With the widespread usage of social media in our daily lives, user reviews emerged as an impactful factor for numerous fields including understanding consumer attitudes, determining political tendency, revealing strengths or weaknesses of many different organizations. Today, people are chatting with their friends, carrying out social relations, shopping and following many current events through the social media. However social media limits the size of user messages. The users generally express their opinions by using emoticons, abbreviations, slangs, and symbols instead of words. This situation makes the sentiment classification of social media texts more complex. In this paper a sentiment classification model for Twitter messages is proposed to overcome this difficulty. In the proposed model first the short messages are expanded with BabelNet which is a concept network. Then the expanded and the original form of the messages are included in an ensemble learning model. Consequently we compared our ensemble model with traditional classification algorithms and observed that the F-measure value is increased.

While the mobile game industry is growing with each passing day with the popularization of 3G smart devices, the creation of successful games, which may interest users, become quite important in terms of the survival of the designed game. Clustering, which has many application fields, is a successful method and its implementation in the field of mobile games is inevitable. In this study, classical ball blasting game was carried out based on clustering. In the game, clustering the color codes with K-means, Iterative K-means, Iterative Multi K-means and K-medoids methods and blasting the balls of colors located in the same cluster by bringing them together were proposed. As a result of the experiments, the suitability of clustering methods for mobile based ball blasting game was shown. At the same time, the clustering methods were compared to produce the more successful clusters and because of obtaining more accurate results and stability, the use of K-medoids method has been chosen for this game.