Topics

Topics of relevance for the conference include, but are not limited to, the following:

Theoretical Foundations of Mining, Inference, and Learning Methods and Algorithms

    Association rule, classification, clustering, indexing, pattern mining, query analysis, and query processing
    Data/entity/event/relationship extraction, integration, cleaning, and summarization
    Anomaly and outlier detection, information retrieval and search, natural language processing, question answering, and recommendation systems
    Asymptotic analysis, intelligence analysis, online and streaming algorithms, and optimization methods
    Dimensionality detection and model selection, feature extraction and selection, kernel methods, matrices and tensors, neural network architectures, probabilistic models and statistical inference, and regression
    Deep and representation learning, reinforcement learning, relational/structured learning, semi-supervised learning, and unsupervised learning
    Few-shot learning, transfer learning, self-supervised learning, meta learning, interpretability, and explainability
    Measurements, evolution, and models of graphs and networks
    Social network/media analysis and dynamics, reputation, influence, trust, opinion mining, sentiment analysis, link prediction, and community detection
    Methods for detecting and combating spamming, trolling, aggression, toxic online behaviors, bullying, hate speech, and low-quality and offensive content
    Semi-structured data, text, web, and social media mining
    Spatio-temporal, time-series, sequential, and streaming data mining
    User activity and behavior data analysis, exploitation, and modeling
    Robustness, sampling, benchmarking, experiments, and evaluations

Big Data Technologies

    Learning-based data cleaning and preparation
    Algorithmically efficient data transformation and integration and the trade-off between the complexity of the transformation and algorithmic efficiency
    Novel algorithmic and statistical techniques for scalable and high-performance big data mining
    Parallel and distributed data mining and searching on emerging architectures
    Analysis, sampling, evaluation, and search in big data and large-scale systems
    Collaborative search, sponsored search, voice search, conversational search, zero-query and implicit search, semantic search, and faceted search
    Human computation and crowdsourcing of big data
    User interfaces and visual analytics of big data analysis

Security, Privacy, Ethics, Information Integrity, and Social Issues

    Modeling credibility, trustworthiness, and reliability
    Privacy-preserving data mining and privacy models
    Ethics of data mining, transparency, algorithmic bias, and fairness models
    Sources, origins, prevalence, and virality of misinformation, and monitoring and detection of misinformation
    Social issues, such as early childhood development, health inequities, mental health and well-being support systems, online education systems, and poverty
    Climate, ecological, and environmental science, and resilience and sustainability

Interdisciplinary Research and Applications of Data Science

    Internet of Things, logistics management, network traffic and log analysis, and supply chain management
    Business and financial data, computational advertising, customer relationship management, intrusion and fraud detection, and intelligent assistants
    Medical and public health applications, drug discovery, healthcare management, and epidemic monitoring and prevention
    Astronomy and astrophysics, genomics and bioinformatics, high energy physics, robotics, and scientific data