This edited book covers ongoing research in both theory and practical applications of using deep learning for social media data. Social networking platforms are overwhelmed by different contents, and their huge amounts of data have enormous potential to influence business, politics, security, planning and other social aspects. Recently, deep learning techniques have had many successful applications in the AI field. The research presented in this book emerges from the conviction that there is still much progress to be made toward exploiting deep learning in the context of social media data analytics. It includes fifteen chapters, organized into four sections that report on original research in network structure analysis, social media text analysis, user behaviour analysis and social media security analysis. This work could serve as a good reference for researchers, as well as a compilation of innovative ideas and solutions for practitioners interested in applying deep learning techniques to social media data analytics.
Author(s): Tzung-Pei Hong, Leticia Serrano-Estrada, Akrati Saxena, Anupam Biswas
Series: Studies in Big Data, 113
Publisher: Springer
Year: 2022
Language: English
Pages: 296
City: Cham
Preface
Contents
Network Structure Analysis
Node Classification Using Deep Learning in Social Networks
1 Introduction
1.1 Applications
2 Preliminaries
3 Community-Based Node Classification
3.1 script upper AmathcalAuto-script upper EmathcalEncoder-Based Approaches
3.2 script upper GmathcalGenerative script upper AmathcalAdversarial Network-Based Approaches
3.3 script upper GmathcalGraph script upper CmathcalConvolution Network-Based Approaches
3.4 Integrating Un-directed Graphical Models and script upper GmathcalGraph script upper CmathcalConvolution Networks
3.5 Random Walk Based Methods
4 Role-Based Node Classification
5 Conclusion and Future Direction
References
NN-LP-CF: Neural Network Based Link Prediction on Social Networks Using Centrality-Based Features
1 Introduction
2 Preliminaries
2.1 Social Network
2.2 Social Graph
2.3 Social Network Analysis
2.4 Centrality Measures
3 Link Prediction
4 Experimental Discussion
5 Conclusion
References
Social Media Text Analysis
Deep Learning for Code-Mixed Text Mining in Social Media: A Brief Review
1 Introduction
2 Code-Mixed Text Mining
2.1 Word Embedding
2.2 Language Detection
2.3 Sentiment Analysis
2.4 Hate Speech Detection
2.5 Stance Detection
2.6 Question Answering
2.7 Machine Translation
2.8 Named Entity Recognition (NER)
2.9 Part of Speech (POS) Tagging
2.10 Parsing
3 Conclusion and Future Direction
References
Convolutional and Recurrent Neural Networks for Opinion Mining on Drug Reviews
1 Introduction
2 Opinions Mining/Sentiment Analysis Generality
3 Existing Works on Drug Reviews
4 Convolutional and Recurrent Neuronal Networks
4.1 CNN (Convolutional Neuronal Network)
4.2 RNN (Recurrent Neural Networks)
4.3 BiRNN (Bidirectional Recurrent Neuronal Network)
4.4 Hybrid Models
5 Experiment and Results
5.1 Hyper-Parameters and Training
5.2 Results and Discussion
6 Conclusion
References
Text-Based Sentiment Analysis Using Deep Learning Techniques
1 Introduction
2 Related Work
3 Taxonomy of Sentiment Analysis Methods
3.1 Machine Learning Methods
3.2 Lexicon Based Methods
3.3 Hybrid Methods
3.4 Other Methods
4 Deep Learning Architectures for Sentiment Analysis
4.1 Convolutional Neural Networks (CNN)
4.2 Recurrent Neural Networks (RNN)
4.3 Long Short-Term Memory (LSTM)
4.4 Gated Recurrent Unit (GRU)
4.5 Bi-LSTM (Bidirectional LSTM)
5 Experimental Work
5.1 Dataset Description
5.2 Data Pre-processing
5.3 Feature Extraction
5.4 Classification Algorithms
5.5 Evaluation Measures
5.6 Hyperparameters of Deep Learning Models
6 Results and Discussion
7 Conclusion
References
Social Sentiment Analysis Using Features Based Intelligent Learning Techniques
1 Introduction
2 Related Work
3 Proposed Methodology
3.1 Dataset
3.2 Pre-processing
3.3 Categorization of Sentiment Polarity
3.4 Classification Using Machine Learning Algorithms
4 Implementation and Result Analysis
4.1 Result Analysis
5 Discussions
6 Conclusion
References
User Behaviour Analysis
Modified-PIP with Deep Neural Network (DNN) Architecture: A Coherent Recommendation Framework for Capturing User Behaviour
