期刊
JOURNAL OF DECISION SYSTEMS
卷 30, 期 2-3, 页码 259-281出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/12460125.2020.1864106
关键词
Sentiment analysis; bag-of-words; TF-IDF; GloVe; machine learning; deep learning; transfer learning; aspect extraction; lime
资金
- Bank Albilad Chair of Electronic Commerce (BACEC)
- Princess Nourah bint Abdulrahman University
Opinion mining has been used to analyze restaurant reviews on Yelp website, applying various predictive models and proposing a new unsupervised method. The reviews were categorized into different aspects based on sentiment context.
Opinion mining has significantly supported knowledge and decision-making. This research analysed the content of online reviews including the text of reviews and their rankings. The restaurant reviews of Yelp website have been analysed into two sentiment classifications, binary classification (positive and negative) and ternary classification (positive, negative, and neutral). Three different types of predictive models have been applied including: machine learning, deep learning and transfer learning models. In addition, we propose a new unsupervised approach to apply for aspect-level sentiment classification based on semantic similarity, which allows our framework to leverage the powerful capacity of pre-trained language models like GloVe and eliminated many of the complications associated with the supervised learning models. Food, service, ambience, and price are the aspects that have been categorized according to their sentiment context. In conclusion, 98.30% of the maximum accuracy obtained using ALBERT model. The proposed aspect extraction method achieved an accuracy of 83.04%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据