Skip to main content
placeholder image

Ranking social emotions by learning listwise preference

Conference Paper


Abstract


  • Abstract—Emotion modeling has received a great attention in

    recent years. This paper models the online social emotions that

    are the online users’ emotional responds when they are exposed

    to news articles. Specifically, we rank social emotion labels for

    online documents. Unlike the existing method, referred to as

    Pair-LR, which learns pairwise preference and adopts binary

    classification, we address the problem of ranking social emotions

    by learning listwise preference. In particular, a novel approach,

    referred to as List-LR, is proposed to learn a ranking model for

    social emotion labels of online documents by minimizing the

    listwise loss defined on instances. Empirical experiments show

    that the proposed approach outperforms Pair-LR and is also

    competitive to other two start-of-the-art approaches for label

    ranking.

UOW Authors


  •   Wang, Qishen (external author)
  •   Wu, Ou (external author)
  •   Hu, Weiming (external author)
  •   Yang, Jinfeng (external author)
  •   Li, Wanqing

Publication Date


  • 2011

Citation


  • Wang, Q., Wu, O., Hu, W., Yang, J. & Li, W. (2011). Ranking social emotions by learning listwise preference. First Asian Conference on Digital Object Identifier (pp. 164-168). USA: IEEE.

Scopus Eid


  • 2-s2.0-84862905380

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/2034

Has Global Citation Frequency


Start Page


  • 164

End Page


  • 168

Place Of Publication


  • USA

Abstract


  • Abstract—Emotion modeling has received a great attention in

    recent years. This paper models the online social emotions that

    are the online users’ emotional responds when they are exposed

    to news articles. Specifically, we rank social emotion labels for

    online documents. Unlike the existing method, referred to as

    Pair-LR, which learns pairwise preference and adopts binary

    classification, we address the problem of ranking social emotions

    by learning listwise preference. In particular, a novel approach,

    referred to as List-LR, is proposed to learn a ranking model for

    social emotion labels of online documents by minimizing the

    listwise loss defined on instances. Empirical experiments show

    that the proposed approach outperforms Pair-LR and is also

    competitive to other two start-of-the-art approaches for label

    ranking.

UOW Authors


  •   Wang, Qishen (external author)
  •   Wu, Ou (external author)
  •   Hu, Weiming (external author)
  •   Yang, Jinfeng (external author)
  •   Li, Wanqing

Publication Date


  • 2011

Citation


  • Wang, Q., Wu, O., Hu, W., Yang, J. & Li, W. (2011). Ranking social emotions by learning listwise preference. First Asian Conference on Digital Object Identifier (pp. 164-168). USA: IEEE.

Scopus Eid


  • 2-s2.0-84862905380

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/2034

Has Global Citation Frequency


Start Page


  • 164

End Page


  • 168

Place Of Publication


  • USA