School of
Information Technology and Electrical Engineering

Speaker: Mr Abdulqader Almars
Seminar Date: Wed, 04/10/2017 - 15:00
Venue: 49-502; AEB Seminar Room
Host: Prof Xue Li

Seminar Type:  PhD Confirmation Seminar


Extracting the latent structure of the aspects and the sentiment polarities is important as it helps customers to understand people' preference to a certain product and show the reasons why they prefer this product. Moreover, it helps users to compare aspects of different products. As a result, they can make informed decisions when buying products. However, insufficient studies have been done to effectively reveal the structure sentiment of the aspects from short texts due to the shortness and sparsity. In this paper, we propose a structured sentiment analysis (SSA) approach to understand the sentiments and opinions expressed by people in short texts. The proposed SSA approach has three advantages: 1) automatically extracts a hierarchical tree of a product's hot aspects from short texts; 2) hierarchically analyses people's opinions on those aspects; and 3) generates a summary and evidences of the results. We evaluate our approach on popular products. The experimental results show that the proposed approach can effectively extract a sentiment tree from short texts. In this talk, we will demonstrate the importance of bringing structure to date and the effectiveness of the proposed approach. 


Mr. Abdulqader Almars achieved his master Degree of computer science from University of Queensland in 2016. He is now a PhD student in his frist year under the  supervision of Prof. Xue LI (principal) and Dr. Xin Zhao (University of Queensland).