Title: Targeted sentiment classification with multi-attention network

Authors: Xiao Tian; Peiyu Liu; Zhenfang Zhu

Addresses: School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China ' School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China ' School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China

Abstract: Targeted sentiment classification aims at recognising the sentiment polarity of specific targets. However, existing methods mainly depend on a crude attention mechanism, while neglecting the mutual effects between target and context. In order to solve this problem, this paper introduces a Multi-Attention Network (MAN) for aspect level sentiment classification. We jointly modelled intra-level and inter-level attentional components to capture the interaction between target and context. The former attention mechanism pays attention to the context relation, whereas the latter attention mechanism considers important parts in a sentence. The experimental conducted on laptop, restaurant and Twitter data sets indicate that our model surpasses the baseline model.

Keywords: attention mechanism; self-attention; targeted sentiment analysis; emotion analysis; neural network.

DOI: 10.1504/IJWMC.2022.127585

International Journal of Wireless and Mobile Computing, 2022 Vol.23 No.3/4, pp.231 - 238

Received: 01 Nov 2021
Accepted: 27 Feb 2022
Published online: 12 Dec 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article