Unsupervised Rule Based Explicit Aspect Extraction and Sarcasm Classification Task for Sentiment Analysis

Abstract

Aspect-based sentiment analysis (ABSA) includes aspect extraction and sentiment analysis on those extracted aspects. This research work is mainly focused on the explicit aspect extraction newlinefrom product-based online customer reviews. Many research studies on explicit aspect extractions newlinehave adopted dependency rule-based techniques but limited their focus to only nouns and newlinenoun phrases as potential aspects. Moreover, extraction of multiple aspects and multi-word newlineaspects from online reviews are also not addressed by previous research studies. Therefore, we have proposed dependency structure-based rules using the ROOT Node (DS-RN) technique using newlinespaCy dependency parser to extract nouns, noun phrases, non-opinionated adjectives, verbs, newlineand verb phrases in addition to single-word, multiple-aspect, and multi-word aspect extractions newlinefrom customer review datasets. In our proposed methodology, 31 new dependency-based rules newlineare formulated and implemented on 5 different product-based datasets. This study is based on newlinethe pattern analysis of dependency structures of review sentences to develop dependency-based newlinerules for explicit aspect extraction. The proposed approach also incorporated lexicon-based newlinepruning techniques to remove irrelevant aspects and retain correct aspects. The performance newlineresults on 5 different product-based customer review datasets demonstrate that our proposed newlineDS-RN approach outperforms all other state-of-the-art baseline works with an averaged value of precision as 87%, recall of 97% and 91% as F1-score.The importance of sarcasm detection and classification is primarily helpful for society newlineto avoid misinterpreting statements or reviews that could affect one s mental condition and newlineperception. Unfortunately, to increase the retention level of audience towards media news, often newlinethe media incorporate sarcasm in their news headlines. However, people find it difficult to detect sarcasm in news headlines, resulting in them having a false impression of the news and spreading it to their surroundings.