Network Analysis of Twitter Users Posting on Online Food Ordering

Abstract

In order to interpret the findings from the analysis of the data sets obtained from social media platforms such as Twitter correctly, free from manipulations, and to increase the visibility of brands on social media platforms, effective actors on the platforms should be identified. This study analyzes the data set collected from Twitter on online food ordering with network analysis methods and techniques and compares the results of different measurement tools and algorithms used during the analysis. Local and global centrality values of influential users within the network structure are determined with a hybrid approach. For users, a weighted average was calculated based on the six centrality values, and a similarity analysis was performed with the rankings based on the mean and median values of the ranking. It is shown how a data set created with keywords can be analyzed with the network analysis method, which is a relational method. In this study, the data taken from a total of 35 428 tweets shared between January 1 and December 31, 2020, was analyzed using the Python programming language and NetwokX library. At the end of the study, it was determined whether the posts on Twitter about online food ordering belong to real users, the central actors and communities that have the power to influence the Twitter public opinion sectorally, the effectiveness of information dissemination in the posts, and the power of communication. The findings can be used as an effective tool for decision-makers by directing business resources to the right target community. It is thought that the study will contribute to filling the gap in this field in the literature, provide motivation for similar studies to be carried out on data sets obtained from other fields, and draw attention to the necessity of network analysis in detecting manipulative shares that are neglected in social media analyses and invisible in social networks.

Keywords

• Twitter Network Analysis
• Social Network Analysis
• NetworkX
• Network Structures
• Online Meal Order

Çevrimiçi Yemek Siparişine İlişkin Paylaşım Yapan Twitter Kullanıcılarının Ağ Yapısının Analizi

Abstract

Twitter gibi sosyal medya platformlarından çekilen veri setlerinin analiz sonuçlarının, yönlendirici etkilerden arındırılarak doğru şekilde yorumlanabilmesi, sosyal medya platformlarında marka görünürlüğünün artırılabilmesi maksadıyla platformlardaki etkili aktörlerin tespit edilmesi gerekir. Bunun için kullanılabilecek en uygun araçlardan biri ağ analizidir. Bu çalışmada çevrimiçi yemek siparişi konusunda Twitter’dan toplanan veri setinin ağ analiz yöntem ve teknikleri ile analizi yapılmış, kullanılan farklı ölçüm araçları ve algoritmaların sonuçları karşılaştırılmıştır. Ağ yapısı içindeki etkili kullanıcıların yerel ve küresel merkezilik değerleri hibrit bir yaklaşımla belirlenmiştir. Kullanıcılar için, altı merkezilik değerine dayalı ağırlıklı ortalama hesaplaması yapılmış, buna bağlı sıralamanın ortalama ve medyan değerlerine bağlı sıralamalarla benzerlik analizi yapılmıştır. Çalışmayla, anahtar kelimelerle oluşturulmuş bir veri setinin, ilişkisel bir yöntem olan ağ analiz yöntemi ile nasıl analiz edilebileceği gösterilmiştir. Veri seti olarak 1 Ocak-31 Aralık 2020 tarih aralığında paylaşılmış toplam 35 428 adet tweet, Python programlama dili ve NetwokX kütüphanesi kullanılarak analiz edilmiştir. Çalışma sonunda, çevrimiçi yemek siparişine ilişkin Twitter’daki paylaşımların gerçek kullanıcılara ait olup olmadığı, Twitter gündemini sektörel olarak etkileyebilme gücüne sahip merkezi konumdaki aktör ve topluluklar, paylaşımlardaki bilgi dağılımının etkinlik ve iletişimin gücü tespit edilmiştir. Yapılan tespitler, işletme kaynaklarının doğru hedef kitlelere yönlendirilmesini sağlayarak karar vericiler için etkili bir araç olarak kullanılabilecektir. Çalışmanın literatürde bu alandaki boşluğun kapatılmasına katkı sağlayacağı, benzer çalışmaların başka alanlardan elde edilmiş veri setleri üzerinde de yapılması konusunda motivasyon sağlayabileceği, sosyal medya analizlerinde ihmal edilen ve sosyal ağlarda gözle görülmeyen yönlendirici paylaşımların tespit edilmesi konusunda ağ analizinin gerekliliğine dikkat çekilebileceği düşünülmektedir.

