Abstract
Cyberspace has been recognized as a conducive environment for use of various hostile, direct, and indirect behavioural tactics to target individuals or groups. Denigration is one of the most frequently used cyberbullying ploys to actively damage, humiliate, and disparage the online reputation of target by sending, posting, or publishing cruel rumours, gossip, and untrue statements. Previous pertinent studies report detecting profane, vulgar, and offensive words primarily in the English language. This research puts forward a model to detect online denigration bullying in low-resource Hindi language using attention residual networks. The proposed model Hindi Denigrate Comment–Attention Residual Network (HDC-ARN) intends to uncover defamatory posts (denigrate comments) written in Hindi language which stake and vilify a person or an entity in public. Data with 942 denigrate comments and 1499 non-denigrate comments is scraped using certain hashtags from two recent trending events in India: Tablighi Jamaat spiked Covid-19 (April 2020, Event 1) and Sushant Singh Rajput Death (June 2020: Event 2). Only text-based features, that is, the actual content of the post, are considered. The pre-trained word embedding for Hindi language from fastText is used. The model has three ResNet blocks with an attention layer that generates a post vector for a single input, which is passed through a sigmoid activation function to get the final output as either denigrate (positive class) or non-denigrate (negative class). An F-1 score of 0.642 is achieved on the dataset.
- [1] . 2019. Cyberbullying detection on social multimedia using soft computing techniques: A meta-analysis. Multimedia Tools and Applications 78, 17 (2019), 23973–24010.
DOI: DOI: https://doi.org/10.1007/s11042-019-7234-zGoogle ScholarCross Ref
- [2] . 2020. D-BullyRumbler: A safety rumble strip to resolve online denigration bullying using a hybrid filter-wrapper approach. Multimedia Systems (2020), 1–17.
DOI: DOI: https://doi.org/10.1007/s00530-020-00661-wGoogle Scholar - [3] . 2019. Sentiment analysis of multimodal Twitter data. Multimedia Tools and Applications 78, 17 (2019), 24103–24119.
DOI: DOI: https://doi.org/10.1007/s11042-019-7390-1Google ScholarCross Ref
- [4] . 2019. Transcultural communication: Language, communication and culture through English as a lingua franca in a social network community. Language and Intercultural Communication 19, 6 (2019), 471–487.
DOI: DOI: https://doi.org/10.1080/14708477.2019.1606230Google ScholarCross Ref
- [5] . 2020. Morphological segmentation to improve crosslingual word embeddings for low resource languages. ACM Transactions on Asian and Low-Resource Language Information Processing 19, 5 (2020), 1–15.
DOI: DOI: https://doi.org/10.1145/3390298Google ScholarDigital Library
- [6] . 2020. Denigration bullying resolution using wolf search optimized online reputation rumour detection. Procedia Computer Science 173 (2020), 305–314.
DOI: DOI: https://doi.org/10.1016/j.procs.2020.06.036Google ScholarCross Ref
- [7] . 2018. Attention-based ResNet for Chinese text sentiment classification. 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE’18). Atlantis Press, 2018.
DOI: DOI: https://doi.org/10.2991/csece-18.2018.108Google ScholarCross Ref
- [8] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 770–778.
DOI: DOI: https://doi.org/10.1109/CVPR.2016.90Google ScholarCross Ref
- [9] , 2020. Detecting and visualizing hate speech in social media: A cyber watchdog for surveillance. Expert Systems with Applications 113725.
DOI: DOI: https://doi.org/10.1016/j.eswa.2020.113725Google ScholarCross Ref
- [10] . 2020. Vulnerable community identification using hate speech detection on social media. Information Processing & Management 57, 3 (2020), 102087.
DOI: DOI: https://doi.org/10.1016/j.ipm.2019.102087Google ScholarCross Ref
- [11] . 2019. Automatic detection of hate speech on Facebook using sentiment and emotion analysis. In 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC’19). IEEE, 169–174.
DOI: DOI: https://doi.org/10.1109/ICAIIC.2019.8669073Google ScholarCross Ref
- [12] 2019. Improving random forest method to detect hatespeech and offensive word. 2019 International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia. IEEE, 514–518.
DOI: DOI: https://doi.org/10.1109/ICOIACT46704.2019.8938451Google ScholarCross Ref
- [13] . 2019. On transfer learning for detecting abusive language online. In International Work-Conference on Artificial Neural Networks (IWANN’19). Lecture Notes in Computer Science, Vol. 11506. Springer, Cham. 688–700.
DOI: DOI: https://doi.org/10.1007/978-3-030-20521-8_57Google ScholarCross Ref
- [14] . 2018. Verbal aggression detection on Twitter comments: Convolutional neural network for short-text sentiment analysis. Neural Computing and Applications 2018, 1–10.
DOI: DOI: https://doi.org/10.1007/s00521-018-3442-0Google Scholar - [15] . 2020. Improving cyberbullying detection using Twitter users’ psychological features and machine learning. Computers & Security 90, 2020, 101710.
