With the advent of Internet and Social networks, the process of knowledge extraction and search has became of great importance, especially for companies that are interested in collecting customer feedback, establishing a brand presence, observing the way their brands are discussed and perceived. Several tools for the extraction of semantically related concepts from unstructured sources are available on the web. These sources such as forums, blogs, etc. can provide real-time information about how users perceive certain brands and can guide companies in making market decisions. In this paper, we propose an innovative knowledge extraction architecture realized through the integration of some existing java based tools that aims to retrieve more frequent concepts from unstructured sources, suggest other links of articles and images, and detect the language used in the sources. The architecture provides a knowledge base of a specific domain, which is used to suggest other concepts related to the research and to filter the results obtained from the elaboration of the unstructured sources. This software, integrated with traditional marketing channels (analysis of reports) makes possible the extraction of useful information for companies. In order to show, interpret and benefit from the software output we present a case of study related to marketing in agri-food sector.

Technological Tools Integration and Ontologies for Knowledge Extraction from Unstructured Sources: A Case of Study for Marketing in Agri-Food Sector

PAIANO, Roberto;CAIONE, ADRIANA;GUIDO, ANNA LISA;FAIT, MONICA MARIA ELENA;SCORRANO, Paola
2013-01-01

Abstract

With the advent of Internet and Social networks, the process of knowledge extraction and search has became of great importance, especially for companies that are interested in collecting customer feedback, establishing a brand presence, observing the way their brands are discussed and perceived. Several tools for the extraction of semantically related concepts from unstructured sources are available on the web. These sources such as forums, blogs, etc. can provide real-time information about how users perceive certain brands and can guide companies in making market decisions. In this paper, we propose an innovative knowledge extraction architecture realized through the integration of some existing java based tools that aims to retrieve more frequent concepts from unstructured sources, suggest other links of articles and images, and detect the language used in the sources. The architecture provides a knowledge base of a specific domain, which is used to suggest other concepts related to the research and to filter the results obtained from the elaboration of the unstructured sources. This software, integrated with traditional marketing channels (analysis of reports) makes possible the extraction of useful information for companies. In order to show, interpret and benefit from the software output we present a case of study related to marketing in agri-food sector.
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/11587/381568
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 2
social impact