The thematic area “Data Science” comprises the study of methods, models, algorithms, approaches, and languages for the management, analysis, and extraction of knowledge from complex and heterogeneous data, such as texts, images, videos, networks, structured data, geo-referenced, multi-media, and multi-dimensional data, varying with time.
The general goal consists in favouring the enrichment of the data themselves, on the one side in an explicit way, by providing semantic information through the use of semantic technologies of artificial intelligence and data analytics, and on the other side in an implicit way, by automatically extracting domain knowledge by means of computational intelligence and machine learning techniques.
From the application point of view, the techniques developed in the research groups referring to this area allow making the activities of business analytics, decision support, and content support and fruition more efficient and reliable. In this perspective, it is of high relevance the fact that the solutions (models, languages, algorithms) proposed to be specified in terms of scalable data processing computational schemes, suitable for the volumes, variety, and speed of complex data resulting from the above-mentioned application scenarios.
The research agenda comprises:
- Social network analysis and recommender systems, aiming at analyzing the interactions among users and those among users and systems;
- Business process management, aiming at monitoring and improving process management and execution;
- Knowledge graphs and Semantic Web, aiming at improving advanced information filtering mechanisms;
- Logistic management and operation research, for the planning of transport networks and logistics;
- Automatic knowledge extraction from data, for descriptive/predictive analyses, and the creation of knowledge bases for Decision Support Systems