1. NCCU Academic Hub
  2. 學術產出
  3. College of Commerce
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization
作者 謝宇倫
Hsieh, Yulun
Liu, S.-H.
Chang, Y.-C.
Hsu, W.-L.
貢獻者 資訊管理學系
關鍵詞 Encoding (symbols); Neural networks; Semantics; Document Representation; Embedding method; Primary objective; reader emotion; Semantic context; Similarity measure; Vector representations; word embedding; Information use
日期 2015
上傳時間 14-Aug-2017 15:35:16 (UTC+8)
摘要 In this paper, we propose a novel approach for reader-emotion categorization using word embedding learned from neural networks and an SVM classifier. The primary objective of such word embedding methods involves learning continuous distributed vector representations of words through neural networks. It can capture semantic context and syntactic cues, and subsequently be used to infer similarity measures among words, sentences, and even documents. Various methods of combining the word embeddings are tested for their performances on reader-emotion categorization of a Chinese news corpus. Results demonstrate that the proposed method, when compared to several other approaches, can achieve comparable or even better performances. © 2015 IEEE.
關聯 Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015, (), 569-573
資料類型 conference
DOI http://dx.doi.org/10.1109/IRI.2015.90
dc.contributor 資訊管理學系zh_Tw
dc.creator (作者) 謝宇倫zh_TW
dc.creator (作者) Hsieh, Yulunen_US
dc.creator (作者) Liu, S.-H.en_US
dc.creator (作者) Chang, Y.-C.en_US
dc.creator (作者) Hsu, W.-L.en_US
dc.date (日期) 2015en_US
dc.date.accessioned 14-Aug-2017 15:35:16 (UTC+8)-
dc.date.available 14-Aug-2017 15:35:16 (UTC+8)-
dc.date.issued (上傳時間) 14-Aug-2017 15:35:16 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/111937-
dc.description.abstract (摘要) In this paper, we propose a novel approach for reader-emotion categorization using word embedding learned from neural networks and an SVM classifier. The primary objective of such word embedding methods involves learning continuous distributed vector representations of words through neural networks. It can capture semantic context and syntactic cues, and subsequently be used to infer similarity measures among words, sentences, and even documents. Various methods of combining the word embeddings are tested for their performances on reader-emotion categorization of a Chinese news corpus. Results demonstrate that the proposed method, when compared to several other approaches, can achieve comparable or even better performances. © 2015 IEEE.en_US
dc.format.extent 178381 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015, (), 569-573en_US
dc.subject (關鍵詞) Encoding (symbols); Neural networks; Semantics; Document Representation; Embedding method; Primary objective; reader emotion; Semantic context; Similarity measure; Vector representations; word embedding; Information useen_US
dc.title (題名) Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorizationen_US
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/IRI.2015.90
dc.doi.uri (DOI) http://dx.doi.org/10.1109/IRI.2015.90