Yazar "Bicer, Melisa" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Automatic Automata Grading System Using JFLAP
    (Institute of Electrical and Electronics Engineers Inc., 2023) Bicer, Melisa; Albayrak, Ferhat; Orhan, Umut
    This study focuses on the automatic grading of exams in the 'theory of computation' course using JFLAP, an open source system. In the study, the source codes of JFLAP are arranged and two interfaces are presented, one for the student and the other for the evaluator. Practical exams with JFLAP support cover three topics: Finite Automata (FA), Pushdown Automata (PDA), Turing Machines (TM). In the student interface, files are sent to a server as soon as responses are recorded using traditional JFLAP. The evaluator adds an answer key to the same folder as the student files on the server and clicks the auto-grading button in the evaluator interface. The student file cannot get points unless more than half of the balanced distributed accept and reject samples in the answer key are correct. This approach reduces the time and subjective interpretation costs associated with traditional assessments, especially in large classrooms. The system's performance analysis shows increased exam participation and classroom interaction without affecting ultimate success. It is expected that the success rates of students who make more preparations in future studies will increase. © 2023 IEEE.
  • [ X ]
    Öğe
    Enhancing Fake News Detection through Clustering with Convolutional Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2023) Bicer, Melisa; Ozel, Selma Ayse
    In this study, a deep learning-based clustering algorithm was applied for the detection of fake news. In the initial stage, true and fake news articles were collected from three different news websites using web scraping method. Subsequently, these collected news data were merged with two publicly available datasets. This resulted in the creation of a dataset encompassing approximately 130206 text samples of true and fake news, providing a wide range of topics. A Convolutional Neural Network (CNN) architecture based on Bidirectional Encoder Representations from Transformers (BERT) was developed to obtain the deep representations of the dataset. Then, clustering using the K-Means algorithm was performed on the deep features of the data to detect fake news. This study presented a higher accuracy rate while reducing the cost and computational process by utilizing fewer features. Additionally, this work contributes to the field as it introduces a new dataset and addresses the scarcity of studies on fake news detection using the deep learning-based clustering approach, thereby serving as a valuable resource for future research in this area. © 2023 IEEE.