Seçim Coğrafyasına Yeni Bir Yaklaşım Olarak Sosyal Medya Veri Madenciliği

Abstract

Sosyal medyada yer alan bireysel söylemler ve tutumlar, sahip oldukları mekânsal-zamansal bilgilerle birlikte seçim coğrafyası için kullanıldığında seçmen davranışları ve oy tercihleri hakkında önemli ipuçları sağlayabilmektedir. Sosyal medya verilerini kullanan seçim odaklı farklı çalışmalar olsa da bu çalışmalar oyların ardındaki nedenleri mekânsal olarak anlamaktan uzak kalmıştır. Bu araştırma, seçim coğrafyası alanı için yeni sayılabilecek veri ve yöntemleri kullanarak seçmen davranışı ve oy vermedeki farklılıkları anlamayı, oy verme üzerindeki bağlamsal etkileri ortaya çıkarmayı amaçlamaktadır. Araştırmada X (Twitter) üzerinde Yenimahalle (Türkiye) ilçesinden paylaşılan seçim odaklı tweetleri elde ediyor, duygu durumlarını belirliyor, tweetlerdeki baskın konuları tespit ediyor ve adayların X (Twitter) üzerindeki popülerlik oranları ile gerçek oy oranları arasındaki ilişkiyi ortaya koyuyoruz. Sonuç olarak, X (Twitter) üzerinde kullanıcılar tarafından oluşturulan mekân-zamansal veriler, seçmen davranışı/katılımı ve oy vermedeki farklılıkları anlamanın yanı sıra oy verme üzerindeki bağlam etkilerinin ortaya çıkarılmasında önemli bir yer tutmaktadır.

Keywords

• Seçim coğrafyası
• Bağlam etkisi
• Doğal dil işleme
• Sosyal medya
• X (Twitter)

Social Media Data Mining as a Novel Approach to Electoral Geography

Abstract

When individual discourses and attitudes on social media are used for electoral geography with their spatio-temporal information, they can provide essential clues about voter behavior and voting preferences. Although there are different election-based studies using data from social media, these studies have remained far from spatial understanding of the reasons behind the votes. This research aims to understand the differences in voter behavior and voting, along with revealing the context effects on voting by using this new data and methods in the field of electoral geography. We obtain the election-oriented tweets on X (Twitter) posted from Yenimahalle (Turkey), determine sentiment states, identify the dominant topics in the tweets, and reveal the relationship between the popularity rates of the candidates on X (Twitter) and the actual vote rates. Consequently, user-generated spatio-temporal data on X (Twitter) is essential in understanding the differences in voter behavior/participation and voting, as well as in revealing context effects on voting.

Keywords

• Electoral geography
• Context effects
• Natural language processing
• Social media
• X (Twitter)

References

1. Adams, P. C. (2015). Social media.In Agnew, J.A., Mamadouh, V., Secor, A. J., Sharp, J. (Eds.), The Wiley Blackwell Companion to Political Geography, West Sussex: John Wiley & Sons. 393-406.
2. Agnew, J. A. (1996). Mapping politics: How context counts in electoral geography. Political Geography, 15 (2), 129–146. doi: 10.1016/0962-6298(95)00076-3
3. Axenov, K. E., Papadopoulos, A. G. (1997). Long-term tendencies in the electoral behavior and the geography of voting in St. Petersburg: 1989–1995. GeoJournal, 42 (4), 433-448. doi: 10.1023/A:1006854916286
4. Bayraktar, S. U. (2011). Yerelin seçimi, çözümlemenin yereli: Mersin’de Mart 2009 il genel meclisi ve büyükşehir belediye başkanlığı seçimleri. Toplum ve Bilim, (121), 9-47.
5. Bekaroğlu, E. A., Kaya Osmanbaşoğlu, G. (2021). Introduction to Turkey’s electoral geography: An overview since 1950. In Bekaroğlu, E. A., Kaya Osmanbaşoğlu, G. (Eds.), Turkey’s Electoral Geography Trends, Behaviors, and Identities, Oxon-New York: Routledge. 1-23.
6. Belcastro, L., Cantini, R., Marozzo, F., Talia, D., Trunfio, P. (2020). Learning Political Polarization on Social Media Using Neural Networks. IEEE Access, 8, 47177-47187. doi: 10.1109/ACCESS.2020.2978950.
7. Bermingham, A., Smeaton, A. (2011). On using Twitter to monitor political sentiment and predict election results. In Bandyopadhyay, S., Okumura, M. (Eds.) Proceedings of the Workshop on Sentiment Analysis Where AI Meets Psychology (SAAIP 2011), Chiang Mai: Asian Federation of Natural Language Processing, 2-10.
8. Books, J. W., Prysby, C. L. (1991). Political Behavior and The Local Context. New York: Praeger Publishers.

