Abstract
In this paper, we propose a four-step guideline to perform twitter mining based on consumer's opinion and adverse drug reaction of certain drugs. Due to advances in technology and increased use of social networks, there has been a tremendous amount of public data which grows from terabytes to petabytes. The accessibility of this enormous amount of data offers vast research opportunities for extracting meaningful opinion data for many applications. Drug consumption is one that could be benefited, from methodical sentiment analysis techniques. In this paper we have focused on social media mining for drug related information. To clean the Twitter streaming data and to increase the accuracy of the results, a spam filter and a preprocessing procedure have been developed, to retrieve relevant information about certain drug. Processing and analysis of data were done on 1579 tweets using R-programming. The results show that Twitter mining with formed word cloud is a very useful technique to get the majority of consumer's opinion about the consumed drug. The obtained results shows that, real time streaming of social networking data could help in early detection and prediction of side effects of the drug for patient safety.