28 September 2022 in Computational Intelligence and Neuroscience
Internet environments such as social networks, news sites, and blogs are the platforms where people can share their ideas and opinions. Many people share their comments instantly on the internet, which results in creating large volumes of entries. It is important for institutions and organizations to analyze this big data in an efficient and rapid manner to produce summary information about the feelings or opinions of individuals. In this study, we propose a scalable framework that makes sentiment classification by evaluating the compound probability scores of the most widely used methods in sentiment analysis through a fuzzy inference mechanism in an ensemble manner. The designed fuzzy inference system makes the sentiment estimation by evaluating the compound scores of valance aware dictionary, word embedding, and count vectorization processes. The difference of the proposed method from the classical ensemble methods is that it allows weighting of base learners and combines the strengths of each algorithm through fuzzy rules. The sentiment estimation process from text data can be managed either as a 2-class (positive and negative) or as a 3-class (positive, neutral, and negative) problem. We performed the experimental work on four available tagged social network data sets for both 2-class and 3-class classifications and observed that the proposed method provides improvements in accuracy.
22 April 2024 in Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi
As the amount of the available information continues to grow, finding the relevant information has become increasingly challenging. As a solution, text summarization has emerged as a vital method for extracting essential information from lengthy documents. There are various techniques available for filtering documents and extracting the pertinent information. In this study, a comparative analysis is conducted to evaluate traditional approaches and state-of-the-art methods on the BBC News and CNN/DailyMail datasets. This study offers valuable insights for researchers to advance their research and helps practitioners in selecting the most suitable techniques for their specific use cases.
31 October 2024 in Firat University Journal of Experimental and Computational Engineering
The smart grid is a crucial aspect of the modern energy landscape, providing a reliable, efficient, and sustainable way of meeting the growing energy demands. However, the vast amounts of data generated by smart grid technology necessitate the development of advanced data processing and analysis techniques. In this paper, we propose an attention-based time series workflow that combines dilated convolution and attention mechanisms for time series forecasting in smart grid applications. This workflow extracts temporal features from time series data using dilated convolutions and emphasizes significant temporal points in the hidden states using attention mechanisms. Experimental evaluations showed up to an 8% better performance for energy demand forecasting compared to commonly used deep learning-based methods. Our workflow achieved this gain by requiring 1/3 of the training time other models took. We also improved performance by 42% in various domains, demonstrating the adaptability of our approach across different areas. This study may assist researchers in constructing accurate forecasting models for smart grid environments. Furthermore, it highlights that the attention-based approach can be employed to promote sustainable energy and optimize smart grid environments.