Abstract
Using artificial intelligence, this article explores the intricate dynamics between ideologies, emotions, and political preferences of the electorate in Turkey. Utilizing a dataset of one billion posts from X (formerly Twitter), the study maps out political opinions, focusing on support for presidential candidates, ideological stances, and collective emotions around the pivotal 2023 Turkish presidential elections. We discuss the limitations of conventional survey techniques and introduce an ERC-funded Politus project that processes digital trace data to offer timely insights into social and political trends. The study's findings, particularly around the “prayer rug (seccade) crisis,” underscore the complexity of electoral politics and the potential of digital trace data in capturing the evolving sentiments and ideological orientations of voters. Through this computational approach, the research provides a granular depiction of Turkey's ideological map and electoral behavior, contributing significantly to the discourse on political analysis in the digital era.
| Original language | English |
|---|---|
| Pages (from-to) | 97-125 |
| Number of pages | 29 |
| Journal | Developing Economies |
| Volume | 63 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Mar 2025 |
Funding
How do we use artificial intelligence methods to understand political opinions on social media platforms? Specifically, what should be the method of measuring ideologies, political support, and emotional stance for presidential candidates? This study is based on a large research project funded by the European Research Council, which aims to (1) measure public opinion from online social platforms and (2) minimize measurement and representation errors. While survey polling has dominated public opinion research for decades, it faces decreasing confidence in the face of wide inaccuracies, highlighted recently by its notable failures to predict outcomes in high‐profile elections such as the US elections in 2016 and 2020 and the Brexit referendum. Key issues that possibly mar survey results include cognitive biases affecting memory and opinion formation, social desirability bias leading to misrepresented views, and the relative rigidity of structured surveys in a rapidly changing political landscape. Additionally, the shift in polling activities to digital platforms complicates data accuracy due to the overwhelming volume of information processed by individuals in self‐administered questionnaires. Validation studies show that self‐reports often fail to accurately capture media use (Biemer 2010 ; Groves and Lyberg 2010 ; Kennedy et al. 2018 ; Jennings and Wlezien 2018 ; Weisberg 2005 ; Saris and Sniderman 2018 ; Saris and Gallhofer 2014 ). Leveraging digital data by means of computational social science methods offers novel techniques that address these biases and help develop new insights into contemporary democratic processes. In this article, we analyze social media data with advanced AI methods to elaborate on the 2023 presidential elections in Turkey, which was a critical juncture in the two‐decade‐long political turmoil that characterized Turkish politics.
| Funders |
|---|
| European Research Council |
Keywords
- Artificial intelligence
- Electoral politics
- Emotion
- Ideology
- Turkey
ASJC Scopus subject areas
- Development
- Economics and Econometrics
Fingerprint
Dive into the research topics of 'A COMPUTATIONAL ANALYSIS OF IDEOLOGICAL POSITIONS, EMOTIONAL STANCE, AND SUPPORT FOR PRESIDENTIAL CANDIDATES IN TURKEY'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS