Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
9 results
Search Results
Conference Object A Data-Driven Framework for Predicting Flight Arrival Delays Using Integrated Aviation and Meteorological Data(Institute of Electrical and Electronics Engineers Inc., 2025-09-17) Akyuz, Muhammed Sefa; Bakal, GokhanConference Object Citation - Scopus: 1Words Speak Louder Than Actions: Decoding Emotions Through NLP(Institute of Electrical and Electronics Engineers Inc., 2024-10-26) Paksoy, Melda; Bakal, GokhanEmotion detection in text remains a significant challenge in Natural Language Processing due to human emotions' complexity and subtle nuances. This paper presents multiple experimental models for emotion classification using an up-to-date dataset curated to address 13 emotions implied in Twitter posts. We evaluated various machine learning (ML) models, including Logistic Regression, Random Forest, SVM, and XGBoost, alongside deep learning (DL) architectures such as LSTM and CNN. Our results demonstrate the efficacy of deep learning models, particularly the CNN model by achieving an impressive F1 score of 0.99. This study contributes to emotion detection capabilities, paving the way for more nuanced and accurate sentiment analysis (SA) in various text analysis applications. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 8On Comparative Classification of Relevant COVID-19 Tweets(Institute of Electrical and Electronics Engineers Inc., 2021-09-15) Bakal, Gokhan; Abar, OrhanDue to the impressive information dissemination power of social networks such as Twitter, people tend to check social networks and Web pages more than other traditional news sources, including newspapers, TV news programs, or radio channels. In that sense, the information carried by the content of the shared social media posts becomes much more considerable. However, most of the posts are commonly either irrelevant or inaccurate. Besides, the more critical case than the correctness of the information is the diffusion speed on Twitter through the reply or retweet actions. These activities make the initial situation even more complicated than itself due to the unregulated nature of the social networks and the lack of an immediate verification mechanism for the correctness of the posts. When we consider the current Covid-19 pandemic period (causing the coronavirus disease), one of the most utilized information resources is Twitter except the official health administration institutions. Thereupon, examining the correctness of the information related to the Covid-19 pandemic by computational techniques (e.g., Data Mining, Machine Learning, and Deep Learning) has been gaining popularity and remains a substantial task. Hence, we mainly focused on analyzing the correctness of the posts related to the current pandemic shared on the Twitter platform. Therefore, the overall goal of this work is to classify the relevant tweets using linear and non-linear machine learning models. We achieved the best F1 performance score (99%) with the neural network model using the unigram features & threshold value of 50 among all model configurations. © 2022 Elsevier B.V., All rights reserved.Conference Object Multi-Method Text Summarization: Evaluating Extractive and BART-Based Approaches on CNN/Daily Mail(Institute of Electrical and Electronics Engineers Inc., 2025-06-27) Inal, Yasin; Bakal, Gokhan; Esit, MuhammedWith the exponential growth of digital content, efficient text summarization has become increasingly crucial for managing information overload. This paper presents a comprehensive approach to text summarization using both extractive and abstractive methods, implemented on the CNN/Daily Mail dataset. We leverage pre-trained BART (Bidirectional and AutoRegressive Transformers) models and fine-tuning techniques to generate high-quality summaries. Our approach demonstrates significant improvements, with our best model trained on 287 k samples achieving ROUGE-1 F1 scores of 0.4174, ROUGE-2 F1 scores of 0.1932, and ROUGE-L F1 scores of 0.2910. We provide detailed comparisons between extractive methods and various BART model configurations, analyzing the impact of training dataset size and model architecture on summarization quality. Additionally, we share our implementation through an opensource NLP toolkit to facilitate further research and practical applications in the field. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 1Improving Salary Offer Processes With Classification Based Machine Learning Models(Institute of Electrical and Electronics Engineers Inc., 2024-09-21) Kaya, Rukiye; Saatci, Mehtap; Bakal, Gokhan; Bakal, Mehmet GokhanIn job applications, salary is major motivational factor for employees and making accurate salary prediction is crucial for both employers and employees. Utilizing advanced technologies can significantly enhance the accuracy and efficiency of salary prediction process. In this study, we explore Machine Learning (ML) methods to enhance salary prediction process. We evaluated seven classification models for predicting salary categories, with the Artificial Neural Network (ANN) model achieving the highest accuracy at 58.2% on the test dataset, followed by the K-Nearest Neighbors (KNN) model with an accuracy of 56.8%. Additionally, we employed ensemble models to further enhance prediction accuracy. Among these, the Majority Voting Classifier using Hard Voting achieved the highest accuracy at 59.3%, demonstrating the potential of ensemble techniques in refining salary predictions. The developed salary prediction tool estimates the most appropriate salary category for each candidate and help mitigate potential biases in manual salary assessments, hence enables a more objective and