Fuzzy based implicit sentiment analysis on quantitative sentences

Abstract

With the rapid growth of social media on the web, emotional polarity computation has become a flourishing frontier in the text mining community. However, it is challenging to understand the latest trends and summarise the state or general opinions about products due to the big diversity and size of social media data and this creates the need of automated and real time opinion extraction and mining. On the other hand, the bulk of currently research has been devoted to study the subjective sentences which contain opinion keyword and limited work has been reported for objective statement that implies sentiment. In this regard, fuzzy based knowledge engineering model has been developed for sentiment classification of special group of such sentences including the change or deviate from desired range or value. Drug reviews are the rich source of such statements. Therefore, in this research, 210 reviews were collected from patient’s review for building corpus. These reviews have been selected from different cholesterol lowering drugs. Medical experts cooperated in this research for building Gold standard corpus. Pre-processing operations including extracting medical terms and their corresponding values have been done on this corpus. An appropriate technique has been developed to map each of these medical terms to their corresponding values. Resulted documents were stored into XML file. Determining sentiment polarity of each sentence employing fuzzy knowledge based system is the next step of this research. The main conclusion through this study is, in order to increase the accuracy level of drug opinion mining system, objective sentences which imply opinion should be taken into consideration.