Deep learning can provide successful results in detecting manipulations made with bot accounts on the X (Twitter) platform and preventing disinformation. As a method for applying deep learning algorithms, numerical values in the data set can be visualized and classified by making sense of them. The methodology used in the data visualization process and the structure of the shape created are critical for deep learning and classification performance. In this article, the effect of the format used to visualize the data in the dataset to be applied deep learning on the classification performance has been demonstrated with more than 400 experimental studies. From visualization methods; The effect of deep learning applied to images created with formats such as area graph, qrcode, spectrogram graph, color map, histogram and distribution on the classification performance with Convolutional Neural Network algorithms has been demonstrated comparatively. As a result of experimental studies, it was observed that while the highest performance was achieved with 98.67% depending on the visual and algorithm used, the performance decreased to 23.70% when different visuals and algorithms were used. In this regard, it has been determined that the methodology applied in revealing the profile confidence index, the effect of the variables that make up the data set and the algorithms used are very important, but the data visualization method used in creating the figure is important. has a critical impact on performance.

Keywords - X, Social Network Analysis, Deep Learning, Transfer Learning, Data Visualization, CNN

Simon Kemp, We Are Social “Digital in 2020” Report, https://wearesocial.com/digital-2022 (2022).

Hoaxy-Indiana University, https://hoaxy.osome.iu.edu/, ( 2023).

H. İş, A. A. Müngen, T. Tuncer and M. Kaya, "Frequent pattern mining for community dedection in web logs group based habit dedection in community using network traces," 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 2017, pp. 1-7, doi: 10.1109/IDAP.2017.8090293.

H. İŞ and T. TUNCER, "Confidence Index Analysis of Twitter Users Timeline," 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 2018, pp. 1-8, doi: 10.1109/IDAP.2018.8620917.

E Ferrara, Manipulation and abuse on social media, arXiv:1503.03752, 2015.

R. Rogers, S. Niederer, The Politics of Social Media Manipulation, Amsterdam University Press, 2020.

S. Gannarapu, A. Dawoud, R. S. Ali and A. Alwan, "Bot Detection Using Machine Learning Algorithms on Social Media Platforms," 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), 2020, pp. 1-8, doi: 10.1109/CITISIA50690.2020.9371778.

İş, H.; Tuncer, T. Interaction-Based Behavioral Analysis of Twitter Social Network Accounts. Appl. Sci. 2019, 9, 4448. https://doi.org/10.3390/app9204448.

O. Loyola-Gonzalez, R. Monroy, J. Rodriguez, A. Lopez-Cuevas and J. I. Mata-Sanchez, "Contrast Pattern-Based Classification for Bot Detection on Twitter", IEEE Access, vol. 7, pp. 45800-45817, 2019.

X. Yuan, R. J. Schuchard and A. T. Crooks, "Examining Emergent Communities and Social Bots Within the Polarized Online Vaccination Debate in Twitter", Social Media + Society, vol. 5, pp. 205630511986546, 2019.

M. Zago, P. Nespoli, D. Papamartzivanos, M. G. Perez, F. G. Marmol, G. Kambourakis, et al., "Screening Out Social Bots Interference: Are There Any Silver Bullets?", IEEE Communications Magazine, vol. 57, pp. 98-104, 2019.

İş, H., Tuncer, T. (2021). A profile analysis of user interaction in social media using deep learning. Traitement du Signal, Vol. 38, No. 1, pp. 1-11. https://doi.org/10.18280/ts.380101

C. Cai, L. Li and D. Zengi, "Behavior enhanced deep bot detection in social media," 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), 2017, pp. 128-130, doi: 10.1109/ISI.2017.8004887.
[14] [14]. H. Ping and S. Qin, "A Social Bots Detection Model Based on Deep Learning Algorithm," 2018 IEEE 18th International Conference on Communication Technology (ICCT), 2018, pp. 1435-1439, doi: 10.1109/ICCT.2018.8600029.
[15] [15]. İş, H , Tuncer, T . "Twitter Users’ Emotion, Emoticons and Scaling Metrics Based Categoric Interaction Analysis". Journal of Engineering and Technology 2 (2018 ): 10-18
[16] [16]. İş, H , Tuncer, T . "Kalite Ölçekleme Kriterleri ile Sosyal Ağ Hesaplarının Etkinliğinin Belirlenmesi". Fırat Üniversitesi Mühendislik Bilimleri Dergisi 31 (2019 ): 99-108