TY - JOUR
T1 - Confidence-Aware Sentiment Quantification via Sentiment Perturbation Modeling
AU - Tang, Xiangyun
AU - Liao, Dongliang
AU - Shen, Meng
AU - Zhu, Liehuang
AU - Huang, Shen
AU - Li, Gongfu
AU - Man, Hong
AU - Xu, Jin
N1 - Publisher Copyright:
© 2010-2012 IEEE.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - Sentiment Quantification aims to detect the overall sentiment polarity of users from a set of reviews corresponding to a target. Existing methods equally treat and aggregate individual reviews' sentiment to judge the overall sentiment polarity. However, the confidence of each review is not equal in sentiment quantification where sentiment perturbation arising from high- and low-confidence reviews may degrade the accuracy of Sentiment Quantification. Specifically, fake reviews with deceptive sentiments are low confidence, which perturbs the overall sentiment prediction. Whereas, some reviews generated by responsible users are high confidence. They contain authoritative suggestions so they should be emphasized in Sentiment Quantification. In this paper, we design and build COSE, a confidence-aware sentiment quantification framework, which can measure the confidence of individual reviews to eliminate sentiment perturbation and facilitate sentiment quantification. We design a Review Graph that achieves review confidence modeling in an unsupervised manner and obtains review confidence representations. Moreover, we develop a dynamic fusion attention mechanism, which produces sentiment 'de-perturbation' vectors to eliminate the sentiment perturbation based on the confidence representations. Extensive experiments on large-scale review datasets validate the significant superiority of COSE over the state-of-the-art.
AB - Sentiment Quantification aims to detect the overall sentiment polarity of users from a set of reviews corresponding to a target. Existing methods equally treat and aggregate individual reviews' sentiment to judge the overall sentiment polarity. However, the confidence of each review is not equal in sentiment quantification where sentiment perturbation arising from high- and low-confidence reviews may degrade the accuracy of Sentiment Quantification. Specifically, fake reviews with deceptive sentiments are low confidence, which perturbs the overall sentiment prediction. Whereas, some reviews generated by responsible users are high confidence. They contain authoritative suggestions so they should be emphasized in Sentiment Quantification. In this paper, we design and build COSE, a confidence-aware sentiment quantification framework, which can measure the confidence of individual reviews to eliminate sentiment perturbation and facilitate sentiment quantification. We design a Review Graph that achieves review confidence modeling in an unsupervised manner and obtains review confidence representations. Moreover, we develop a dynamic fusion attention mechanism, which produces sentiment 'de-perturbation' vectors to eliminate the sentiment perturbation based on the confidence representations. Extensive experiments on large-scale review datasets validate the significant superiority of COSE over the state-of-the-art.
KW - Confidence modeling
KW - sentiment analysis
KW - sentiment quantification
UR - http://www.scopus.com/inward/record.url?scp=85166748651&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85166748651&partnerID=8YFLogxK
U2 - 10.1109/TAFFC.2023.3301956
DO - 10.1109/TAFFC.2023.3301956
M3 - Article
AN - SCOPUS:85166748651
SN - 1949-3045
VL - 15
SP - 736
EP - 750
JO - IEEE Transactions on Affective Computing
JF - IEEE Transactions on Affective Computing
IS - 2
ER -