Sentiment Analysis in the Era of Web 2.0: Applications, Implementation Tools and Approaches for the Novice Researcher

Abstract

Nowadays, people find it easier to express opinions via social media-formally known as Web 2.0. Sentiment analysis is an essential field under natural language processing in Computer Science that deals with analyzing people's opinions on the subject matter and discovering the polarity they contain. These opinions could be processed in collective form (as a document) or segments or units as sentences or phrases. Sentiment analysis can be applied in education, research optimization, politics, business, education, health, science and so on, thus forming massive data that requires efficient tools and techniques for analysis. Furthermore, the standard tools currently used for data collection, such as online surveys, interviews, and student evaluation of teachers, limit respondents in expressing opinions to the researcher's surveys and could not generate huge data as Web 2.0 becomes bigger. Sentiment analysis techniques are classified into three (3): Machine learning algorithms, lexicon and hybrid. This study explores sentiment analysis of Web 2.0 for novice researchers to promote collaboration and suggest the best tools for sentiment data analysis and result efficiency. Studies show that machine learning approaches result in large data sets on document-level sentiment classification. In some studies, hybrid techniques that combine machine learning and lexicon-based performance are better than lexicon. Python and R programming are commonly used tools for sentiment analysis implementation, but SentimentAnalyzer and SentiWordnet are recommended for the novice.

Keywords:   Sentiment Analysis; Web 2.0; Applications; Tools; Novice