9. Cantey, C. (2013). Data-mining social media for spatiotemporal patterns of negative opinion. Master’s thesis. Wisconsin: University of Wisconsin–Madison, College of Letters and Science.
10. Ceron, A., Curini, L., Iacus, S. M., Porro, G. (2014). Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France. New Media & Society, 16(2), 340-358. doi: 10.1177/1461444813480466
11. Chauhan, P., Sharma, N., Sikka, G. (2023). Application of Twitter sentiment analysis in election prediction: a case study of 2019 Indian general election. Social Network Analysis and Mining, 13(1), 1-29. doi: 10.1007/s13278-023-01087-8
12. Convery, I., Cox, D. (2012). A review of research ethics in internet-based research. Practitioner Research in Higher Education, 6 (1), 50-57. Retrieved from http://insight.cumbria.ac.uk/id/eprint/1334/
13. Cox, K. R. (1969). The voting decision in a spatial context. Progress in Geography 1, 81-117.
14. Çarkoğlu, A., Avcı, G. (2002). An analysis of the electorate from a geographical perspective. In Sayari S., Esmer, Y. (Eds.), Politics, parties, and elections in Turkey, Boulder-London: Lynne Rienner Publishers. 115-136.
15. Çarkoğlu, A., Hinich, M. J. (2006). A spatial analysis of Turkish party preferences. Electoral Studies, 25, 369-392. doi: 10.1016/j.electstud.2005.06.010
16. GeeksforGeeks (2023). What is web scraping and how to use it? Access date: 28.12.2023, Retrieved from https://www.geeksforgeeks.org/what-is-web-scraping-and-how-to-use-it/
17. Goodchild, M. F. (2007). Citizens as sensors: the world of volunteered geography. GeoJournal, 69 (4), 211-221. doi: 10.1007/s10708-007-9111-y
18. Gundecha, P., Liu, H. (2012). Mining social media: a brief introduction. Tutorials in Operations Research, 1-17. doi: 10.1287/educ.1120.0105
19. Güven, A. (2020). Latent Dirichlet Allocation (LDA) Algoritması. Retrieved from https://medium.com/@anilguven1055/latent-dirichlet-allocation-ldaalgoritmas%C4%B1 13154d246e05
20. Han, J., Kamber, M. (2001). Data Mining: Concepts and Techniques. Massachusetts: Morgan Kaufmann Publishers.
21. Harrison, T. M., Barthel, B. (2009). Wielding new media in Web 2.0: Exploring the history of engagement with the collaborative construction of media products. New Media & Society, 11 (1-2), 155-178. doi: 10.1177/1461444808099580
22. IBM. (2021). Data Mining. Retrieved from https://www.ibm.com/cloud/learn/data-mining
23. Ibrahim, M., Abdillah, O., Wicaksono, A. F., Adriani, M. (2015). Buzzer detection and sentiment analysis for predicting presidential election results in a Twitter nation. 2015 IEEE International Conference on Data Mining Workshop (ICDMW), Los Alamitos, CA: IEEE Computer Society. 1348-1353.
24. İncioğlu, N. (2002). Local elections and electoral behavior. Sayari, S., Esmer, Y. (Eds.), Politics, Parties, and Elections in Turkey, Boulder-London: Lynne Rienner Publishers. 73-90.
25. Jaidka, K., Ahmed, S., Skoric, M., Hilbert, M. (2019). Predicting elections from social media: a three-country, three-method comparative study. Asian Journal of Communication, 29(3), 252-273. doi: 10.1080/01292986.2018.1453849
26. Johnston, R. J., Pattie, C. (2006). Putting Voters in Their Place: Geography and Elections in Great Britain. Oxford: Oxford University Press.
27. Kalaycıoğlu, E. (1999). The shaping of party preferences in Turkey: Coping with the Post-Cold War era. New Perspectives on Turkey, (20), 47-76. doi: 10.1017/S0896634600003137
28. Kamalak, İ. (2013). Yerelin yerel seçimlere etkisi: belediye başkan adayları üzerinden bir inceleme. Dokuz Eylül Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 15 (3), 419-446. Retrieved from https://dergipark.org.tr/en/pub/deusosbil/issue/4632/63145