consistent compensation system. ∗CRITICAL: Do Not Use Symbols, Special Characters, or Math in Paper Title or Abstract, and do not cite other papers in the abstract. © 2024 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 1From Traditional to Deep: Evaluating Sentiment Analysis Models on a Large-Scale Tweet Dataset(Institute of Electrical and Electronics Engineers Inc., 2024-10-26) Mammadov, Alisahib; Bakal, GokhanThis study investigates the effectiveness of various machine learning (ML) and deep learning (DL) techniques for large-scale sentiment analysis on Twitter data. We leverage a publicly available dataset of one million tweets, annotated with four sentiment labels (positive, negative, uncertainty, and liti-gious), to train and evaluate a range of models. Our experiments demonstrate that traditional ML algorithms, particularly XG-Boost, achieve high performance, with the best F1 score reaching 95.81% using a combination of unigrams and bigrams. Among DL models, a hybrid CNN-BiGRU architecture yields the highest average F1 score of 95.42%. Our findings highlight the strengths of different approaches for sentiment analysis on Twitter data and emphasize the importance of data preprocessing and model selection for achieving optimal performance. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 4A Transfer Learning Application on the Reliability of Psychological Drugs' Comments(Institute of Electrical and Electronics Engineers Inc., 2023-07-25) Sen, Tarik Uveys; Bakal, GokhanAs digitalization and the Internet stay emerging concepts by gaining popularity, the accuracy of personal reviews/opinions will be a critical issue. This circumstance also particularly applies to patients taking psychological drugs, where accurate information is crucial for other patients and medical professionals. In this study, we analyze drug reviews from drugs.com to determine the effectiveness of reviews for psychological drugs. Our dataset includes over 200,000 drug reviews, which we labeled as positive, negative, or neutral according to their rating scores. We apply machine learning (ML) models, including Logistic Regression, Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) algorithms, to predict the sentiment class of each review. Our results demonstrate an F1-Weighted score of 85.3% for the LSTM model. However, by applying the transfer learning technique, we further improved the F1 score (nearly 3% increase) obtained by the LSTM model. Our findings proved that there is no contextual difference between the comments made by the patients suffering from psychological or other diseases. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 3A Computational Drug Repositioning Effort Using Patients' Reviews Dataset(Institute of Electrical and Electronics Engineers Inc., 2023-07-25) Akkaya, Ali; Bakal, GokhanThe drug discovery process is one of the core motivations in both medical and, specifically, pharmaceutical disciplines. Due to the nature of the process, it requires an excessive amount of time, clinical experiments, and budget to cover each discovery phase. In this sense, computational drug discovery efforts can shorten the discovery process by providing plausible candidates since many of the attempts fail for several reasons, such as a lack of participants, financial problems, or ineffective results. In this study, the goal is to identify plausible candidate drugs for diseases. To do that, we utilize a personal experience of drugs dataset generated by patients. Beyond the user-generated comments, the users also give a rate between 1 and 10. Since we want to ensure the dataset quality, we first performed sentiment analysis experiments to prove that the reviews/comments are consistent with the given rating score. Then, only the review pairs having an effectiveness rate of 6 or more are selected as pre-filtered drug-disease pairs. We also build a knowledge graph using treatment-related biomedical relations using predications from Semantic Medline Database to identify drug similarities utilizing the Simrank similarity algorithm. As a result, we reported a list of plausible drugs as repurposing/repositioning candidates for further experiments. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 7A Comparative Analysis on Medical Article Classification Using Text Mining & Machine Learning Algorithms(Institute of Electrical and Electronics Engineers Inc., 2021-09-15) Kolukisa, Burak; Dedeturk, Bilge Kagan; Dedeturk, Beyhan Adanur; Gulsen, Abdulkadir; Bakal, Gokhan; Guisen, AbdulkadirThe document classification task is one of the widely studied research fields on multiple domains. The core motivation of the classification task is that the manual classification efforts are impractical due to the exponentially growing document volumes. Thus, we densely need to exploit automated computational approaches, such as machine learning models along with data & text mining techniques. In this study, we concentrated on the classification of medical articles specifically on common cancer types, due to the significance of the field and the decent number of available documents of interest. We deliberately targeted MEDLINE articles about common cancer types because most cancer types share a similar literature composition. Therefore, this situation makes the classification effort relatively more complicated. To this end, we built multiple machine learning models, including both traditional and deep learning architectures. We achieved the best performance (R¿82% F score) by the LSTM model. Overall, our results demonstrate a strong effect of exploiting both text mining and machine learning methods to distinguish medical articles on common cancer types. © 2022 Elsevier B.V., All rights reserved.