Due to the advent of Web 2.0, the size of social media content (SMC) is growing rapidly and likely to increase faster in the near future. Social media applications such as Instagram, Twitter, Facebook, etc. have become an integral part of our lives, as they prompt the people to give their opinions and share information around the world. Identifying emotions in SMC is important for many aspects of sentiment analysis (SA) and is a top-level agenda of many firms today. SA on social media (SASM) extends an organization's ability to capture and study public sentiments toward social events and activities in real time. This chapter studies recent advances in machine learning (ML) used for SMC analysis and its applications. The framework of SASM consists of several phases, such as data collection, pre-processing, feature representation, model building, and evaluation. This survey presents the basic elements of SASM and its utility. Furthermore, the study reports that ML has a significant contribution to SMC mining. Finally, the research highlights certain issues related to ML used for SMC.
TopOverview
In recent days, social media applications have emerged as leading mass media, as they allow users to work collaboratively and publish their content (Wadawadagi & Pagi, in press; Anami et al. 2014). Accordingly, large volumetric semantically rich information is being generated and accumulated every day in the form of tweets, posts, blogs, news, comments, reviews, etc. Investigating hidden but potentially useful patterns from a huge collection of SMC is a critical task, due to users struggle with overloaded information (Yang & Rim, 2014). SASM is a practice of collecting data from social networks and automatically identifying whether a phrase comprehends sentiment or opinionative content, and further determines the opinion polarity (Jianqiang & Xiaolin, 2017). However, detecting sentiment in SMC faces several challenges, as they are composed of incomplete, chaotic and unstructured sentences, erratic phrases, ungrammatical expressions, and non-lexical words. Moreover, it is hard to detect correlations among opinion sentences due to the broad range of linguistic issues and drives the SA still more challenging (Choi & Park, 2019). To cope with these challenges a real-time SA system needs to be developed to process a large volume of sentiment data in very little time. Furthermore, knowing the public emotions is very useful in many fields, including marketing, politics, online shopping, and many more (Jianqiang & Xiaolin, 2017). To increase productivity, many business firms encourage their customers to participate in virtual discussions, asking for their feedback, opinions, and suggestions.