PON R&C 2007-2013 Progetto SINTESYS Security and INTElligence SYSstem
Selected Publications:

Pilato, G., & Vassallo, G. (2014), TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm, In IEEE Transactions on Emerging Topics in Computing. Volume:3 ,  Issue: 2  pp 185 – 192

D’Avanzo, E., & Pilato, G. (2014). Mining social network users opinions’ to aid buyers’ shopping decisions. Computers in Human Behavior. Volume 51, Part B, October 2015, Pages 1284–1294

 Terrana, D., Augello, A., & Pilato, G. (2014). Analysis of Facebook Users’ Relationships Through Sentiment Classification: A Case Study of Italian Politicians. International Journal of Semantic Computing, 8(03), 301-317. 

Pilato, G., Augello, A., & Gaglio, S. (2012). A modular system oriented to the design of versatile knowledge bases for chatbots. ISRN Artificial Intelligence, 2012. Volume 2012 (2012), Article ID 363840, 10 pages

Augello, A., Gaglio, S., Oliveri, G., & Pilato, G. (2013). An algebra for the manipulation of conceptual spaces in cognitive agents. Biologically Inspired Cognitive Architectures, Volume 6, October 2013, Pages 23–29

Augello, A., Infantino, I., Pilato, G., Rizzo, R., & Vella, F. (2014). Creativity evaluation in a cognitive architecture. Biologically Inspired Cognitive Architectures. Volume 11, January 2015, Pages 29–37

Augello, A., Gentile, M., Pilato, G., & Vassallo, G. (2014). A Geometric Algebra Based Distributional Model to Encode Sentences Semantics. In Distributed Systems and Applications of Information Filtering and Retrieval (pp. 101-114). Springer Berlin Heidelberg.

Spiccia, C., Augello, A., Pilato, G., & Vassallo, G. (2015, February). A word prediction methodology for automatic sentence completion. In Semantic Computing (ICSC), 2015 IEEE International Conference on (pp. 240-243). IEEE.

 Terrana, D., Augello, A., & Pilato, G. (2015, February). A system for analysis and comparison of social network profiles. In Semantic Computing (ICSC), 2015 IEEE International Conference on (pp. 109-115). IEEE.

Sangiorgi, P., Augello, A., & Pilato, G. (2014). An approach to detect polarity variation rules for sentiment analysis. In Proc of WEBIST 2014–10th international conference on web information systems and technologies, 3–5 April.

Terrana, D., Augello, A., & Pilato, G. (2014, June). Automatic Unsupervised Polarity Detection on a Twitter Data Stream. In Semantic Computing (ICSC), 2014 IEEE International Conference on (pp. 128-134). IEEE.

Augello, A., Infantino, I., Pilato, G., Rizzo, R., & Vella, F. (2014). Combining Representational Domains for Computational Creativity. In Proceedings of 5th international conference on computational creativity, ICCC 2014, June.

Chella, A., Gaglio, S., Augello, A., Pilato, G. (2014). Creativity in conceptual spaces. In Proceedings of 5th international conference on computational creativity, ICCC 2014, June.

Terrana, D., Augello, A., & Pilato, G. (2014, June). Facebook Users Relationships Analysis Based on Sentiment Classification. In Semantic Computing (ICSC), 2014 IEEE International Conference on (pp. 290-296). IEEE.

Mazzonello, V., Gaglio, S., Augello, A., & Pilato, G. (2013, September). A Study on Classification Methods Applied to Sentiment Analysis. In Semantic Computing (ICSC), 2013 IEEE Seventh International Conference on (pp. 426-431). IEEE.

Augello, A., Gaglio, S., Oliveri, G., & Pilato, G. (2013). Acting on Conceptual Spaces in Cognitive Agents. In AIC@ AI* IA (pp. 25-32).

Sangiorgi, P., Augello, A., & Pilato, G. (2013, September). An unsupervised data-driven cross-lingual method for building high precision sentiment lexicons. In Semantic Computing (ICSC), 2013 IEEE Seventh International Conference on (pp. 184-190). IEEE.

Terrana, D., & Pilato, G. (2013, September). Detection, Clustering and Tracking of Life Cycle Events on Twitter Using Electric Fields Analogy. In Semantic Computing (ICSC), 2013 IEEE Seventh International Conference on (pp. 220-227). IEEE 

Augello, A., Gentile, M., Pilato, G., & Vassallo, G. (2012). Geometric Encoding of Sentences based on Clifford Algebra. In KDIR 2012 – Proceedings of the International Conference on Knowledge Discovery and Information Retrieval 10/2012 KDIR (pp. 457-462).

PON R&C 2007-2013 Progetto SINTESYS Security And INTElligence SYSstem

General objective

The SINTESYS project addresses the problem of homeland security according to an integrated perspective that summarizes studies conducted on different scientific and technological areas in order to discover and prevent situations of real danger for the community.

An in-depth Intelligence process is thus conducted through the acquisition of as much information as possible on the situations of interest in order to deduce useful information during a decision-making phase.

In particular, the goal is to design an intelligent system able to analyze, predict and investigate in an integrated, coherent and consistent way, sources of “open” (OSINT – Open Source INTelligence), multi-modal data (such as texts, images, videos, audio recordings, etc.) in order to discover the presence of links and relationships which the separate evaluation of the single sources would not be able to highlight. This approach could give a significant contribution to public safety.

Site: http://sintesys.eng.it/

Contribution gave by ICAR

  • Study and development of text mining methodologies based on the induction of semantic spaces and on the subsequent identification of primitive concepts automatically induced starting from a corpus of texts;
  • Identification and development of predominantly sub-symbolic models of knowledge representation, that can be useful for semantic annotation and for fusion of information;
  • Automatic induction of semantic/conceptual spaces;
  • Using the Latent Semantic Analysis paradigm as an estimator and an innovative coding of sentences in conceptual spaces;
  • Using of machine learning methodologies for text analysis aimed at clustering and classifying potentially dangerous events/profiles;
  • Implementation of thematic crawlers, information retrieval (IR) for security and information extraction (IE) for security. 
Back To Top