NILC_USP: Aspect Extraction using Semantic Labels

Abstract

This paper details the system NILC USP that participated in the Semeval 2014: Aspect Based Sentiment Analysis task. This system uses a Conditional Random Field (CRF) algorithm for extracting the aspects mentioned in the text. Our work added semantic labels into a basic feature set for measuring the efficiency of those for aspect extraction. We used the semantic roles and the highest verb frame as features for the machine learning. Overall, our results demonstrated that the system could not improve with the use of this semantic information, but its precision was increased.

Identifying Fine-Grained Opinion and Classifying Polarity on Coronavirus Pandemic

“…In the last step, performed the extracting of relations among product features and opinion expressions. For Portuguese, which is the language of interest in this paper, in [17], [16], [2] and [7], proposed methods for clustering and extraction of aspects in product reviews using machine learning and lexicon-based approaches.…”

NILC_USP: An Improved Hybrid System for Sentiment Analysis in Twitter Messages

“…Our previous system had demonstrated that a hybrid approach could achieve good results (F-measure of 56.31%), even if we did not use the state-of-theart algorithms for each approach (Balage Filho and Pardo, 2013). In this way, this work aims to verify how much this hybrid system could improve in relation to the previous one by including modifications on both lexicon-based and machine learning approaches.…”