Sequential patterns rule-based approach for opinion target extraction from customer reviews

摘要

Aspect extraction or opinion target extraction is the key task of sentiment analysis, which aims to identify targets of people's sentiments. This is the most important task of aspect-based sentiment analysis as without the aspects, there is no much use of extracted opinions. Recent approaches have shown the significance of dependency-based rules for the given task. These rules are heavily dependent on the dependency parser and generated with the help of grammatical rules. In this article, we are proposing to learn from user's behaviour to identify the relation among aspects and opinions. The use of sequential patterns has been proposed for the extraction of aspects. The key purpose of this research is to study the impact of sequential pattern mining in the phase of aspect extraction. Our experimental results show that the approach proposed in our work produced better results as compared with the state-of-the-art approaches.