Embedding Refinement Framework for Targeted Aspect-Based Sentiment Analysis

TY - JOUR

T1 - Embedding Refinement Framework for Targeted Aspect-Based Sentiment Analysis

AU - Liang, Bin

AU - Yin, Rongdi

AU - Du, Jiachen

AU - Gui, Lin

AU - He, Yulan

AU - Yang, Min

AU - Xu, Ruifeng

N1 - Publisher Copyright: © 2010-2012 IEEE.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - The state-of-the-art approaches to targeted aspect-based sentiment analysis (TABSA) are mostly built on deep neural networks with attention mechanisms. One problem is that embeddings of targets and aspects are either pre-trained from large external corpora or randomly initialized. We argue that affective commonsense knowledge and words indicative of sentiment could be used to learn better target and aspect embeddings. We therefore propose an embedding refinement framework called RAEC (Refining Affective Embedding from Context), in which sentiment concepts extracted from affective commonsense knowledge and word relative location information are incorporated to derive context-affective embeddings. Furthermore, a sparse coefficient vector is exploited in refining the embeddings of targets and aspects separately. In this way, embeddings of targets and aspects can capture the highly relevant affective words. Experimental results on two benchmark datasets show that our framework can be easily integrated with existing embedding-based TABSA models and achieves state-of-the-art results compared to models relying on pre-trained word embeddings or built on other embedding refinement methods.

AB - The state-of-the-art approaches to targeted aspect-based sentiment analysis (TABSA) are mostly built on deep neural networks with attention mechanisms. One problem is that embeddings of targets and aspects are either pre-trained from large external corpora or randomly initialized. We argue that affective commonsense knowledge and words indicative of sentiment could be used to learn better target and aspect embeddings. We therefore propose an embedding refinement framework called RAEC (Refining Affective Embedding from Context), in which sentiment concepts extracted from affective commonsense knowledge and word relative location information are incorporated to derive context-affective embeddings. Furthermore, a sparse coefficient vector is exploited in refining the embeddings of targets and aspects separately. In this way, embeddings of targets and aspects can capture the highly relevant affective words. Experimental results on two benchmark datasets show that our framework can be easily integrated with existing embedding-based TABSA models and achieves state-of-the-art results compared to models relying on pre-trained word embeddings or built on other embedding refinement methods.

KW - affective knowledge

KW - aspect sentiment analysis

KW - embedding refinement

KW - Target sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=85103915604&partnerID=8YFLogxK

U2 - 10.1109/TAFFC.2021.3071388

DO - 10.1109/TAFFC.2021.3071388

M3 - Article

AN - SCOPUS:85103915604

SN - 1949-3045

VL - 14

SP - 279

EP - 293

JO - IEEE transactions on affective computing

JF - IEEE transactions on affective computing

IS - 1

ER -