China 
Africa 
Explore chapters and articles related to this topic
Machine Learning Applications
Published in Peter Wlodarczak, Machine Learning and its Applications, 2019
Sentiment analysis, also called opinion mining, is the field of study that analyzes peoples opinions, sentiments, evaluations, appraisals, attitudes, and emotions towards entities such as products, services, organizations, individuals, issues, events, topics, and their attributes [24]. Sentiment analysis is extensively used by companies to determine the popularity of products or services in order to improve them. It is also used in politics to make predictions on the outcome of elections or to determine the popularity of TV programs or series. With the advent of Social Media, such as Twitter or Facebook, it has become very easy for anybody to post an opinion on a movie or on a new product on the internet. Analyzing Social Media has, thus, become mainstream in many areas. Social media mining is used for personalized ads or for targeted marketing campaigns. It has also been used to determine the credit worthiness of a person. If an applicant for a load or mortgage has wealthy Facebook friends, he is likely to be wealthy himself and considered credit worthy.
Social media analytics
Published in Catherine Dawson, A–Z of Digital Research Methods, 2019
If you are interested in finding out more about social media analytics for your research, Ganis and Kohirkar (2016) provide a good overview. Although this book is aimed at executives and marketing analysts, it nevertheless provides an interesting introduction and overview of practical tools for researchers from other disciplines and fields of study who are interested in social media analytics. Marres and Gerlitz (2016) and Brooker et al. (2016) provide relevant and interesting discussions for those interested in methods and methodology of social digital media. A method that is closely related to, and can be part of, social media analytics, is social media mining: a useful introduction to concepts, principles and methods for social media mining is provided by Zafarani et al. (2014). There are various digital tools and software packages available if you are interested in social media analytics and relevant websites are listed below. It is useful to visit some of these sites so that you can get a better idea of functions, capabilities, purposes, user-friendliness (some require programming skills, for example) and costs. You may also find it useful to read Yang et al. (2016) who describe the development of a web-based social media analytics and research testbed (SMART), which is designed ‘with the goal of providing researchers with a platform to quickly test hypotheses and to refine research questions’. This will help you to think more about how social media analytics will help to answer your own research question. It is important that you also understand more about data analytics (Chapter 10), data mining (Chapter 12) and data visualisation (Chapter 13) and the ethics of social media research (see questions for reflection, below).
Combining Theory and Data-Driven Approaches for Epidemic Forecasts
Published in Anuj Karpatne, Ramakrishnan Kannan, Vipin Kumar, Knowledge-Guided Machine Learning, 2023
Lijing Wang, Aniruddha Adiga, Jiangzhuo Chen, Bryan Lewis, Adam Sadilek, Srinivasan Venkatramanan, Madhav Marathe
Social media data can capture timely and ubiquitous disease information from social media users who may talk about their symptoms through online posts. These posts are known to be one of the best signals for early disease detection, even before diagnoses [40]. Several attempts have been made to track disease outbreaks through including the aggregate volume of flu-related social media posts as exogenous variables in purely data-driven models [2, 32, 22, 71]. However, involving social media mining techniques into agent-based modeling and simulating process has not been explored.
“Can’t think of anything more to do”: Public displays of power, privilege, and surrender in social media disaster monologues
Published in Human–Computer Interaction, 2023
Melissa Bica, Leysia Palen, Jennifer Henderson, Jennifer Spinney, Joy Weinberg, Erik R. Nielsen
Crisis informatics research has sought to show what kinds of valuable, actionable information can be extracted from social media mining of posts from the public and emergency management during disasters. For instance, research has investigated how social media posts during disasters could be used for gaining situational awareness (Ireson, 2009; Tang et al., 2015; Verma et al., 2011; Vieweg et al., 2010), verifying information (Mendoza et al., 2010; Starbird et al., 2016), solving event-specific problems (Palen et al., 2009; Sarcevic et al., 2012; White et al., 2014; Wong-Villacres et al., 2017), seeking information to reduce uncertainty (Fraustino et al., 2012; Gui et al., 2017), coping with trauma in the aftermath of a crisis (Frey, 2018), and distributing information, especially in the absence of mainstream media coverage of certain communities or populations (Anderson et al., 2016; Shklovski et al., 2008; Simon et al., 2015). The inherent assumption in much of this research is that social media is used instrumentally to achieve these goals. The research hope then is that the data can be mined, collated, and transformed into actionable information.