Abstract: Social media sites are places where citizens voice their opinions without fear. There is growing sense of urgency to understand public opinions because of the viral nature of social media. Making sense of these mass conversations for interacting meaningfully is in demand. Sentiment analysis is the study where sentiments are computed for a conclusion. It is extremely useful in monitoring and can help gain an overview of wider public opinions behind certain topics. The applications of sentiment analysis are broad and powerful. Shifts in sentiment on social media have been shown to correlate with shifts in the stock market or quickly understand consumer attitudes. From a managerial point of view, sentiment analysis can provide means to optimize marketing strategies. In marketing tactics, sentiment analysis can help fit marketing campaigns for target audiences. Success of a campaign also lies in positive discussions amongst customers, where sentiment analysis plays a major role. Sentiment analysis can also be the base for market research and quality improvement. Moreover, the volume of digital information on the Internet has been responsible in increasing access times on items of interest for users. This voluminous information has to be filtered, prioritized and delivered to users to satisfy their search requirements for recommendations. This paper underlines the need for sentimental analysis and recommender systems based on sentimental analysis for users. Further, it proposes a Sentiment Analysis Method based on Naïve Bayes data mining technique on unigram and bigram tweets. The proposed work aims to fulfill sentimental analysis with speed for recommender systems useful to end users.
Keywords: API, Data mining, Social media, Sentiment analysis.