Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis

Research paper by Md Shad Akhtar, Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya

Indexed on: 07 Apr '17Published on: 27 Mar '17Published in: Knowledge-Based Systems


In this paper we present a cascaded framework of feature selection and classifier ensemble using particle swarm optimization (PSO) for aspect based sentiment analysis. Aspect based sentiment analysis is performed in two steps, viz. aspect term extraction and sentiment classification. The pruned, compact set of features performs better compared to the baseline model that makes use of the complete set of features for aspect term extraction and sentiment classification. We further construct an ensemble based on PSO, and put it in cascade after the feature selection module. We use the features that are identified based on the properties of different classifiers and domains. As base learning algorithms we use three classifiers, namely Maximum Entropy (ME), Conditional Random Field (CRF) and Support Vector Machine (SVM). Experiments for aspect term extraction and sentiment analysis on two different kinds of domains show the effectiveness of our proposed approach.

Figure 10.1016/j.knosys.2017.03.020.0.jpg
Figure 10.1016/j.knosys.2017.03.020.1.jpg
Figure 10.1016/j.knosys.2017.03.020.2.jpg
Figure 10.1016/j.knosys.2017.03.020.3.jpg