Yazar "Ozhan, Erkan" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Automatically Discovering Relevant Images From Web Pages
    (Ieee-Inst Electrical Electronics Engineers Inc, 2020) Uzun, Erdinç; Ozhan, Erkan; Agun, Hayri Volkan; Yerlikaya, Tarık; Buluş, Halil Nusret
    Web pages contain irrelevant images along with relevant images. The classification of these images is an error-prone process due to the number of design variations of web pages. Using multiple web pages provides additional features that improve the performance of relevant image extraction. Traditional studies use the features extracted from a single web page. However, in this study, we enhance the performance of relevant image extraction by employing the features extracted from different web pages consisting of standard news, galleries, video pages, and link pages. The dataset obtained from these web pages contains 100 different web pages for each 200 online news websites from 58 different countries. For discovering relevant images, the most straightforward approach extracts the largest image on the web page. This approach achieves a 0.451 F-Measure score as a baseline. Then, we apply several machine learning methods using features in this dataset to find the most suitable machine learning method. The best f-Measure score is 0.822 using the AdaBoost classifier. Some of these features have been utilized in previous web data extraction studies. To the best of our knowledge, 15 new features are proposed for the first time in this study for discovering the relevant images. We compare the performance of the AdaBoost classifier on different feature sets. The proposed features improve the f-Measure by 35 percent. Besides, using only the cache feature, which is the most prominent feature, corresponds to 7 percent of this improvement.
  • Küçük Resim Yok
    Öğe
    The analysis of brand reputation and willingness to pay price premium with regression analysis and classification algorithms
    (Emerald Group Publishing Ltd, 2023) Ozhan, Seniz; Ozhan, Erkan; Habiboglu, Ozge
    Purpose - Brand reputation (BR) is one of the most important factors that affect the consumer-brand relationship and give businesses a competitive advantage. Businesses with a strong BR can increase their market shares and product market prices, in addition to gaining a competitive advantage. In order for businesses to have these advantages, they need to know and analyze their consumers. This study aimed to develop an alternative analysis method by using classification algorithms and regression analysis to measure and evaluate the effect of consumers' BR perceptions on their willingness to pay premium prices (WPP). Design/methodology/approach - The research data were collected from 483 participants by the online survey method due to the COVID-19 pandemic. The data were first analyzed with regression analysis, and the effect of BR on WPP was found to be significant. Then, using artificial intelligence (AI) methods that were not used in previous studies, consumers' perceptions of BR and WPP were clustered and classified. Findings - The results revealed the highest and lowest customer groups with BR and WPP and empirically demonstrated that highly accurate practical classification models can be applied to determine strategies in line with these findings. Originality/value - The model proposed in this study offers an integrated approach by using AI and regression analysis together and tries to fill the gap in the literature in this field. Therefore, the novelty of this study is to quantitatively reveal and evaluate the relationship between BR and WPP by using AI classification algorithms and regression analysis together.