29. Khan, A., Boudjellal, N., Zhang, H., Ahmad, A., Khan, M. (2023). From social media to ballot box: Leveraging location-aware sentiment analysis for election predictions. Computers, Materials & Continua, 77(3), 3037-3055. doi: 10.32604/cmc.2023.044403
30. Kozinets, R. V. (2002). The field behind the screen: Using netnography for marketing research in online communities. Journal of Marketing Research, 39 (1), 61-72. doi: 10.1509/jmkr.39.1.61.18935
31. Köksal, A. (2020). BERT-Sentiment-analysis-Turkish, GitHub repository. Retrieved from https://github.com/akoksal/BERT-Sentiment-Analysis-Turkish
32. Liu, R., Yao, X., Guo, C., Wei, X. (2021). Can we forecast presidential election using Twitter data? An integrative modelling approach. Annals of GIS, 27(1), 43-56. doi: 10.1080/19475683.2020.1829704
33. Markham, A. N. (2004). Internet communication as a tool for qualitative research. In Silverman, D. (Ed.), Qualitative research: Theory, method and practice (2nd Ed.), London: Sage Publications. 95-124.
34. Marozzo, F., Bessi, A. (2018). Analyzing polarization of social media users and news sites during political campaigns. Social Network Analysis and Mining 8 (1). doi: 10.1007/s13278-017-0479-5
35. McPhail, I. R. (1971). Recent trends in electoral geography. In Johnston, R. J., Chapman, J., Soons, J. M. (Eds.), Proceedings of the Sixth New Zealand Geography Conference, Christchurch: New Zealand Geographical Society, 7-12.
36. Miş, N., Duran, H. (2019). İttifaktan blok siyasetine 31 Mart yerel seçimleri. Adam Akademi Sosyal Bilimler Dergisi, 9 (2), 363-393. doi: 10.31679/adamakademi.634750
37. Murugesan, S. (2007). Understanding Web 2.0. IT Professional, 9 (4), 34-41. doi: 10.1109/MITP.2007.78
38. O'Connor, B., Balasubramanyan, R., Routledge, B., Smith, N. (2010). From tweets to polls: Linking text sentiment to public opinion time series. Proceedings of The Fourth International AAAI Conference on Weblogs and Social Media, California: The AAAI Press. 122-129.
39. Oğlakcı, B., Uzun, A. (2021). Metinsel mesajdan mekânsal bilgiye: coğrafya araştırmalarında veri kaynağı olarak sosyal ağ Twitter. lnternational Journal of Geography and Geography Education, (44), 176-191. doi: 10.32003/igge.927907
40. Oikonomou, L., Tjortjis, C. (2018). A Method for Predicting the Winner of the USA Presidential Elections using Data extracted from Twitter. South-Eastern European Design Automation, Computer Engineering, Computer Networks and Society Media Conference (SEEDA_CECNSM), 1-8. Doi: 10.23919/SEEDA-CECNSM.2018.8544919.
41. Okcu, M., Albayrak, M., Topal, K., Turhan, G., Altıntaş. (2019). Yapay zekayla sosyal medyadan şehir verisini dinlemek. Şehircilik ve Mutlu Şehirler Uluslararası Akademik Bildiriler Kitabı, Kocaeli: Kocaeli BB. 302-321.
42. O’Loughlin, J. (1981). The neighbourhood effect in urban voting surfaces: a crossnational analysis. In Burnett, A. D., Taylor, P. J. (Eds.), Political Studies from Spatial Perspectives: Anglo-American Essays on Political Geography, Chichester: John Wiley. 357-388.
43. Olshannikova, E., Olsson, T., Huhtamäki, J., Kärkkäinen, H. (2017). Conceptualizing big social data. Journal of Big Data, 4(1), 1-19. doi: 10.1186/s40537-017-0063-x
44. Özen, I. C., Kalkan, K. O. (2017). Spatial analysis of contemporary Turkish elections: a comprehensive approach. Turkish Studies, 18, 358-377. doi: 10.1080/14683849.2016.1259576
45. Pattie, C., Johnston, R. J. (2009). Electoral geography. In Kitchin, R., Thrift, N. (Eds.), International Encyclopedia of Human Geography, Elsevier. 405–422.
