•  
  •  
 

Abstract

Nowadays, in many real-life applications, sentiment analysis plays a vital role in the automaticprediction of human activities, especially on online social networks (OSNs). Since the last decade, the research onopinion mining and sentiment analysis has been growing with the increase in volume of online reviews available overthe social media networks, such as Facebook OSNs. Sentiment analysis falls under the data mining domain researchproblem. Sentiment analysis is a type of text mining process to determine subjective attitude, such as sentimentsfrom written texts, and hence has become a main research interest in domains of natural language processing anddata mining. The main task of sentiment analysis is to classify human sentiments with the objective of classifying thesentiment or emotion of end users based on their specific text on the OSNs. Several research approaches have beendesigned for sentiment analysis, in which the factors of accuracy, efficiency and speed have been used to evaluatethe effectiveness of sentiment analysis methods. The Map-Reduce framework under the domain of big data is usedto minimise the speed of execution and efficiency recently with many data mining methods. The sentiment analysisof messages on Facebook OSNs is more challenging compared with those of other sites because of the misspellingsand slang words in their Twitter dataset. In this study, the different solutions that have been recently presented arediscussed in detail. Then, a new approach for sentiment analysis based on hybrid feature extraction and multi-classsupport vector machine methods is proposed. The algorithms have been designed using big data techniques in viewof optimising the performance of sentiment analysis.

Download

Share

COinS