{Aji Ghose Hassan Tahir Patrycja Sliwiak Thomas Metcalfe Georgia Harrison Jordan Clive Georgios Kontonatsios}

Abstract

Aspect-based sentiment analysis (ABSA) aims at automatically extracting aspects of entities and classifying the polarity of each extracted aspect. The majority of available ABSA systems heavily rely on manually annotated datasets to train supervised machine learning models. However, the development of such manually curated datasets is a labour-intensive process and therefore existing ABSA datasets cover only a few domains and they are limited in size. In response, we present FABSA (Feedback ABSA), a new large-scale and multi-domain ABSA dataset of feedback reviews. FABSA consists of approximately 10,500 reviews which span across 10 domains. We conduct a number of experiments to evaluate the performance of state-of-the-art deep learning models when applied to the FABSA dataset. Our results demonstrate that ABSA models can generalise across different domains when trained on our FABSA dataset while the performance of the models is enhanced when using a larger training dataset. Our FABSA dataset is publicly available.