Keywords

• Twitter Ağ Analizi
• Sosyal Ağ Analizi
• NetworkX
• Ağ Yapıları
• Çevrimiçi Yemek Siparişi

References

1. Ağcasulu, H. (2018). Sosyal Bilimlerde İlişkileri İnceleyen Bir Yöntem: Sosyal Ağ Analizi. Atatürk Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 2018 (22), 1915-1933. https://dergipark.org.tr/tr/pub/ataunisosbil/issue/39871/403709
2. Akgül, S. K., Pazarbaşı, B., & Yıldız, G. (2016). Dış Politika Alanında Siyasal İletişim Aracı Olarak Sosyal Ağ Twitter Kullanımının Karar Alma Sürecine Etkisi: Su 24 Rus Uçağının Düşürülmesi ile İlgili Türk ve Rus Siyasi Haber Aktörlerinin Tweet İletilerinin Analizi. AJIT-e: Academic Journal of Information Technology , 7 (25) , 37-70. https://doi.org/10.5824/1309-1581.2016.4.003.x
3. Al-Garadi, M.A., Varathan, K.D., Ravana, S. D., Ahmed, E., Chang, V., 2016. Identifying the influential spreaders in multilayer interactions of online social networks.  Journal of Intelligent and Fuzzy Systems 31, 2721–2735. https://doi.org/10.3233/JIFS-169112
4. Anderson, J., & Rainie, L. (2017). The Future of Truth and Misinformation Online. Pew Research Center. https://www.pewresearch.org/internet/2017/10/19/the-future-of-truth-and-misinformation-online/
5. Aragon,  E. (2023). Connecting Sunken Actors: Social Network Analysis in Maritime Archaeology. Hist Arch, 2023(57), 209-219. https://doi.org/10.1007/s41636-023-00385-4
6. ArcGIS Pro (2023, Nisan 3) Diagram Layout References.  https://pro.arcgis. com/en/pro-app/latest/help/data/network-diagrams/force-directed-layout-reference.html
7. Arslan, C., Gümüş, B., & Öztürk, İ. D. (2019). Türkiye’de Ekoloji Hareketlerinin Sınırlı Sosyal Medya Kullanımı: Ekoloji Birliği Twitter Ağı Analizi Örneği. Connectist: İstanbul University of Journal Communication Sciences, 2019 (56) 31-66.  https://dergipark.org.tr/en/pub/connectist/issue/46393/583027
8. Bakan, U. (2020). Sanat Okullarının Twitter Kullanım Karakteristiklerine İlişkin Bir Sosyal Ağ Analizi Perspektifi. Aydın Adnan Menderes Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 7(1), 138-155. https://dergipark.org.tr/tr/pub/adusobed/issue/54494/634941

