The abundance of available data that is retrieved from or is related to the areas of Humanities and the human condition challenges the research community in processing and analyzing it. The aim is two-fold: on the one hand, to extract knowledge that will help understand human behavior, creativity, way of thinking, reasoning, learning, decision making, socializing and even biological processes; on the other hand, to exploit the extracted knowledge by incorporating it into intelligent systems that will support humans in their everyday activities.
The nature of humanistic data can be multimodal, semantically heterogeneous, dynamic, time and space-dependent, and highly complicated. Translating humanistic information, e.g. behavior, state of mind, artistic creation, linguistic utterance, learning and genomic information into numerical or categorical low-level data is a significant challenge on its own. New techniques, appropriate to deal with this type of data, need to be proposed and existing ones adapted to its special characteristics.
The workshop aims to bring together interdisciplinary approaches that focus on the application of innovative as well as existing data matching, fusion and mining and knowledge discovery and management techniques (like decision rules, decision trees, association rules, ontologies and alignments, clustering, filtering, learning, classifier systems, neural networks, support vector machines, preprocessing, post processing, feature selection, visualization techniques) to data derived from all areas of Humanistic Sciences, e.g. linguistic, historical, behavioral, psychological, artistic, musical, educational, social etc., Ubiquitous Computing and Bioinformatics.
Ubiquitous Computing applications (aka Pervasive Computing, Mobile Computing, Ambient Intelligence, etc.) collect large volumes of usually heterogeneous data in order to effect adaptation, learning and in general context awareness. Data matching, fusion and mining techniques are necessary to ensure human centred application functionality.
An important aspect of humanistics centers around managing, processing and computationally analyzing Biological and Biomedical data. Hence, one of the aims of this workshop will be to also attract researchers that are interested in designing, developing and applying efficient data and text mining techniques for discovering the underlying knowledge existing in Biomedical data, such as sequences, gene expressions and pathways.
Topics of interest include but are not limited to:
- Humanistic data collection and interpretation
- Data pre-processing
- Feature selection methodologies
- Supervised or unsupervised learning of humanistic knowledge
- Clustering/Classification techniques
- Fuzzy modeling
- Heterogeneous data fusion
- Knowledge representation and reasoning
- Linguistic data mining
- Educational data mining
- Music information retrieval
- Data-driven profiling/ personalization
- User modeling
- Behavior prediction
- Recommender systems
- Web sentiment analysis
- Social data mining
- Data visualization techniques
- Integration of data mining results into real-world applications with humanistic context
- Ontologies, ontology matching and alignment
- Mining humanistic data in the cloud
- Game data mining
- Virtual-world data mining
- Speech and audio data processing
- Data mining techniques for knowledge discovery
- Biomedical data mining
- Content creation, annotation and modeling for semantic and social web
- Computational intelligence for media adaptation and personalization
- Semantics-driven indexing and retrieval of multimedia contents
- Semantic context modeling and extraction
- Context-aware applications
- Social web economics and business
- Privacy/security issues in social and personalized applications
- Privacy preserving data mining and social networks
- Social data analytics