46. Ramteke, J., Shah, S., Godhia, D., Shaikh, A. (2016). Election result prediction using Twitter sentiment analysis. 2016 International Conference on Inventive Computation Technologies (ICICT), Piscataway, NJ: IEEE. 1-5.
47. Reynolds, D.R. (1990). Whither electoral geography? A critique. In Johnston, R. J., Shelley, F.M., Taylor, P.J. (Eds.), Developments in Electoral Geography, London: Routledge. 22-35.
48. Sakaki, T., Okazaki, M., Matsuo, Y. (2010). Earthquake Shakes Twitter Users: Real-time Event Detection by Social Sensors. Proceedings of the 19th International Conference on World Wide Web, New York: Association for Computing Machinery. 1-10.
49. Scanfeld, D., Scanfeld, V., Larson, E. L. (2010). Dissemination of health information through social networks: Twitter and antibiotics. American Journal of Infection Control, 38 (3), 182-188. doi: 10.1016/j.ajic.2009.11.004
50. Seymour, W. S. (2001). In the flesh or online? Exploring qualitative research methodologies. Qualitative Research, 1 (2), 147-168. doi: 10.1177/146879410100100203
51. Shelley, F. M. (2006). Electoral geography. In Warf, B. (Ed.), Encyclopedia of Human Geography, California: SAGE Publications. 127-128.
52. Shin, M. (2015). Electoral geography in the twenty‐first century. In Agnew, J. A., Mamadouh, V. Secor, A. J., Sharp, J. (Eds.) The Wiley Blackwell Companion to Political Geography, West Sussex: John Wiley & Sons. 279-296.
53. Snelson, C. L. (2016). Qualitative and Mixed Methods Social Media Research: A Review of the Literature. International Journal of Qualitative Methods, 15(1). doi: 10.1177/1609406915624574
54. Soler, J. M., Cuartero, F.i Roblizo, M. (2012). Twitter as a tool for predicting elections results. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Los Alamitos, CA: IEEE Computer Society. 1194-1200.
55. Song, M., Kim, M. C., Jeong, Y. K. (2014). Analyzing the political landscape of 2012 Korean Presidential Election in Twitter. IEEE Intelligent Systems, 29 (2), 18-26. Doi: 10.1109/MIS.2014.20.
56. Şahin, S. Z., Çekiç, A., Gözcü, A. (2014). An attempt of a local government monography method in Ankara: The example of Çankaya Municipality. Journal of Ankara Studies, 2 (2), 159-183.
57. Şahin, S. Z., Gözcü, A. (2017). Monograph of Yenimahalle Municipality. Journal of Ankara Studies, 5 (2), 283-318. Temple, L. (2023). Reckoning with the digital turn in electoral geography. Progress in Human Geography, 47(4), 555-574. doi: 10.1177/03091325231170328
58. Tumasjan, A., Sprenger, T. O., Sandner, P. G., Welpe, I. M. (2011). Predicting elections with Twitter: What 140 characters reveal about political sentiment. Social Science Computer Review, 29 (4), 402-418. doi: 10.1609/icwsm.v4i1.14009
59. Tweet Location Metadata, (2023). Tweet with Twitter Place. Access date: 05.08.2023. Retrieved from https://developer.twitter.com/en/docs/twitter-api/v1/data-dictionary/object-model/geo#:~:text=Tweet%20Location%20Metadata&text=There%20are%20two%20'root%2Dlevel,a%20Tweet%3A%20coordinates%20and%20place%20.&text=The%20place%20object%20is%20always,is%20assigned%20an%20exact%20location.
60. Wang, L., Gan, J. Q. (2018). Prediction of the 2017 French election based on Twitter data analysis using term weighting. 10th Computer Science and Electronic Engineering (CEEC 2018), Piscataway, NJ: IEEE. 231-235.
61. Wuthrich, F. M. (2015). National Elections in Turkey: People, Politics, and The Party System. Syracuse: Syracuse University Press.
62. Yıldırım, A., Şimşek, H. (2016). Sosyal Bilimlerde Nitel Araştırma Yöntemleri. (10. Ed.). Ankara: Seçkin Yayıncılık. Zafarani, R., Abbasi, M. A., Liu, H. (2014). Social Media Mining: An Introduction. New York: Cambridge University Press.