DOI: DOI: https://doi.org/10.1016/j.cose.2019.101710Google ScholarCross Ref
- [16] . 2019. Xbully: Cyberbullying detection within a multi-modal context. In Proceedings of the 12th ACM International Conference on Web Search and Data Mining, 2019. ACM, 339–347.
DOI: DOI: https://doi.org/10.1145/3289600.3291037Google ScholarCross Ref
- [17] . 2019. Multilingual cyber abuse detection using advanced transformer architecture. TENCON 2019—2019 IEEE Region 10 Conference (TENCON), Kochi, India, 2019. IEEE, 784–789.
DOI: DOI: https://doi.org/10.1109/TENCON.2019.8929493Google ScholarCross Ref
- [18] . 2018. Aggression identification and multi lingual word embeddings. In Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC’18), Santa Fe, USA. 74–79. 2018.Google Scholar
- [19] . 2018. Benchmarking aggression identification in social media. In Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC’18), 1–11. 2018.Google Scholar
- [20] . 2019. Mind your language: Abuse and offense detection for code-switched languages. In Proceedings of the AAAI Conference on Artificial Intelligence. 33, 9951–9952.Google Scholar
Digital Library
- [21] . 2019. Aggression detection on multilingual social media text. In 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), IEEE, 1–5.
DOI: DOI: https://doi.org/10.1109/ICCCNT45670.2019.8944868Google ScholarCross Ref
- [22] . 2019. CIT Kokrajhar team: LSTM based deep RNN architecture for hate speech and offensive content (HASOC). Identification in Indo-European languages. In FIRE (Working Notes), 359–365.Google Scholar
- [23] . 2020. Automatic detection of offensive language for Urdu and Roman Urdu. In IEEE Access 8, 91213–91226.
DOI: DOI: https://doi.org/10.1109/ACCESS.2020.2994950Google Scholar - [24] . 2020. DHOT-repository and classification of offensive tweets in the Hindi language. Procedia Computer Science 171, 2324–2333.
DOI: DOI: https://doi.org/10.1016/j.procs.2020.04.252Google ScholarCross Ref
- [25] . 2019. Multilingual cyberbullying detection system. In 2019 IEEE International Conference on Electro Information Technology (EIT’19), Brookings, SD, USA. IEEE, 40--44.
DOI:
10.1109/EIT.2019.8833846Google Scholar
Cross Ref
- [26] . 2020. Aggression identification in English, Hindi and Bangla text using BERT, RoBERTa and SVM. In Proceedings of the 2nd Workshop on Trolling, Aggression and Cyberbullying, Marseille, France. 76–82.Google Scholar
- [27] . 2018. Social media bullying detection using machine learning on Bangla text. In 2018 10th International Conference on Electrical and Computer Engineering (ICECE’18), Dhaka, Bangladesh, 385–388.
DOI: DOI: https://doi.org/10.1109/ICECE.2018.8636797Google Scholar - [28] . 2018. Deep contextualized word representations. (accessed July 10, 2020). Statista. https://www.statista.com.Google Scholar
- [29] . 2016. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), Las Vegas, NV. 770–778.
DOI: DOI: https://doi.org/10.1109/CVPR.2016.90Google ScholarCross Ref
- [30] . 2020. Sarcasm detection in mash-up language using soft-attention based bi-directional LSTM and feature-rich CNN. Applied Soft Computing (2020): 106198.
DOI: DOI: https://doi.org/10.1016/j.asoc.2020.106198Google ScholarCross Ref
- [31] . 2020. Using cognition to resolve duplicacy issues in socially connected healthcare for smart cities. Computer Communications 152 (2020), 272–281.
DOI: DOI: https://doi.org/10.1016/j.comcom.2020.01.041Google ScholarCross Ref
Index Terms
Denigrate Comment Detection in Low-Resource Hindi Language Using Attention-Based Residual Networks
Recommendations
Cyberbullying victimization and substance use among Quebec high schools students: The mediating role of psychological distress
AbstractCyberbullying has become a significant public health issue among youth and is associated with numerous mental health problems. While the majority of studies explored its mental consequences using cross-sectional design, this article ...
Highlights- Cyberbullying victimization, exposure to family violence and gender are significantly associated to psychological distress.
Pathological narcissism, cyberbullying victimization and offending among homosexual and heterosexual participants in online dating websites
Homosexual individuals are exposed to high levels of victimization. However, no studies have examined personality risk factors for cyberbullying victimization and offending among this population. This study investigated the relationships between ...
Bullying victimization and poor relationships with parents as risk factors of problematic internet use in adolescence
AbstractDuring adolescence, adolescents move away from their parents in order to establish their place in society. Therefore, there are two arenas that have a significant impact on adolescents; the family and the social one. Adolescents’ ...
Highlights- Poor parent-child communication and being a cyberbullying victim were related to PIU.






Comments