Send to

Choose Destination
Neural Netw. 2014 Oct;58:82-97. doi: 10.1016/j.neunet.2014.05.010. Epub 2014 Jun 2.

Sentiments analysis at conceptual level making use of the Narrative Knowledge Representation Language.

Author information

Sorbonne University-STIH Laboratory, 1, rue Victor Cousin-75005 Paris, France. Electronic address:


This paper illustrates some of the knowledge representation structures and inference procedures proper to a high-level, fully implemented conceptual language, NKRL (Narrative Knowledge Representation Language). The aim is to show how these tools can be used to deal, in a sentiment analysis/opinion mining context, with some common types of human (and non-human) "behaviors". These behaviors correspond, in particular, to the concrete, mutual relationships among human and non-human characters that can be expressed under the form of non-fictional and real-time "narratives" (i.e., as logically and temporally structured sequences of "elementary events").


Behaviors; Narratives; Ontologies of events; Querying and inference techniques; Representation of deep sentiments; Standard ontologies

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center