Aspect-Based Sentiment Analysis for Financial Review with Implicit Aspect and Opinion Using Semantic Similarity and Hybrid Approach

Abstract

Aspect-Based Sentiment Analysis (ABSA) for financial review still has some errors which impact the low accuracy of ABSA performance. One of the errors happens because there are implicit aspects and opinions, which are indicated as polysemy terms. For example, the term spread can refer to the aspect term for financial aspect categories and can also refer to the opinion term. Implicit opinion extraction in financial reviews requires in-depth attention because several opinion terms contained in reviews are nouns and not adjectives or verbs that describe explicit opinions (e.g., the review Copper market may get a 2003-style supply shock from Glencore closures). This research proposes ABSA for financial review with implicit aspects and opinions using Semantic similarity and a hybrid approach. We use the FiQA 2018 dataset, which has been classified into four aspect categories: Corporate, Economy, Stock, and Market. First, the dataset is pre-processed. Then, we extract aspect category keywords from Wikipedia using Word2vec. For the aspect categorization method, we use implicit aspect extraction, Semantic similarity, and hybrid BERT-BiLSTM to calculate the similarity between extracted aspect terms and aspect category keywords for determining the aspect category. For the ABSA method, we use implicit opinion extraction and hybrid BERT-BiLSTM. The obtained performance result of aspect categorization reaches 91% and the obtained performance result of ABSA reaches 92%.