A5011009667- Hate Speech and Cyberbullying Detection
- Internet Traffic Analysis and Secure E-voting
- Advanced Malware Detection Techniques
- Bullying, Victimization, and Aggression
- Spam and Phishing Detection
- Adversarial Robustness in Machine Learning
- Numerical methods in engineering
- Social Media and Politics
- Network Security and Intrusion Detection
Indian Institute of Technology Patna
2018-2023
Hate speech is now a frequent occurrence on social media. Recently, the majority of study was devoted to identifying hate in languages with abundant resources (e.g., English). However, relatively few works are developed for limited Hindi, third most widely used language earth). In this study, Hindi Language Dataset (HHLD) created following novel hierarchical fine-grained four-layer annotation approach. The top layer separates posts into hateful and non-hateful categories. second further...
The phenomenal growth on the internet has helped in empowering individual's expressions, but misuse of freedom expression also led to increase various cyber crimes and anti-social activities. Hate speech is one such issue that needs be addressed very seriously as otherwise, this could pose threats integrity social fabrics. In paper, we proposed deep learning approaches utilizing embeddings for detecting types hate speeches media. Detecting from a large volume text, especially tweets which...
In this paper we built several deep learning architectures to participate in shared task OffensEval: Identifying and categorizing Offensive language Social media by semEval-2019. The dataset was annotated with three level annotation schemes detect between offensive not offensive, categorization target identification contents. Deep models POS information as feature were also leveraged for classification. best that performed on individual sub tasks are stacking of CNN-Bi-LSTM Attention, BiLSTM...
Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. Most existing speech detection solutions have utilized the features by treating each post as an isolated input instance classification. This paper addresses this issue introducing unique model that improves identification English utilising intra-user...
With the exponential rise in user-generated web content on social media, proliferation of abusive languages towards an individual or a group across different sections internet is also rapidly increasing. It very challenging for human moderators to identify offensive contents and filter those out. Deep neural networks have shown promise with reasonable accuracy hate speech detection allied applications. However, classifiers are heavily dependent size quality training data. Such high-quality...
The increase in usage of the internet has also led to an unsocial activities, hate speech is one them. Hate over a few years been biggest problems and automated techniques need be developed detect it. This paper aims use eight publicly available Hindi datasets explore different deep neural network aggression, hate, abuse, etc. We experimented on multilingual-bidirectional encoder representations from transformer (M-BERT) multilingual for Indian languages (MuRIL) four settings (i) Single task...
In recent years, the increasing propagation of hate speech on social media has encouraged researchers to address problem hateful content identification. To build an efficient detection model, a large number annotated data is needed train model. solve this approach we utilized eleven datasets from domain and compared different transformer encoder-based approaches such as BERT, ALBERT in single-task learning multi-task (MTL) framework. We also leveraged eight sentiment emotion analysis...