Domain-specific organization management processes require particular operations and information exchange. A large amount of information concerning these tasks has to be reported and capitalized. Usually, people working in big organizations use Information Systems (IS) and other collaborative software producing a large number of information sources (data, documents, e-mails, images, etc.). The methodology presented in this paper concentrates on the contribution of semantic knowledge within textual information to improve processes carried out in domain-specific organizations. For example, activity logs, technical reports or contracts represent a part of structured textual knowledge. E-mails or texts describing activities are a part of unstructured (or semi-structured) knowledge and often contain important information to support decision-makers. Therefore, people involved in these processes need to analyze such documents to enrich their knowledge about said processes. Hence, the present methodology concerns the use of textual analysis approaches in order to evaluate their contribution to expert’s activities. The experts are the human resources with specific competences involved in processes that require particular analyses. The methodology proposed is focused on an automatic semantic annotation technique considering the most important entities and their significance within specific domains. It works on the different kinds of textual knowledge (structured and unstructured) and allows to construct the most representative document classification label. In particular, the proposed method uses results of semantic annotation techniques to optimize document classification and, consequently, to support the decision-making process. This methodological proposal is the result of a work experience within a company operating in the energy sector.

Semantic annotation to support decision-making

Francesca Parisi
2016-01-01

Abstract

Domain-specific organization management processes require particular operations and information exchange. A large amount of information concerning these tasks has to be reported and capitalized. Usually, people working in big organizations use Information Systems (IS) and other collaborative software producing a large number of information sources (data, documents, e-mails, images, etc.). The methodology presented in this paper concentrates on the contribution of semantic knowledge within textual information to improve processes carried out in domain-specific organizations. For example, activity logs, technical reports or contracts represent a part of structured textual knowledge. E-mails or texts describing activities are a part of unstructured (or semi-structured) knowledge and often contain important information to support decision-makers. Therefore, people involved in these processes need to analyze such documents to enrich their knowledge about said processes. Hence, the present methodology concerns the use of textual analysis approaches in order to evaluate their contribution to expert’s activities. The experts are the human resources with specific competences involved in processes that require particular analyses. The methodology proposed is focused on an automatic semantic annotation technique considering the most important entities and their significance within specific domains. It works on the different kinds of textual knowledge (structured and unstructured) and allows to construct the most representative document classification label. In particular, the proposed method uses results of semantic annotation techniques to optimize document classification and, consequently, to support the decision-making process. This methodological proposal is the result of a work experience within a company operating in the energy sector.
2016
978-1-61208-457-2
semantic annotation, document classification, corpus annotation, decision-making support
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/312144
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact