A hybrid approach to the sentiment analysis problem at the sentence level

详细信息    查看全文

• 作者：Orestes Appel^a ; ^{orestes.appel@email.dmu.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; Francisco Chiclana ; ^a ; ^{chiclana@dmu.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; Jenny Carter^a ; ^{jennyc@dmu.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; Hamido Fujita^b ; ^{issam@iwate-pu.ac.jp" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Sentiment analysis ; Semantic rules ; Fuzzy sets ; Unsupervised machine learning ; SentiWordNet ; Naï ; ve Bayes ; Maximum entropy ; Computing with sentiments
• 刊名：Knowledge-Based Systems
• 出版年：2016
• 出版时间：15 September 2016
• 年：2016
• 卷：108
• 期：Complete
• 页码：110-124
• 全文大小：1326 K

文摘

The objective of this article is to present a hybrid approach to the Sentiment Analysis problem at the sentence level. This new method uses natural language processing (NLP) essential techniques, a sentiment lexicon enhanced with the assistance of SentiWordNet, and fuzzy sets to estimate the semantic orientation polarity and its intensity for sentences, which provides a foundation for computing with sentiments. The proposed hybrid method is applied to three different data-sets and the results achieved are compared to those obtained using Naïve Bayes and Maximum Entropy techniques. It is demonstrated that the presented hybrid approach is more accurate and precise than both Naïve Bayes and Maximum Entropy techniques, when the latter are utilised in isolation. In addition, it is shown that when applied to datasets containing snippets, the proposed method performs similarly to state of the art techniques.