Method and system for analyzing emotion on basis of position related document, and non-transitory computer-readable recording medium
AssigneeKonolabs, Inc.
InventorsJung Hee Ryu, Joon Hee Kim
Life of this patent
Estimating the term…
Abstract
According to one aspect of the present invention, provided is a method for analyzing an emotion on the basis of a position related document. The method includes generating a position related document with reference to content collected from at least one user terminal device or at least one server and position information related to the content; calculating an object-emotion score for each topic at positions related to the generated position related document; and determining, with reference to the object-emotion score for each topic at a first position, a predicted preference level of a user positioned at the first position with respect to at least one topic.
Claims15
A method for analyzing emotions on the basis of a position-related document, comprising the steps of:
- generating a position-related document with reference to contents collected from at least one user terminal device or at least one server and position information related to the contents;
- calculating an object-emotion score for each topic at positions related to the generated position-related document;
- and
- determining, with reference to the object-emotion score for each topic at a first position, a preference that a user positioned at the first position is expected to have for at least one topic.
A system for analyzing emotions on the basis of a position-related document, comprising:
- a position--related document management unit configured to generate a position-related document with reference to contents collected from at least one user terminal device or at least one server and position information related to the contents;
- and
- an emotion analysis unit configured to calculate an object-emotion score for each topic at positions related to the generated position-related document, and to determine, with reference to the object-emotion score for each topic at a first position, a preference that a user positioned a first position is expected to have for at least one topic.
Dependencies are inferred from the claim text.