No abstract

No abstract

Sentiment analysis techniques are widely used for extracting feelings of users in different domains such as social media content, surveys, and user reviews. This is mostly performed by using classical text classification techniques. One of the major challenges in this field is having a large and sparse feature space that stems from sparse representation of texts. The high dimensionality of the feature space creates a serious problem in terms of time and performance for sentiment analysis. This is particularly important when selected classifier requires intense calculations as in k-NN. To cope with this problem, we used sentiment analysis techniques for Turkish Twitter feeds using the NVIDIA's CUDA technology. We employed our CUDA-based distance kernel implementation for k-NN which is a widely used lazy classifier in this field. We conducted our experiments on four machines with different computing capacities in terms of GPU and CPU configuration to analyze the impact on speed-up.

In the last decade, useful information extraction from moving objects has become widespread in the spatial-temporal data mining field with the increasing use of devices such as RFID and GPS. For this purpose, the outlier detection method, which is a subfield of data mining, was applied to the trajectory of patients and diseases in the dental health service. In this article, TRAOD and TOD-SS algorithms combining distance and density-based methods were preferred. These algorithms do not handle the moving object trajectory as a whole unlike other outlier detection techniques. They investigate whether each piece exhibits different behavior according to its neighbors by separating trajectories into pieces. So, they detect outlying trajectory pieces that other algorithms cannot locate. Algorithms preferred in this study were used in a COMB-O model we developed and their performances were compared. In addition, according to the region and clinic, the classification of patients was made. Also, clustering, which is another branch of spatial-temporal data mining, was performed for trajectory. When the COMB-O model was executed, results showed sub-trajectories that deviated from the trajectory data were successfully detected with the help of the trajectory outlier detection algorithms. Inconsistent trajectories perceived provided significant data. In addition to this, successful classification was performed by making use of non-linear classification features of DVM. Moreover, stops and moves in the Faculty of Dentistry were detected by using CB-SMoT and DB-SMoT which are clustering algorithms.

No abstract