Issues of Social Data Analytics with a New Method for Sentiment Analysis of Social Media Data

Abstract

Social media data consists of feedback, critiques and other comments that are posted online by internet users. Collectively, these comments may reflect sentiments that are sometimes not captured in traditional data collection methods such as administering a survey questionnaire. Thus, social media data offers a rich source of information, which can be adequately analyzed and understood. In this paper, we survey the extant research literature on sentiment analysis and discuss various limitations of the existing analytical methods. A major limitation in the large majority of existing research is the exclusive focus on social media data in the English language. There is a need to plug this research gap by developing effective analytic methods and approaches for sentiment analysis of data in non-English languages. These analyses of non-English language data should be integrated with the analysis of data in English language to better understand sentiments and address people-centric issues, particularly in multilingual societies. In addition, developing a high accuracy method, in which the customization of training datasets is not required, is also a challenge in current sentiment analysis. To address these various limitations and issues in current research, we propose a method that employs a new sentiment analysis scheme. The new scheme enables us to derive dominant valence as well as prominent positive and negative emotions by using an adaptive fuzzy inference method (FIM) with linguistics processors to minimize semantic ambiguity as well as multi-source lexicon integration and development. Our proposed method overcomes the limitations of the existing methods by not only improving the accuracy of the algorithm but also having the capability to perform analysis on non-English languages. Several case studies are included in this paper to illustrate the application and utility of our proposed method.