9. Balkundi, P., & Kilduff, M. (2006). The Ties That Lead: A Social Network Approach to Leadership. The Leadership Quarterly, 17(4), 419-439,. https://psycnet.apa.org/doi/10.1016/j.leaqua.2006.01.001
10. Bastian, M., Heymann, S. , & Jacomy, M. (2009, Mayıs 17-20). Gephi: An Open Source Software for Exploring and Manipulating Networks.  Proceedings of the Third International ICWSM Conference, 361-362. https://doi.org/10.1609/icwsm.v3i1.13937
11. Blondel, V.D., Guillaume, J.L., Lambiotte, R. & Lefebvre, E. (2008). Fast Unfolding of Communuties in Large Networks, 2008 (1-12). arXiv:0803.0476v2 [physics. soc-ph] 25 Jul 2008
12. Brandão, F., Breda, Z., & Costa, C. (2023). Network Analysis in Tourism and Hospitality: A Comprehensive Review. Cutting Edge Research Methods in Hospitality and Tourism, Emerald Publishing, 95-120.
13. Burhan, Y., Baykara, M., & Daş, R. (2017). Sosyal Ağ Analizi ve Veri Görselleştirme Araçlarının İncelenmesi ve Uygulamalı Karşılaştırılması, 1-5. 10.1109/IDAP.2017.8090295.
14. Burt, R. S.  , Kilduff, M., & Tasselli, S.  (2013). Social Network Analysis: Foundation and Frontiers on Advantage. Annual Review of Psychology, 2013 (64), 527-547. 10.1146/annurev-psych-113011-143828
15. Chae, B. K. (2015). Insights from Hashtag #Supplychain and Twitter Analytics: Considering Twitter and Twitter Data for Supply Chain Practice and Research. Int. J. Production Economics, 2015 (165), 247-259. https://doi.org/10.1016/j.ijpe.2014.12.037
16. Chau, M., & Xu, J. (2012). Business Intelligence in Blogs: Understanding Consumer Interactions and Communities.  MIS Quarterly 36(4), 1189-1216. https://doi.org/10.2307/41703504
17. Colombia University (2023, Eylül 17). Social Network Analysis.  https://www.publichealth.columbia.edu/research/population-health-methods/social-network-analysis.
18. Conway, B. A., Kenski, K., & Wang, D. (2015). The Rise of Twitter in the Political Campaign: Searching for Intermedia Agenda-Setting Effects in the Presidential Primary. Journal of Computer-Mediated Communication, 20(4), 363-380. 10.1111/jcc4.12124.
19. Costa, A. R., & Ralha, C. G. (2023). AC2CD:An Actor-Critic Architecture for Community Detection in Dynamic Social Networks.  Knowledge-Based Systems, 2023 (261). https://doi.org/10.1016/j.knosys. 2022.110202
20. Demir, Y., & Ayhan, B. (2020). Sosyal Medyanın Gündem Belirleyicileri: Twitter’da Gündem Belirleme Süreci Üzerine Bir Sosyal Ağ Analizi. Ankara Hacı Bayram Veli Üniversitesi İletişim Kuram ve Araştırma Dergisi, 2020 (51). https://dergipark.org.tr/tr/pub/ikad/issue/57520/775120
21. Disney, A. (2020, Ocak 14). PageRank Centrality and EigenCentrality. https://cambridge-intelligence.com/eigencentrality-pagerank/#:~:text=PageRank%20centrality%3A%20the%20Google%20algorithm,any%20kind%20of%20network%2C%20though
22. Dujin, M. A. J. V., & Vermunt, J. K. (2006). What is Special About Social Network Analysis.  Hogrefe and Huber Publishers-Methodology, 2(1), 2-6. 10.1027/1614-2241.2.1.2.
23. Dwivedi, Y.K., Ismagilova, E., Y., Hughes, D.L., Carlson, J., Filieri, R., Jacobson, J., Jain, V., Karjaluoto, H., Kefi, H., Krishen, A.S. , Kumar, V., Rahman, M.M., Raman, R., Rauschnabel, P.A., Rowley, J., Salo, J., Tran, G.A., & Wang, Y. (2021). Setting the future of digital and social media marketing research: Perspectives and research propositions.  International Journal of Information Management, 2021 (59), 102168. https://doi.org/10.1016/j.ijinfomgt.2020.102168
24. El-Hashash, E.F. ve Shiekh, R.H.(2022). A Comparison of the Pearson, Spearman Rank and Kendall Tau Correlation Coefficients Using Quantitative Variables.  Asian Journal of Probability and Statistics, 20(3), 36-48, 2022.
25. Es’haghi, S.  R., & Karamidehkordi, E. (2023). Understanding the Structure of Stakeholders-Projects Network in Endangered Lakes Restoration Programs Using Social Network Analysis.   Environmental Science and Policy, 140, 172-188, 2023. j.envsci.2022.12.001
