DC Field | Value | Language |
---|---|---|
dc.contributor.author | Joo, Won-Tae | ko |
dc.contributor.author | Jeong, Young-Seob | ko |
dc.contributor.author | Oh, Kyo-Joong | ko |
dc.date.accessioned | 2016-07-07T06:37:16Z | - |
dc.date.available | 2016-07-07T06:37:16Z | - |
dc.date.created | 2016-06-13 | - |
dc.date.created | 2016-06-13 | - |
dc.date.issued | 2016-01-18 | - |
dc.identifier.citation | The 3rd International Conference on Big Data and Smart Computing (BigComp2016), pp.502 - 504 | - |
dc.identifier.uri | http://hdl.handle.net/10203/210144 | - |
dc.description.abstract | In Korea, authors of the newspaper article tend to express their intention indirectly, that is, they choose a method to leave out some important facts, or sometimes uses biased terms to support their opinion. Since they’re not expressing their opinion directly, detecting the political bias is a difficult task. In this paper, we propose a method to detect political bias in the Korean articles by first building word vectors and sentence vectors, and second do a DBN-Training with those vectors and finally do a regression with SVM to calculate the bias. We used our own dataset which is scored with the political bias before doing the regression. | - |
dc.language | English | - |
dc.publisher | Korean Institute of Information Scientists and Engineers (KIISE) | - |
dc.title | Political orientation detection on Korean newspapers via sentence embedding and deep learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000381792400093 | - |
dc.identifier.scopusid | 2-s2.0-84964577684 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 502 | - |
dc.citation.endingpage | 504 | - |
dc.citation.publicationname | The 3rd International Conference on Big Data and Smart Computing (BigComp2016) | - |
dc.identifier.conferencecountry | HK | - |
dc.identifier.conferencelocation | Regal Riverside Hotel, Hong Kong | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.