In 2013 Daniel Gayo-Avello captured the state of the art regarding election prediction with social media publishing a meta-analysis, the very first one in this field of study. Concluding after an extensive literature review, that the „prevailing view [among scientists] is overly optimistic“, Gayo-Avello declares three major problems, that have to be addressed by future research: 1) The need to produce a true forecast, that is published before the election. 2) The need to take into account the biases on Twitter, especially the unrepresentativeness of the sample. 3) The need to incorporate sentiment rather than just tweet volume.
The research question of this paper is very similar to Gayo-Avello's meta-analysis, to give an overview of the current state of the art two years later, assess if the past problems and questions scientists raised have been discussed, and in the last step answer, whether or not Twitter can be used as an efficient alternative to traditional electoral forecasting.
Although two years might not be a lot of time considering the time it takes for a study to be conducted and published, the number of scientists contributing to this fairly new field of research is extremely high, therefore making much more understanding in a short time possible.
Necessarily I will only highlight a selection of studies, not being able to shed light on all studies. In a nutshell, I will take the 3 demands by Gayo-Avello as a guideline to order recent studies, then give a quick insight into the current discussion in the scientific field, and in the end come to the conclusion, that traditional polling and social media-based approaches do not have to be exclusive, but can and should be combined in future research.
Table of Contents
1. Introduction
2. Cornerstones of Research
3. Recent Studies
4. Scientific Community
5. Conclusion
Objectives and Research Themes
This paper aims to provide an updated meta-analysis, two years after Gayo-Avello's seminal work, to evaluate whether scientific advancements have successfully addressed the core challenges of using social media for election forecasting and to determine if Twitter can serve as an efficient alternative to traditional polling methods.
- Evolution of social media-based election forecasting methods
- Assessment of Gayo-Avello's three major research demands
- Integration of sentiment analysis versus tweet volume metrics
- Addressing sampling bias and demographic representativeness
- Synthesis of traditional polling and social media data
Excerpt from the Book
Recent Studies
Authors Kagan, Stevens, and Subrahmanian (2015) predicted the 2013 Pakistani and 2014 Indian elections with a dynamic model that presented daily forecasts, based on Twitter tweets. In both elections they correctly predicted the winner (that is the prime minister) well ahead of time. Furthermore, they used the sentiment analysis in contrast to the mere tweet volume method, which Tumasjan et al. (2010) employed in their study. With their approach they already address two of Gayo-Avello's concerns, only disregarding the bias concern. Kagan et al. do acknowledge his point though and state, that although the sample is indeed biased, “perhaps biases get worked out when such large numbers are considered” (2015, 4). Admittedly this is a rather universal proclamation, but in their study the bias really does seem small enough to not falsify the results. What has to be noted is their interesting choice of countries though. The choice of India and Pakistan now shows researchers, that even in relatively poor countries, where comprehensive Internet connection is not as self-evidently as in Europe or the USA, Twitter still provides a solid indicator of public sentiment. Furthermore, their dynamic model could identify the most influential individuals on Twitter, which is very valuable information for an election campaign.
Chapter Summary
Introduction: This chapter outlines the emergence of big data in political science and presents the core challenges defined by Gayo-Avello regarding the use of social media for election forecasting.
Cornerstones of Research: This section reviews the foundational studies from the early 2010s and establishes the criteria for selecting current research to evaluate progress.
Recent Studies: This chapter analyzes selected studies from the past two years, applying Gayo-Avello’s guidelines to assess improvements in forecasting accuracy and methodology.
Scientific Community: This part examines the shifting landscape of political science, specifically the debate between traditional pollsters and new social media-based approaches, while suggesting a fusion of both.
Conclusion: The final chapter summarizes how the scientific community has adopted better standards and advocates for a combined approach using both traditional polls and social media data.
Keywords
Election Forecasting, Social Media, Twitter, Big Data, Sentiment Analysis, Public Opinion, Political Science, Electoral Predictions, Sampling Bias, Meta-Analysis, ARIMA Model, Hopkins and King Method, Traditional Polling, Data Fusion, Political Behavior.
Frequently Asked Questions
What is the primary focus of this research paper?
The paper investigates the current state of election forecasting using social media data, specifically evaluating how recent studies have addressed methodological problems identified in earlier meta-analyses.
What are the central themes discussed in the work?
Key themes include the transition from tweet volume counting to sentiment analysis, the challenge of representativeness and bias in social media samples, and the potential for integrating traditional polling with social media data.
What is the main research question?
The research assesses whether social media, particularly Twitter, has matured into an efficient and reliable alternative or complement to traditional electoral forecasting methods.
Which scientific methods are analyzed?
The paper reviews various approaches, including simple tweet volume counting, dynamic ARIMA models, and the supervised sentiment analysis known as the Hopkins and King (HK) method.
What is covered in the main body of the paper?
The main body evaluates recent case studies—such as those by Kagan et al., Franch, and Ceron et al.—and explores the divide within the scientific community regarding the validity of these new methods.
Which keywords define this paper?
The work is defined by terms like election forecasting, sentiment analysis, Twitter, bias, and the fusion of traditional and modern data streams.
How did the 2015 UK General Election serve as a counter-example?
The 2015 UK election showed the limitations of existing social media models, as many failed to predict the specific regional influence of the Scottish National Party and the failure of traditional polls, highlighting that every election is a unique event.
Why does the author advocate for a fusion of methods?
The author argues that combining traditional quantitative opinion polling with qualitative social media analysis could increase predictive accuracy while overcoming the individual biases inherent in each method alone.
- Arbeit zitieren
- Marla van Nieuwland (Autor:in), 2015, The Future Of Election Forecasting Using Social Media Based Methods. Prospect or Pitfall?, München, GRIN Verlag, https://www.hausarbeiten.de/document/310629
