Building a concept-level sentiment dictionary based on commonsense knowledge

Angela Charng Rurng Tsai; Chi En Wu; Richard Tzong Han Tsai; Jane Yung Jen Hsu

doi:10.1109/MIS.2013.25

Building a concept-level sentiment dictionary based on commonsense knowledge

Angela Charng Rurng Tsai, Chi En Wu, Richard Tzong Han Tsai, Jane Yung Jen Hsu

Research output: Contribution to journal › Journal Article › peer-review

95 Scopus citations

Abstract

Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.

Original language	English
Article number	6461369
Pages (from-to)	22-30
Number of pages	9
Journal	IEEE Intelligent Systems
Volume	28
Issue number	2
DOIs	https://doi.org/10.1109/MIS.2013.25
State	Published - 2013
Externally published	Yes

Keywords

commonsense knowledge
ConceptNet
sentiment analysis
sentiment dictionary

Access to Document

10.1109/MIS.2013.25

Cite this

@article{0aad3bbb82d24236aaf05cff80c0822f,

title = "Building a concept-level sentiment dictionary based on commonsense knowledge",

abstract = "Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.",

keywords = "commonsense knowledge, ConceptNet, sentiment analysis, sentiment dictionary",

author = "Tsai, {Angela Charng Rurng} and Wu, {Chi En} and Tsai, {Richard Tzong Han} and Hsu, {Jane Yung Jen}",

year = "2013",

doi = "10.1109/MIS.2013.25",

language = "英语",

volume = "28",

pages = "22--30",

journal = "IEEE Intelligent Systems",

issn = "1541-1672",

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

number = "2",

}

TY - JOUR

T1 - Building a concept-level sentiment dictionary based on commonsense knowledge

AU - Tsai, Angela Charng Rurng

AU - Wu, Chi En

AU - Tsai, Richard Tzong Han

AU - Hsu, Jane Yung Jen

PY - 2013

Y1 - 2013

N2 - Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.

AB - Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.

KW - commonsense knowledge

KW - ConceptNet

KW - sentiment analysis

KW - sentiment dictionary

UR - http://www.scopus.com/inward/record.url?scp=84880175617&partnerID=8YFLogxK

U2 - 10.1109/MIS.2013.25

DO - 10.1109/MIS.2013.25

M3 - 文章

AN - SCOPUS:84880175617

SN - 1541-1672

VL - 28

SP - 22

EP - 30

JO - IEEE Intelligent Systems

JF - IEEE Intelligent Systems

IS - 2

M1 - 6461369

ER -

Building a concept-level sentiment dictionary based on commonsense knowledge

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this