A5025618229- Sentiment Analysis and Opinion Mining
- Language, Metaphor, and Cognition
- Hate Speech and Cyberbullying Detection
- Humor Studies and Applications
- Topic Modeling
- Internet Traffic Analysis and Secure E-voting
- Advanced Malware Detection Techniques
- Spam and Phishing Detection
- Advanced Text Analysis Techniques
- Misinformation and Its Impacts
- Comics and Graphic Narratives
- Digital Communication and Language
- Text and Document Classification Technologies
Jamia Millia Islamia
2018-2021
Adversaries and anti-social elements have exploited the rapid proliferation of computing technology online social media in form novel security threats, such as fake profiles, hate speech, bots, rumors. The speech problem on networks (OSNs) is also widespread. existing literature has machine learning approaches for detection OSNs. However, effectiveness contextual information at different orientations understudied. This study presents a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Online social networks(OSNs) face the challenging problem of hate speech, which should be moderated for growth OSNs. The machine learning approaches dominate existing set speech detection. In this study, we introduce BiCHAT: a novel BiLSTM with deep CNN and Hierarchical ATtention-based model tweet representation toward proposed takes tweets as input passes through BERT layer followed by an attention-aware convolutional layer. encoded further Bidirectional LSTM network. Finally, labels...
The frequent usage of figurative language on online social networks, especially Twitter, has the potential to mislead traditional sentiment analysis and recommender systems. Due extensive use slangs, bashes, flames, non-literal texts, tweets are a great source language, such as sarcasm, irony, metaphor, simile, hyperbole, humor, satire. Starting with brief introduction its various categories, this article presents an in-depth survey state-of-the-art techniques for computational detection...
Sarcasm is a special category of figurative language, which mainly used in online social media to convey messages with implicit semantics and criticism. Such are for sarcastic remarks using contemptuous, ridicule, bitter, taunt, mock related words or phrases. Though sarcasm detection well-considered problem by the researchers, best our knowledge, none them has considered self-deprecating sarcasm, users deprecate criticize themselves In this paper, we propose novel approach an amalgamation...
Online social media (OSM) communications sometimes turn into hate-filled and offensive comments or arguments. It not just disrupts the fabric online, but also leads to hate, violence, crime, in real physical world worst scenarios. The existing content moderation practices of OSM platforms often fail control online hate. In this article, we develop a deep learning model called <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Satire is prominent in user-generated content on various online platforms the form of satirical news, customer reviews, blogs, articles, and short messages that are typically an informal nature. As satire also used to disseminate false information Internet, its computational detection has become a well-known issue. Existing work focuses primarily formal document- or sentence-level textual data, whereas texts have gotten less attention for detection. This paper presents new model called...
Fake news is a pervasive phenomenon over online social media platforms. The computation detection of fake well-known problem. Financial has immense potential to mislead the financial domain, but it drawn less attention from researchers. In this paper, we introduce new approach for detection. Starting with preparing datasets using topic modelling and Transformer-based techniques. We two cross-joint networks. first network - CAEN used give context-aware linguistic embeddings. combined...
Stance detection has been gaining popularity in text mining and information retrieval-based research. Recognition of sentiment also plays an important role the analysis whether underline stances are favor or against for a particular domain. However, there is extensive research this direction, but considering its impact on financial not explored yet. This paper presents new deep learning based multi-task approach stance detection. A model called Fin-STance introduced which performs...