Gianluca Moro (PhD) carries out teaching and research activities in the areas of machine learning, data mining, text analytics & deep learning for natural language processing. His scientific contributions focus also on supervised and semi-supervised methods for dealing with domains lacking or with insufficient labeled data, the main drawback that prevents the applicability to real life problems of the most powerful supervised machine learning solutions as well. In particular he contributed to approaches for transfer learning from source domains of pre-labeled data to semantically different target domains with unlabelled data. He worked to several european, national and industrial research projects, heading also research unit and supervising PhD students, in particular recently GenData on data driven genomic computing, Toreador for advanced business analytics, LAILA for legal text analytics, RINGRID, DORII and Autonomic Security regarding grid computing and data-centric sensor networks. He organised and chaired several editions of international conferences, such as ACM International Conference on Intelligent Agent Technology, Agents and Peer-to-Peer Computing, Database Information Systems and P2P Computing etc. He co-authored seventy scientific publications in international conferences, workshops, books, journals, co-edited five books and has served in more than fifty program committees among international conferences, workshops and as journal referee.
The goal of the course unit is to present theoretical and practical aspects of text mining regarding text classification and sentiment analysis & opinion mining.
The learning outcomes are technical capabilities of coping with text processing, text classification, sentiment analysis & opinion mining, transfer learning, using also deep neural networks, language models and explanation text mining.
Data Science and Business AnalyticsThis course aims at providing students with a basic understanding of the theoretical foundations, the computational properties and the uses of some of the most common supervised and unsupervised learning techniques as well as of the principles and the main use cases of the data mining algorithms. At the end of the course, students will be able to set classification, clustering and rule discovery problems, using modern machine learning methods and libraries. Moreover, they will be able to understand and apply a wide set of analysis algorithms to extract from large datasets useful relationships. The students can also design a process of data selection, transformation, analysis and interpretation to support strategic decisions.