26. Everett, M.G., & Borgatti, S. P. (2013). The Dual-Projection Approach for Two-Mode Networks.  Social Networks,  35(2), 204-210. https://doi.org/10.1016/j.socnet.2012.05.004
27. Fei, L., Mo, H., Deng, Y., 2017. A new method to identify influential nodes based on combining of existing centrality measures.  Modern Physics Letters B 2017 (31), 257-267. https://doi.org/10.1142/S0217984917502438.
28. Freeman, L.C. (1978). Centrality in Social Networks Conceptual Clarification. Social Network, 1(3), 215-239. https://doi.org/10.1016/0378-8733(78)90021-7
29. Garcia, M.F., Alan, J.D., & Sánchez-Cabezudo, S. S.  (2016). Identifying the New Influences in the Internet Era: Social Media and Social Network Analysis.  Revista Española de Investigaciones Sociologicas, 2016 (153), 23-40. 10.5477/cis/reis. 153.23
30. Girvan, M., & Newman, M. (2002). Community Structure in Social and Biological Networks.  Proceedings of the National Academy of Sciences.  2001(99), 7821–7826. https://arxiv.org/abs/cond-mat/0112110v1
31. Granovetter, M.S.  (2015). The Strength of Weak Ties.  American Journal of Sociology, 78 (6), 1360-1380.
32. Graphviz (2022, Ekim 4). Graphviz-Layout Engine. https://graphviz.org/docs/layouts/
33. Günaçar, O. (2023, Mart 29) Pagerank Nedir, SEO için Neden Önemlidir?. https://www.dijitalzade.com/pagerank/
34. Hastuti, H., Maulana, H., Tompo, A., & Ferizka, Z. (2023). Analysis of Social Media Opinion on the Representation of the 2024 Presidential Election on Twitter: A Social Network Analysis.  Jurnal Studi Ilmu Pemerintahan, 4(1), 117-128. https://doi.org/10.35326/jsip.v4i1.3140
35. Heymann, S.  (2015, Şubat 23).  Fruchterman Reingold. https://github.com/gephi/gephi/wiki/Fruchterman-Reingold
36. Huzaifa, M., Bajwa, A.J., & Majid, M.R. (2023). Investigating the Role of Twitter in Manipulation of Public Opinion. Pakistan Journal of Social Research, 5(2), 197-206. 10.52567/pjsr.v5i02.1127.
37. Ishfaq, U., Khan H.U. ve Iqbal, S.  (2022), Journal of King Saud University Computer and Information Sciences, (2022 (34), 9376–9392.
38. İspir, N.B., & Deniz, K. (2017). Kasım 2015 Genel Seçimlerinde Köşe Yazarlarının Twitter Gündemine Yönelik Bir Sosyal Ağ Analizi Uygulaması. Kurgu, 25(1), 77-83. https://dergipark.org.tr/tr/pub/kurgu/issue/59642/859539
39. Jayawickrama, T.D. (2021, Ocak 29). Community Detection Algorithms.   https://towardsdatascience.com/community-detection-algorithms-9bd8951e7dae
40. Jeyasudha, J., Usha, G. (2020). An Intelligent centrality measures for influential node detection in COVID-19 Environment. Wireless Personal Communications, 2022(127), 1283–1309. https://doi.org/10.1007/s11277-021-08577-y
41. Kim, Y., Choi, T.Y., Yan, T. & Dooley, K. (2011). Structural Investigation of Supply Networks: A Social Network Analysis Approach. Journal of Operations Management, 2011 (29), 194-211. https://doi.org/10.1016/j.jom.2010.11.001
42. Kobak, K. (2022). #TikTokkapansın Hareketi: Twitter’da Sosyal Ağ Analizi. MANAS Sosyal Araştırmalar Dergisi, 11(1), 309-319. https://doi.org/10.33206/mjss. 935068
43. Luo, L., Liu, K., Guo, B., Ma, J. (2020a). User interaction-oriented community detection based on cascading analysis.  Information Sciences, 2020(510), 70-88.
44. Luo, W., Lu, N., Ni, L., Zhu, W. ve Ding, W. (2020b). Local community detection by the nearest nodes with greater centrality. Information Sciences, 2020 (517), 377-392. https://doi.org/10.1016/j.ins. 2020.01.001
45. Neo4j (2023, Nisan 4). Label Propagation. https://neo4j.com/docs/graph-data-science/current/algorithms/label-propagation/
46. NetworkX Developers (2023, Nisan 2). NetworkX-Network Analysis in Python. https://networkx.org
47. Newman, M. E. J. (2012). The Mathematics of Networks.  Center for the Study of Complex Systems.  University of Michigan, Ann Arbor, http://www-personal.umich.edu/~mejn/papers/palgrave.pdf
48. Pang, N., Sun, M., & Zhu, H. (2023). Louise or Ferdinand? Exploring the Protagonists of Love and Intrigue Using Social Network Analysis.  Digital Scholarship in the Humanities, 38 (3), 1214-1226. https://doi.org/10.1093/llc/fqad007.
