Apparatus and method for tagging topic to content

1. An apparatus for tagging a topic to content based on a viewing situation, the apparatus comprising:

an unstructured data-based topic generator configured to generate a topic model comprising an unstructured data-based topic based on the content and unstructured data, wherein the content includes at least one of content-related unstructured data and external unstructured data, the content-related unstructured data including subtitles and content dialogue, and the external unstructured data including a blog post and news;

a viewer group analyzer configured to analyze a characteristic of a viewer group comprising a viewer of the content based on a social network of the viewer and viewing situation information of the viewer;

a multifaceted topic generator configured to generate a multifaceted topic based on the topic model and the characteristic of the viewer group;

a content divider configured to divide the content into a plurality of scenes; and

a tagger configured to tag the multifaceted topic to a scene obtained through the division,

wherein the unstructured data-based topic generator, the viewer group analyzer, the multifaceted topic generator, the topic divider, and the tagger each comprise a processing unit including a processor running software to cause the processing unit to perform the functions of the unstructured data-based topic generator, the viewer group analyzer, the multifaceted topic generator, the topic divider, and the tagger, respectively.

2. The apparatus of claim 1 , wherein the unstructured data-based topic generator comprises:

a content-related unstructured data collector configured to collect, from the content, content-related unstructured data associated with the content;

a keyword extractor configured to extract a first keyword and a second keyword from the content-related unstructured data; and

a topic model generator configured to generate the unstructured data-based topic on the content using the first keyword and the second keyword, and generate the topic model based on the unstructured data-based topic,

wherein the second keyword is determined among first keywords based on respective frequency numbers of the first keywords.

3. The apparatus of claim 2 , wherein the unstructured data-based topic generator comprises:

an external unstructured data analyzer configured to extract a third keyword from external unstructured data; and

a model expander configured to expand the topic model based on the third keyword.

4. The apparatus of claim 1 , wherein the viewer group analyzer comprises:

a social network generator configured to generate the social network based on online information of the viewer;

a proximity network generator configured to generate a proximity network from the viewing situation information;

a network integrator configured to integrate the social network and the proximity network; and

a group characteristic extractor configured to extract a common characteristic of the viewer group based on an integrated network obtained through the integration.

5. The apparatus of claim 4 , further comprising:

a viewer group extractor configured to extract the viewer group from the integrated network.

6. The apparatus of claim 1 , wherein the multifaceted topic generator comprises:

a correlation analyzer configured to analyze a correlation between the unstructured data-based topic and the characteristic of the viewer group; and

a weight calculator configured to calculate a weight for each viewer group corresponding to the unstructured data-based topic based on the correlation, and apply the calculated weight to the topic model.

7. The apparatus of claim 6 , wherein the multifaceted topic generator further comprises:

a topic model retrainer configured to change the topic model based on the correlation.

8. The apparatus of claim 1 , wherein the tagger is configured to analyze a correlation between the viewer group and the scene and a correlation between the multifaceted topic and the scene, and

tag the multifaceted topic to the scene based on the correlation between the viewer group and the scene and the correlation between the multifaceted topic and the scene.

9. The apparatus of claim 8 , wherein the correlation between the multifaceted topic and the scene is analyzed based on a correlation between a first keyword and the scene,

wherein the first keyword is extracted from content-related unstructured data associated with the content.

10. A method of tagging a topic, comprising:

generating, by a processor, a topic of broadcast content based on characteristics of the broadcast content;

extracting, by the processor, a characteristic of a viewer group based on viewing information of a viewer of the broadcast content;

generating, by the processor, a multifaceted topic based on the topic of the broadcast content and the characteristic of the viewer group;

dividing the broadcast content into units of one or more scenes; and

tagging the multifaceted topic to the divided broadcast content.

11. The method of claim 10 , wherein the generating of the topic comprises:

collecting broadcast content-related unstructured data associated with the broadcast content;

extracting a first keyword based on the collected broadcast content-related unstructured data;

extracting a second keyword of the topic based on the extracted first keyword;

generating an unstructured data-based topic on the broadcast content using the first keyword and the second keyword, and generating a topic model based on the unstructured data-based topic; and

extracting a third keyword using the topic model and external unstructured data.

12. The method of claim 10 , further comprising:

storing information associated with the tagged multifaceted topic as metadata.

13. A method of tagging a topic to content based on a viewing situation, the method comprising:

generating, by a processor, a topic model comprising an unstructured data-based topic based on the content and unstructured data, wherein the content includes at least one of content-related unstructured data including subtitles and content dialogue, and external unstructured data including a blog post and news;

analyzing a characteristic of a viewer group comprising a viewer of the content based on a social network of the viewer and viewing situation information of the viewer;

generating a multifaceted topic based on the topic model and the characteristic of the viewer group;

dividing the content into a plurality of scenes; and

tagging the multifaceted topic to a scene obtained through the division.

14. The method of claim 13 , wherein the generating of the topic model comprises:

collecting content-related unstructured data associated with the content;

extracting a first keyword and a second keyword from the content-related unstructured data; and

generating the unstructured data-based topic on the content using the first keyword and the second keyword, and generating the topic model based on the unstructured data-based topic.

15. The method of claim 14 , wherein the generating of the topic model comprises:

extracting a third keyword from external unstructured data; and

expanding the topic model based on the third keyword.