exercises, e.g., photo and video sharing, blogging, business networks, comments & reviews and many others which introduce continuous harassment and stalking which are commonly referred as cyberbullying [28]. Broadly cyberbullying can come up of different forms such as racism (e.g., facial features, skin colour), sexism (e.g., male, female), physical appearance (e.g., ugly, fat), intelligence (e.g., ass, stupid) and so on. Sometimes this act of cyberbullying is anonymous1 , i.e., quite hard to trace, which has intense and devastating effects. Therefore detect
Data Loading...