1 Introduction
2 Related Background
2.1 Common Recommendation Approaches
2.2 Recommendation System Based on Neural Network Approaches
3 Experimental Methodology
3.1 Similarity Measure
3.2 Deep Neural Network (DNN)
4 Proposed Model
5 Experimental Outcomes and Investigation
6 Conclusion and Future Work
References
A Survey on Graph Neural Network Based Video Recommendation System
1 Introduction
2 Preliminaries of Video Recommendation Systems and Challenges Associated with the Field
3 Findings
3.1 Simple Recommendation System
3.2 Content Based Recommendation System
3.3 Collaborative Filtering Based Recommendation System
3.4 Hybrid Recommendation System
4 Why Do We Need GNN Based Video Recommendation System?
5 GNN Models for Video Recommendation
6 Comparison of Different Models
6.1 Addressing Cold Start Problem
7 Application
8 Data Privacy
9 Conclusions and Future Scope
References
Characterisation of Mental Health Conditions in Social Media Using Deep Learning Techniques
1 Introduction
2 Mental-Health Detection Techniques
2.1 Stress Detection
2.2 Anxiety Prediction
2.3 Depression Detection
2.4 Anorexia Prediction
2.5 Suicide Prediction
2.6 Predicting Multiple Mental-Health Conditions
3 Datasets
4 Conclusion and Future Directions
References
Predicting Mental Health and Nutritional Status from Social Media Profile Using Deep Learning
1 Introduction
1.1 Related Studies
1.2 Scope for Contribution
1.3 Research Objectives
2 Methodology
2.1 Used Model
2.2 Dataset Details and Pre-processing
3 Results
3.1 Results Obtained from Convolutional Neural Network
3.2 Results Obtained from Simple Recurrent Neural Network
3.3 Results Obtained from Long Short-Term Memory Network
4 Discussions
4.1 Comparison
4.2 Prediction of Mental Health and Nutritional Status
5 Conclusion and Future Work
References
Impact of Artificial Intelligence-Based Chatbots on Customer Engagement and Business Growth
1 Introduction
2 Chat Bot in Customers Engagement
3 Chatbot for Businesses Growth
3.1 Increased Customer Engagement
3.2 Improve Lead Generation
4 Customer Service with Automation
5 Usage of AI Chatbot by Brands
5.1 Emirates Vacations Introduces a Chatbot to Their Banner Advertisements
5.2 Domino's
5.3 KIAN Chatbot
5.4 Kiehl's
5.5 The Wall Street Journal
5.6 Hazel
5.7 Spotify
5.8 Staples
5.9 Uber
5.10 Starbucks
5.11 Nike
6 Conclusion
References
Social Media Security Analysis
Do Not `Fake It Till You Make It'! Synopsis of Trending Fake News Detection Methodologies Using Deep Learning
1 Introduction
2 Formal Problem Definition
3 Deep Learning Techniques for Fake News Detection
3.1 Misinformation
3.2 Clickbait
3.3 Satire
3.4 Deepfake
4 Limitations of Deep Learning Approaches
5 Fairness and Interpretability
6 Emerging Trends
References
Towards Detecting Fake Spammers Groups in Social Media: An Unsupervised Deep Learning Approach
1 Introduction
2 Literature Review
3 Learning-Based Algorithms
4 Unsupervised Algorithms
5 Framework and Libraries
6 Practical Implementation
7 Conclusion
References
A Deep Learning Approach for Anomalous User-Intrusion Detection in Social Media Network System
1 Introduction
1.1 Intrusion Detection Methods
1.2 Motivation
2 Literature Review
3 Proposed Work
3.1 Methodology
3.2 Dataset Description
3.3 Pre-processing the Dataset
4 Experimental Details
5 Results
5.1 Discussion
6 Conclusion
7 Future Scope
References
Deep Digging of Anomalous Transactions in Financial Networks with Imbalanced Data
1 Introduction
1.1 Motivation
2 Literature Review
2.1 Anomaly Detection Using Deep Learning
2.2 Imbalanced Data
2.3 Ensemble Learning
3 Methodology
3.1 Data
3.2 Subset Resampling
3.3 Performance Metrics
4 Experiments and Analysis
5 Conclusion
References
