Universities play a key role in the cultural and economic development of countries. It also provides necessary and useful information to the community. Industry university collaborations are essential for the emergence and diffusion of innovations. For these reasons, perceptions of universities in the public game are extremely important. By determining whether the opinions about universities are positive or negative, more accurate decisions can be made in terms of perception. In order to change the perceptions positively, it is necessary to understand the thoughts in the society. With social media mining, ideas are effective and easier to understand than other methods. Tweets were collected in this study. Tweets were regularly recorded for three months. Then the sentences were separated into words and their frequency was determined. For this purpose Rapidminer software which is widely used in the world is used. This software has attracted interest in many data, web and social media mining studies. The main reason for this is that it is easy to use and available in many data mining tools. As a result of the study, it was determined which words are more frequently mentioned in university tweets. Further studies are needed in the future.

Keywords - University, twitter, data, perception, society

[1] A. Sağır, “Karabük’te üniversite algısı: Karabük Üniversitesi örneği,” İnsan ve Toplum Bilimleri Araştırmaları Dergisi, cilt 2(2), sayfa 49-81, 2013.
[2] M. Rathan, V. R. Hulipalled, K. R. Venugopal, and L. M. Patnaik “Consumer insight mining: Aspect based twitter opinion mining of mobile phone reviews,” Applied Soft Computing, vol. 68, p. 765-773, 2018.
[3] A. Bifet, and E. Frank, “Sentiment knowledge discovery in twitter streaming data,” In International conference on discovery science, pp. 1-15, 2010.
[4] J. Guo, P. Zhang, and L. Guo, “Mining hot topics from twitter streams,” Procedia Computer Science, vol. 9, pp. 2008-2011, 2012.
[5] S. Das, A. Dutta, G. Medina, L. Minjares-Kyle, and Z. Elgart, “Extracting patterns from Twitter to promote biking,” IATSS Research, vol. 43(1), pp. 51-59. 2019.
[6] S. Lim, C. S. “Mining Twitter data for causal links between tweets and real-world outcomes”, Expert Systems with Applications: X, vol. 3, 2019.
[7] M. Mozaffarinya, A.R. Shahriyari, M. K. Bahadori, A. Ghazvini, S.S. Athari, and G. Vahedi, “A data-mining algorithm to assess key factors in asthma diagnosis,” Revue Française d'Allergologie, vol. 59 (7), pp. 487-492, 2019.
[8] P. Ristoski, C. Bizer, and H. Paulheim, “Mining the web of linked data with rapidminer,” Web Semantics: Science, Services and Agents on the World Wide Web, vol. 35, pp. 142-151, 2015.
[9] J. Ribeiro, J. Duarte, F. Portela, and M. F. Santos, “Automatically detect diagnostic patterns based on clinical notes through Text Mining,” Procedia Computer Science, vol. 160, pp. 684-689. 2019.
[10] A. Viloria, J. R. López, K. Payares, C. Vargas-Mercado, S. E. Duran, H. Hernández-Palma, and M. A. David, “Determinating Student Interactions in a Virtual Learning Environment Using Data Mining,” Procedia Computer Science, vol. 155, pp. 587-592, 2019.
[11] W. Ji, and L. Wang, “Big data analytics based fault prediction for shop floor scheduling,” Journal of Manufacturing Systems, vol. 43, pp. 187-194, 2017.