49. Purbasari, R., Munajat, E., & Fauzan, F. (2022). Digital Innovation Ecosystem on Digital Entrepreneur: Social Network Analysis Approach. International Journal of E-Enterpreneurship and Innovation (IJEEI), 13(1), 1-21. 10.4018/IJEEI.319040
50. Raghavan, U. N., Albert, R., & Kumara, S.  (2007). Near Linear Time Algorithm to Detect Community Structures in Large-Scale Networks.  https://doi.org/10.1103/PhysRevE.76.036106
51. Rehman, A.U., Jiang, A., Rehman, A., Paul, A., Din, S. , Sadiq, M.T., 2020. Identification and role of opinion leaders in information diffusion for online discussion network. Journal of Ambient Intelligence and Humanized Computing, 2020 (1–13). https://doi.org/10.1007/ s12652-019-01623-5.
52. Rodda, I., & Bhavani, D. (2023, Ocak 4-7). Visualition of the Dynamics in Character Networks Using Social Network Analysis, 284-285. 10.1145/3570991.3571019
53. Saxena, A., & Iyengar, S.  (2020). Centrality Measures in Complex Networks: A Survey. 2020 (abs/2011.07190). https://doi.org/10.48550/arXiv.2011.07190
54. Seohocası (2023, Mart 29). PageRank Algoritması Nedir?. https://www.seohocasi.com/pagerank-algoritmasi-nedir/
55. Shi, Z., Rui, H. & Whinston, A.B. (2014). Content Sharing in a Social Broadcasting Environment: Evidence From Twitter. MIS Quarterly, 38 (1), 123-142.
56. Tan, P.N., Steinbach, M. & Kumar, V. (2006). Introduction to the Data Mining (Ed. Pearson Addison-Wesley). Instructor’s Solution Manual. https://www-users. cse.umn.edu/~kumar001/dmbook/sol.pdf.
57. Uğurlu, O. (2022). Comparative Analysis of Centrality Measures for Identifying Critical Nodes in Complex Networks.  Journal of Computational Science, 2022 (62), 101738.  https://doi.org/10.1016/j.jocs. 2022.101738
58. Ullah, A., wang, B., Sheng, J., Long, J., Khan, N., Gambuzza, L.V., 2021a. Identification of Influential Nodes via Effective Distance-based Centrality Mechanism in Complex Networks.  Complexity, 2021 (1–16). https://doi.org/10.1155/2021/8403738
59. Uzun, E. (2023, Nisan 2). Generators.  https://erdincuzun.com/python/13-2-generators/
60. Wan, Y.P., Wang, J., Zhang, D.G., Dong, H.Y. ve Ren, Q.H. (2018). Ranking the spreading capability of nodes in complex networks based on link significance. Physica A: Statistical Mechanics and its Applications, 2018(503), 929-937. 10.1016/j.physa.2018.08.127
61. Yang, X.H., Xiong, Z., Ma, F., Chen, X., Ruan, Z., Jiang, P., Xu, X. (2021). Identifying influential spreaders in complex networks based on network embedding and node local centrality. Physica A: Statistical Mechanics and its Applications, 2021 (573). https://doi.org/10.1016/ j.physa.2021.125971 125971.
62. Güneş, Y., & Arıkan, M. (2023). Twitter Veri Seti İçeriğinin Tanımlayıcı Analiz ile Keşfi: Çevrimiçi Yemek Siparişi Üzerine Bir Uygulama. Gazi Üniversitesi Bilişim Teknolojileri Dergisi, 16(2), 119-133. https://doi.org/10.17671/gazibtd.1190184
63. Zareie, A., Sheikhahmadi, A., Jalili, M., Fasaei, M.S. K., 2020. Finding influential nodes in social networks based on neighborhood correlation coefficient. Knowledge- Based Syst. 194,. https://doi.org/10.1016/j.knosys. 2020.105580 105580.
64. Zhang, J. & Luo, Y. (2017). Degree Centrality, Betweenness Centrality, and Closeness Centrality in Social Network. Advances in Intelligent Systems Research, 2017 (132), 300-303. https://www.atlantis-press. com/article/25874733.pdf
65. Zhao, J., Wang, Y., Deng, Y., 2020. Identifying influential nodes in complex networks from global perspective. Chaos, Solitons Fractals 133, 1777–1787. https://doi.org/10.1016/j.chaos. 2020.109637
66. Zhong, L.F., Liu, Q.H., Wang, W., Cai, S. M. (2018). Comprehensive influence of local and global characteristics on identifying the influential nodes, Physica A: Statistical Mechanics and its Applications, 2018 (511), 78-84, https://doi.org/10.1016/j.physa.2018.07.031