Classification of sentiment reviews using n-gram machine learning approach

• Published in: Expert systems with applications Vol. 57; pp. 117 - 126
• Main Authors: Tripathy, Abinash, Agrawal, Ankit, Rath, Santanu Kumar
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.09.2016
• Subjects: Algorithms; Classification; Decision making; IMDb dataset; Information dissemination; Machine learning; Maximum Entropy (ME); N-gram; Naive Bayes (NB); Polarity; Recall; Sentiment analysis; Stochastic Gradient Descent (SGD); Support Vector Machine (SVM); Support vector machines; Sentiment analysis; Naive Bayes (NB); N-gram; Support Vector Machine (SVM); Maximum Entropy (ME); IMDb dataset; Stochastic Gradient Descent (SGD)
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2016.03.028

•A large number of sentiment reviews, blogs and comments present online.•These reviews must be classified to obtain a meaningful information.•Four different supervised machine learning algorithm used for classification.•Unigram, Bigram, Trigram models and their combinations used for classification.•The classification is done on IMDb movie review dataset. With the ever increasing social networking and online marketing sites, the reviews and blogs obtained from those, act as an important source for further analysis and improved decision making. These reviews are mostly unstructured by nature and thus, need processing like classification or clustering to provide a meaningful information for future uses. These reviews and blogs may be classified into different polarity groups such as positive, negative, and neutral in order to extract information from the input dataset. Supervised machine learning methods help to classify these reviews. In this paper, four different machine learning algorithms such as Naive Bayes (NB), Maximum Entropy (ME), Stochastic Gradient Descent (SGD), and Support Vector Machine (SVM) have been considered for classification of human sentiments. The accuracy of different methods are critically examined in order to access their performance on the basis of parameters such as precision, recall, f-measure, and accuracy.