Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization

Yu Lun Hsieh; Shih Hung Liu; Yung Chun Chang; Wen Lian Hsu

doi:10.1109/IRI.2015.90

Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization

Yu Lun Hsieh, Shih Hung Liu, Yung Chun Chang, Wen Lian Hsu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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.

Original language	English
Title of host publication	Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	569-573
Number of pages	5
ISBN (Electronic)	9781467366564
DOIs	https://doi.org/10.1109/IRI.2015.90
Publication status	Published - Oct 19 2015
Externally published	Yes
Event	16th IEEE International Conference on Information Reuse and Integration, IRI 2015 - San Francisco, United States Duration: Aug 13 2015 → Aug 15 2015

Conference

Conference	16th IEEE International Conference on Information Reuse and Integration, IRI 2015
Country/Territory	United States
City	San Francisco
Period	8/13/15 → 8/15/15

Keywords

document representation
neural network
reader emotion
word embedding

ASJC Scopus subject areas

Information Systems
Information Systems and Management
Electrical and Electronic Engineering

Access to Document

10.1109/IRI.2015.90

Cite this

Hsieh, Y. L., Liu, S. H., Chang, Y. C., & Hsu, W. L. (2015). Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization. In Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015 (pp. 569-573). [7301028] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRI.2015.90

Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization. / Hsieh, Yu Lun; Liu, Shih Hung; Chang, Yung Chun et al.

Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 569-573 7301028.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hsieh, YL, Liu, SH, Chang, YC & Hsu, WL 2015, Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization. in Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015., 7301028, Institute of Electrical and Electronics Engineers Inc., pp. 569-573, 16th IEEE International Conference on Information Reuse and Integration, IRI 2015, San Francisco, United States, 8/13/15. https://doi.org/10.1109/IRI.2015.90

@inproceedings{6954d617e75641828accf8964018e630,

title = "Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization",

abstract = "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.",

keywords = "document representation, neural network, reader emotion, word embedding",

author = "Hsieh, {Yu Lun} and Liu, {Shih Hung} and Chang, {Yung Chun} and Hsu, {Wen Lian}",

year = "2015",

month = oct,

day = "19",

doi = "10.1109/IRI.2015.90",

language = "English",

pages = "569--573",

booktitle = "Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "16th IEEE International Conference on Information Reuse and Integration, IRI 2015 ; Conference date: 13-08-2015 Through 15-08-2015",

}

TY - GEN

T1 - Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization

AU - Hsieh, Yu Lun

AU - Liu, Shih Hung

AU - Chang, Yung Chun

AU - Hsu, Wen Lian

PY - 2015/10/19

Y1 - 2015/10/19

N2 - 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.

AB - 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.

KW - document representation

KW - neural network

KW - reader emotion

KW - word embedding

UR - http://www.scopus.com/inward/record.url?scp=84959135511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959135511&partnerID=8YFLogxK

U2 - 10.1109/IRI.2015.90

DO - 10.1109/IRI.2015.90

M3 - Conference contribution

AN - SCOPUS:84959135511

SP - 569

EP - 573

BT - Proceedings - 2015 IEEE 16th International Conference on Information Reuse and Integration, IRI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE International Conference on Information Reuse and Integration, IRI 2015

Y2 - 13 August 2015 through 15 August 2015

ER -

Neural Network-Based Vector Representation of Documents for Reader-Emotion Categorization

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this