HITSZ_CITYU: Combine Collocation, Context Words and Neighboring Sentence Sentiment in Sentiment Adjectives Disambiguation
Ruifeng Xu, Jun Xu, Chunyu Kit · 2013
This paper presents the HIT_CITYU systems in Semeval-2 Task 18, namely, disambiguating sentiment ambiguous adjectives. The baseline system (HITSZ_CITYU_3) incorporates bi-gram and n-gram collocations of sentiment adjectives, and other context words as features in a one-class Support Vector Machine (SVM) classifier. To enhance the baseline system, collocation set expansion and characteristics learning based on word similarity and semisupervised learning are investigated, respectively. The final system (HITSZ_CITYU_1/2) combines collocations, context words and neighboring sentence sentiment in a two-class SVM classifier to determine the polarity of sentiment adjectives. The final systems achieved 0.957 and 0.953 (ranked 1 st and 2nd) macro accuracy, and 0.936 and 0.933 (ranked 2 nd and 3 rd) micro accuracy, respectively. 1