Order from us for quality, customized work in due time of your choice.
Predictive analytics provides politicians and other stakeholders interested in electoral behavior with sound tools to evaluate peoples attitude and possible outcomes of the elections. The primary tools employed are predictive modeling, data mining, and machine learning (Buresh & Pavone, 2018). Researchers have developed numerous techniques to improve the effectiveness of diverse methods, but new tools appear and contribute to the development of the field (Buresh & Pavone, 2018; Kennedy et al., 2017). For instance, Swani and Tyagi (2017) offered a method incorporating traits of Big Data as the basis for Data Mining through the utilization of Apache Hadoop. Considerable attention is paid to the effectiveness of such traditional methods used in the prediction of electoral behavior as polls (Buresh & Pavone, 2018; Kenett et al., 2018). There is still no definite conclusion regarding the potential of election surveys as researchers provide evidence displaying effective and the benefits and downsides of this method. However, the research on predictive analytics in voter behavior analysis is not confined to exact instruments that can be employed.
The type of data to be analyzed is an important area of inquiry, and the focus on social media is apparent. Grover et al. (2019) explored the effects of social media discussions and concluded that networking and social media influence voter behavior. Another conclusion is the relevance of the data extracted from social media to predict voting trends. However, the predictive power of the analysis of social media discussions is limited, which is evident from certain studies. For instance, Vepsäläinen et al. (2017) found that the data extracted from Facebook was not instrumental in predicting voting behaviors in Finland. Smith & Gustafson (2017) noted that the analysis of searches related to the use of social media (such as Wikipedia) could be more illustrative compared to discussions and other types of information.
In addition to social media use in predicting voter behavior, researchers analyze the relevance of diverse sources of information and trends. Dalege et al. (2017) explained that network structure could shed light on the influence of peoples attitudes on voting decisions. As an illustration of this relationship, it was found that peoples sentiment concerning the Ebola outbreak had a significant impact on voter behavior as people had enhanced inclinations to conform to the current popular opinion (Beall et al., 2016). Peoples political views, and as a result, their voting behavior is also affected by their personal ideologies and beliefs that are not related to political aspects. For instance, sexism proved to have a substantial effect on presidential elections in the USA in 2016 (Ratliff et al., 2017). The analysis of different views and public opinion has proved to be a relevant area that can help in predicting voter behavior.
In conclusion, this brief literature review displays the most apparent trends in the current research on predictive analytics in political sciences. Researchers pay attention to such fields as exact statistical tools, diverse analytical instruments, appropriate sources of data, as well as numerous aspects of peoples lives that can have an impact on their decisions during elections. One of the most discussed topics in academia sat present is the utilization of social media in predictive analytics. Researchers explore diverse methods of the integration of these sources into their research and the application of different statistical tools in social media content analysis.
References
Beall, A. T., Hofer, M. K., & Schaller, M. (2016). Infections and elections. Psychological Science, 27(5), 595-605.
Buresh, D. L., & Pavone, T. (2018). Why no one knew that Hillary Clinton would lose the 2016 election. American Journal of Political Science Review, 1-19.
Dalege, J., Borsboom, D., van Harreveld, F., Waldorp, L. J., & van der Maas, H. L. J. (2017). Network structure explains the impact of attitudes on voting decisions. Scientific Reports, 7(1), 1-11. Web.
Grover, P., Kar, A., Dwivedi, Y. K., & Janssen, M. (2019). Polarization and acculturation in US Election 2016 outcomes Can twitter analytics predict changes in voting preferences? Technological Forecasting and Social Change, 145, 438-460.
Kenett, R. S., Pfeffermann, D., & Steinberg, D. M. (2018). Election pollsA survey, a critique, and proposals. Annual Review of Statistics and Its Application, 5(1), 1-24.
Kennedy, R., Wojcik, S., & Lazer, D. (2017). Improving election prediction internationally. Science, 355(6324), 515-520.
Ratliff, K. A., Redford, L., Conway, J., & Smith, C. T. (2017). Engendering support: Hostile sexism predicts voting for Donald Trump over Hillary Clinton in the 2016 U.S. presidential election. Group Processes & Intergroup Relations, 22(4), 578-593.
Smith, B., & Gustafson, A. (2017). Using Wikipedia to predict election outcomes. Public Opinion Quarterly, 81(3), 714-735.
Swani, L., & Tyagi, P. (2017). Predictive modelling analytics through data mining. International Research Journal of Engineering and Technology, 4(9), 5-11.
Vepsäläinen, T., Li, H., & Suomi, R. (2017). Facebook likes and public opinion: Predicting the 2015 Finnish parliamentary elections. Government Information Quarterly, 34(3), 524-532.
Order from us for quality, customized work in due time of your choice.