IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis

• DOI: 10.18653/v1/d18-1377
• Publication Date: 2019-06-29T16:01:17Z
• Authors: Navonil Majumder; Soujanya Poria; Alexander Gelbukh; Md. Shad Akhtar; Erik Cambria; Asif Ekbal
• Keywords: Sentiment Analysis; Laptop

Sentiment analysis has immense implications in e-commerce through user feedback mining. Aspect-based sentiment takes this one step further by enabling businesses to extract aspect specific sentimental information. In paper, we present a novel approach of incorporating the neighboring aspects related information into classification target using memory networks. We show that our method outperforms state art 1.6% on average two distinct domains: restaurant and laptop.