Social big data mining: A survey focused on opinion mining and sentiments analysis

The emergence of social media and the huge amount of data generated by them, has lead researchers to study the possibility of their exploitation in order to identify hidden knowledge. Thus, two areas are attracting more and more interest in the research community, the opinion mining and sentiment analysis. The research papers in this field are increasing rapidly. However, few survey papers have been published in this area. The rare survey papers that have been published focusing on a particular aspect (for example, the sentiment classification techniques, the challenges and application of opinion mining and sentiment analysis, etc.) and don´t concern the research work proposed this last two years. We propose, in this paper, a study of 60 recent papers (60 % published between 2013 and 2015) treating the social media mining. We compare this work regarding to several criteria. Finally, we present a table summarizing all studied work. Due to the richness of social media opinions, emotions and sentiments. We focus in this paper on opinion mining and sentiment analysis and show the position of this field in social media mining issues. Then, we describe them in detail by studying the research work on each task in these issues. We will finish by identifying a set of open issues that we will try to propose contributions in our future work.