Coreference between subjective expression and holder: A classification perspective

Dipankar Das, Sunit Bhattacharya

Abstract: Instead of applying the traditional keyword spotting approach, the presence of coreference between the holders and their subjective expressions often becomes important to identify and classify opinion and sentiment, accurately. In the present task, we have developed a classification system to resolve coreference of subjective expressions with their holders and thus automate the process of text annotations. The dependency parsed features in addition to sentiment words helped in classifying the corefered instances using machine learning framework.