TY - JOUR
T1 - Product reputation mining
T2 - Bring informative review summaries to producers and consumers
AU - Piao, Zhehua
AU - Park, Sang Min
AU - On, Byung Won
AU - Choi, Gyu Sang
AU - Park, Myong Soon
N1 - Funding Information:
This work was supported by the National Research of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1F1A1060752) for Byung-Won On, and by the Ministry of Trade, Industry Energy (MOTIE, Korea) under Industrial Technology Innovation Program, No. 10063130 and MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program (IITP-2019-2016-0-00313) supervised by the IITP(Institute for Information communications Technology Promotion) for Gyu Sang Choi.
Funding Information:
Acknowledgments. This work was supported by the National Research of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1F1A1060752) for Byung-Won On, and by the Ministry of Trade, Industry Energy (MOTIE, Korea) under Industrial Technology Innovation Program, No. 10063130 and MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program (IITP-2019-2016-0-00313) supervised by the IITP(Institute for Information communications Technology Promotion) for Gyu Sang Choi.
Publisher Copyright:
© 2019, ComSIS Consortium. All rights reserved.
PY - 2019/6
Y1 - 2019/6
N2 - Product reputation mining systems can help customers make their buying decision about a product of interest. In addition, it will be helpful to investigate the preferences of recently released products made by enterprises. Unlike the conventional manual survey, it will give us quick survey results on a low cost budget. In this article, we propose a novel product reputation mining approach based on three dimensional points of view that are word, sentence, and aspect–levels. Given a target product, the aspect–level method assigns the sentences of a review document to the desired aspects. The sentence–level method is a graph-based model for quantifying the importance of sentences. The word–level method computes both importance and sentiment orientation of words. Aggregating these scores, the proposed approach measures the reputation tendency and preferred intensity and selects top-k informative review documents about the product. To validate the proposed method, we experimented with review documents relevant with K5 in Kia motors. Our experimental results show that our method is more helpful than the existing lexicon–based approach in the empirical and statistical studies.
AB - Product reputation mining systems can help customers make their buying decision about a product of interest. In addition, it will be helpful to investigate the preferences of recently released products made by enterprises. Unlike the conventional manual survey, it will give us quick survey results on a low cost budget. In this article, we propose a novel product reputation mining approach based on three dimensional points of view that are word, sentence, and aspect–levels. Given a target product, the aspect–level method assigns the sentences of a review document to the desired aspects. The sentence–level method is a graph-based model for quantifying the importance of sentences. The word–level method computes both importance and sentiment orientation of words. Aggregating these scores, the proposed approach measures the reputation tendency and preferred intensity and selects top-k informative review documents about the product. To validate the proposed method, we experimented with review documents relevant with K5 in Kia motors. Our experimental results show that our method is more helpful than the existing lexicon–based approach in the empirical and statistical studies.
KW - Opinion mining
KW - Product reputation mining
KW - Sentiment analysis
KW - Sentiment lexicon construction
UR - http://www.scopus.com/inward/record.url?scp=85071248841&partnerID=8YFLogxK
U2 - 10.2298/CSIS180703006P
DO - 10.2298/CSIS180703006P
M3 - Article
AN - SCOPUS:85071248841
SN - 1820-0214
VL - 16
SP - 359
EP - 380
JO - Computer Science and Information Systems
JF - Computer Science and Information Systems
IS - 2
ER -