hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20180123005000

High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs

Ferhat Bozkurt   ORCID icon orcid.org/0000-0003-0088-5825 ; Department of Computer Engineering, Faculty of Engineering, Ataturk University, Erzurum, 25240, Turkey
Önder Çoban   ORCID icon orcid.org/0000-0001-9404-2583 ; Department of Computer Engineering, Faculty of Engineering, Adıyaman University, Adıyaman, 02040, Turkey
Faruk Baturalp Günay   ORCID icon orcid.org/0000-0001-5472-3608 ; Department of Computer Engineering, Faculty of Engineering, Ataturk University, Erzurum, 25240, Turkey
Şeyma Yücel Altay   ORCID icon orcid.org/0000-0002-7460-3993 ; Department of Computer Engineering, Faculty of Engineering, Ataturk University, Erzurum, 25240, Turkey

Puni tekst: engleski, pdf (1 MB) str. 1218-1227 preuzimanja: 81* citiraj
APA 6th Edition
Bozkurt, F., Çoban, Ö., Baturalp Günay, F. i Yücel Altay, Ş. (2019). High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs. Tehnički vjesnik, 26 (5), 1218-1227. https://doi.org/10.17559/TV-20180123005000
MLA 8th Edition
Bozkurt, Ferhat, et al. "High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs." Tehnički vjesnik, vol. 26, br. 5, 2019, str. 1218-1227. https://doi.org/10.17559/TV-20180123005000. Citirano 15.11.2019.
Chicago 17th Edition
Bozkurt, Ferhat, Önder Çoban, Faruk Baturalp Günay i Şeyma Yücel Altay. "High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs." Tehnički vjesnik 26, br. 5 (2019): 1218-1227. https://doi.org/10.17559/TV-20180123005000
Harvard
Bozkurt, F., et al. (2019). 'High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs', Tehnički vjesnik, 26(5), str. 1218-1227. https://doi.org/10.17559/TV-20180123005000
Vancouver
Bozkurt F, Çoban Ö, Baturalp Günay F, Yücel Altay Ş. High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs. Tehnički vjesnik [Internet]. 2019 [pristupljeno 15.11.2019.];26(5):1218-1227. https://doi.org/10.17559/TV-20180123005000
IEEE
F. Bozkurt, Ö. Çoban, F. Baturalp Günay i Ş. Yücel Altay, "High Performance Twitter Sentiment Analysis Using CUDA Based Distance Kernel on GPUs", Tehnički vjesnik, vol.26, br. 5, str. 1218-1227, 2019. [Online]. https://doi.org/10.17559/TV-20180123005000

Sažetak
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.

Ključne riječi
CUDA; k-NN; LDA; parallel computing; sentiment analysis; twitter

Hrčak ID: 226002

URI
https://hrcak.srce.hr/226002

Posjeta: 153 *