Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- BildiriAçık Erişim2018Scopus SJRQ2Evaluating deep learning models for sentiment classification
Ay Karakuş, Betül; Talo, Muhammed; Hallaç, İbrahim Rıza; Aydin, Galip
Deep learning has emerged as an effective solution to various text mining problems such as document classification and clustering, document summarization, web mining, and sentiment analysis. In this paper, we describe our work on investigating several deep learning models for a binary sentiment classification problem. We used movie reviews in Turkish from the website www.beyazperde.com to train and test the deep learning models. We also report a detailed comparison of the models in terms of accuracy and time performances. Two major deep learning architectures used in this study are Convolutional Neural Networks and Long Short-Term Memory. We built several variants of these models by changing the number of layers, tuning the hyper-parameters, and combining models. Additionally, word embeddings were created by applying the word2vec algorithm with a skip-gram model on a large dataset (∼ 13 M words) composed of movie reviews. We investigate the effect of using the pre-word embeddings with these models. Experimental results have shown that the use of word embeddings with deep neural networks effectively yields performance improvements in terms of run time and accuracy.
AtıfScopus55WoS40OpenAlex64
İncele - MakaleAçık Erişim2017Scopus SJRQ2Big social network data and sustainable economic development
Can, Umit; Alatas, Bilal
New information technologies have led to the rapid and effective growth of social networks. The amount of data produced by social networks has increased the value of the big data concept, which is one of the popular current phenomena. The immediate or unpredictable effects of a wide array of economic activities on large masses and the reactions to them can be measured by using social media platforms and big data methods. Thus, it would be extremely beneficial to analyze the harmful environmental and social impacts that are caused by unsustainable business applications. As social networks and big data are popular realms currently, their efficient use would be an important factor in sustainable economic development. Accurate analysis of people's consumption habits and economic tendencies would provide significant advantages to companies. Moreover, unknown consumption factors that affect the economic preferences of individuals can be discovered and economic efficiency can be increased. This study shows that the numerous solution opportunities that are provided by social networks and big data have become significant tools in dynamic policy creation by companies and states, in solving problems related to women's rights, the environment, and health.
AtıfScopus42WoS34OpenAlex50İncele - BildiriAçık Erişim2017Sosyal aǧ analizi ve veri görselleştirme araçlarinin incelenmesi ve uygulamali karşilaştirilmasi
Bürhan, Yücel; Baykara, Muhammet; Daş, Resul
Social network analysis has become an important issue in recent years because of the development and use of social networks widespread. Almost any kind of data can be easily obtained as valuable information about actors from these data. In this study, general information about the most used social network analysis and visualization tools are given. The author-subject network that analyzed with the help of link estimation methods, the author-writer network showing the links between co-authors is drawn and displayed visually through four different social network analysis and visualization tools.
AtıfScopus1OpenAlex5İncele