Advertising recommendation system based on dynamic data analysis on Turkish speaking Twitter users

Sevli, Onur; Küçüksille, Ecir Uğur

doi:10.17559/tv-20151020205558

Cited by 2 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset contains randomly collected public Twitter feeds by sending emoticons as a query key [23], [24]. The TTF dataset has totally 20000 Twitter feeds (after preprocessing) which are equally distributed between negative and positive categories [25]. Each tweet in this dataset is labeled by using distant supervision approach that considers whether related tweet contains an emoticon from the following positive and negative groups:…”

Section: Selected Dataset As Evaluation Materialsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

Section: Selected Dataset As Evaluation Materialsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

Emerging trends in social media marketing: a retrospective review using data mining and bibliometric analysis

Bashar,

Wasiq,

Nyagadza

et al. 2024

Futur Bus J

View full text Add to dashboard Cite

The study conducts a comprehensive retrospective analysis of the social media marketing literature along with text mining and bibliometric analysis using data obtained from the Scopus database. The analysis is conducted for the literature published during 2007–2022 using VOSviewer application and Biblioshiny. The analysis revealed the publication trend and emerging themes in the research landscape of social media marketing. This study has pointed towards important theoretical and practical implications pertaining to the social media marketing. It contributes to the understanding of social media marketing research by identifying and listing the best journal, authors, country, documents, most occurred words, social and intellectual structure, and emerging research trends. The results revealed that social media marketing research is at the focal point of the researchers throughout the word. This study found that there are lack of studies from firm perspective especially small retailers; adoption of disruptive technologies such as AI, ML and block chain and its impact need more exploration.

show abstract

Advertising recommendation system based on dynamic data analysis on Turkish speaking Twitter users

Cited by 2 publications

References 30 publications

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

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

Emerging trends in social media marketing: a retrospective review using data mining and bibliometric analysis

Contact Info

Product

Resources

About