Yazar "Kekul, Hakan" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Developing a new ensemble method for sentiment analysis in mobile assisted language learning: a case study for Duolingo
    (Inderscience Enterprises Ltd, 2025) Kekul, Hakan; Polatgil, Mesut
    In today's world, mobile devices and mobile technologies have become one of the indispensable elements, especially for young people. Learning activities using these technologies have also become widespread, and mobile assisted language learning (MALL) has become even more important. This study was conducted to evaluate users' opinions about MALL methods. For this purpose, Duolingo user comments, which is currently the most known and used mobile application in foreign language education, were used. One million comments to the app are classified in terms of sentiment analysis. In the study, a new model was proposed by combining different feature extraction and classification methods and the results were compared. It has been determined that the proposed model has high classification success. With the proposed model, it is thought that user opinions can be analysed and software and applications can be developed according to user needs, especially for foreign language learning.
  • Küçük Resim Yok
    Öğe
    Estimating vulnerability metrics with word embedding and multiclass classification methods
    (Springer, 2024) Kekul, Hakan; Ergen, Burhan; Arslan, Halil
    Cyber security has an increasing importance since the day when information technologies are an invariable part of modern human life. One of the fundamental areas of cyber security is the concept of software security. Security vulnerabilities in software are one of the main reasons for the exploitation of information systems. For this reason, it has been systematically reported, analyzed and classified for a long time, with a protocol established between the states and the stakeholders of the issue at the level. All these processes are carried out manually by humans today. This situation causes errors and delays caused by human nature. Therefore, the current study aims to help the experts and increase the accuracy of the analysis results by speeding up the processes. To achieve this goal, a model is proposed that uses technical explanations of security reports written in natural language. Our model basically proposes a method that uses word embedding approaches and multi-class classification algorithms from natural language processing techniques. In order to compare the proposed model more accurately, the NVD database, which is open to everyone and accepted as a reference, was chosen. In addition, previous studies in the literature and the model we propose were compared. In order for the results of the compared models to be analyzed more accurately, our model was trained with the data sets of the studies it was compared and the results were presented clearly. The proposed method showed estimation success in the range of 87.34-96.25% for CVSS 2.0 metrics, and in the range of 84-90% for CVSS 3.1. This study, in which different word embedding and classification algorithms are used together, is one of the limited studies on the latest version of the official scoring system used for classification of software security vulnerabilities. Moreover, it is the most comprehensive and original study in its field due to the size of the dataset it uses and the number of databases evaluated.
  • Küçük Resim Yok
    Öğe
    The Effect of Document Length on Machine Learning Success in Text-Based Data
    (Institute of Electrical and Electronics Engineers Inc., 2023) Polatgil, Mesut; Kekul, Hakan
    Natural Language Processing (NLP) is an important research area for artificial intelligence studies. In the process of processing textual data, feature extraction and the creation of the word-document vector are very important. Especially for machine learning algorithms, these numerical vectors play a critical role in the creation of the model. Textual data must be preprocessed to generate these vectors. There are common methods such as removing stopwords, converting text to lowercase, and cleaning punctuation marks. The effects of these methods on the created model have also been investigated in the literature. However, it has not been investigated how the length values of the text can affect the model created. So how does a document or text having less than 10 or 20 characters affect the machine learning model? This study was carried out in order to solve this problem and fill the gap in the literature. The effect of text length on text classification models has been tested with different feature extraction methods. © 2023 IEEE.