Article
Chemistry, Analytical
Sergiu Cosmin Nistor, Mircea Moca, Darie Moldovan, Delia Beatrice Oprean, Razvan Liviu Nistor
Summary: This paper introduces a sentiment analysis solution on tweets using Recurrent Neural Networks, achieving an accuracy rate of 80.74% after experimenting with 20 design approaches. The solution integrates an attention mechanism and a two-way localization system, based on an in-depth literature review for Twitter sentiment analysis.
Article
Computer Science, Information Systems
Narisa Zhao, Huan Gao, Xin Wen, Hui Li
Summary: ABSA is a technique for identifying views and sentiment polarities towards a given aspect in reviews, which has become an important task in natural language understanding. The sentiment polarity of a sentence is significantly correlated with the targeted aspect.
Article
Computer Science, Information Systems
Asma Al Wazrah, Sarah Alhumoud
Summary: Over the past decade, the amount of Arabic content on websites and social media has increased significantly, allowing for rich sources for trend analysis through natural language processing tasks like sentiment analysis. Deep learning techniques, such as GRU and SBi-GRU, have been utilized to improve accuracy in analyzing unstructured data. Research has proposed neural models and ensemble methods for Arabic NLP, with the use of automatic sentiment refinement to discard stop words and achieve high accuracy in sentiment classification.
Article
Computer Science, Artificial Intelligence
Sarah Omar Alhumoud, Asma Ali Al Wazrah
Summary: The amount of Arabic content created on websites and social media has significantly increased in the past decade, leading to a rise in studies using recurrent neural networks (RNNs) for Arabic sentiment analysis. These studies vary in the areas they address, the functionality and weaknesses of the models, and the number and scale of available datasets.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Review
Computer Science, Artificial Intelligence
Minghui Huang, Haoran Xie, Yanghui Rao, Yuwei Liu, Leonard K. M. Poon, Fu Lee Wang
Summary: With the availability and popularity of sentiment-rich resources, new opportunities and challenges have emerged in sentiment analysis. Previous studies have either ignored contextual information of sentences or not considered sentiment information embedded in sentiment words. To address these limitations, we propose a new model, called Sentiment Convolutional Neural Network (SentiCNN), which combines contextual and sentiment information to analyze the sentiments of sentences.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Chemistry, Multidisciplinary
Yifei Zhang, Zhiqing Zhang, Shi Feng, Daling Wang
Summary: This study proposes a visual enhancement capsule network for multimodal sentiment analysis, which can better capture local aspect-based sentiment features and is more applicable for general multimodal user reviews.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Lifang Wu, Sinuo Deng, Heng Zhang, Ge Shi
Summary: Sentiment analysis is a challenging task due to the affective gap in accurately extracting sentimental features from visual contents. Previous approaches neglect the interaction among objects and may introduce noisy features. In this paper, a method called Sentiment Interaction Distillation (SID) Network is proposed to guide feature learning using object sentimental interaction. Experimental results show that the reasonable use of interaction features can improve the performance of sentiment analysis.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Tao Zhou, Jiuxin Cao, Xuelin Zhu, Bo Liu, Shancang Li
Summary: This article proposed a hierarchical cross-modality interaction model for visual-textual sentiment analysis, emphasizing consistency and correlation across modalities and addressing noise and joint understanding issues. Through experiments, the framework outperformed existing methods, with phrase-level text fragments playing an important role in joint visual-textual sentiment analysis.
IEEE SYSTEMS JOURNAL
(2021)
Article
Environmental Sciences
Yunqi Jiang, Wenjuan Shen, Huaqing Zhang, Kai Zhang, Jian Wang, Liming Zhang
Summary: In this study, an interpretable recurrent neural network (IRNN) based on the material balance equation is proposed to characterize flow disequilibrium and predict production behaviors. IRNN consists of two interpretable modules: the inflow module computes the total inflow rate from injectors to producers, and the drainage module approximates the fluid change rate among water drainage volumes. IRNN uses a self-attention mechanism to handle the interference between injection-production groups on the spatial scale, and employs a recurrent neural network to incorporate the impact of historical injection signals on current production behavior on the temporal scale. Through verification experiments, IRNN outperforms traditional multilayer perceptron models in history matching and productivity forecasting, while effectively reflecting subsurface flow disequilibrium between injectors and producers.
Article
Computer Science, Information Systems
Guangquan Lu, Jiecheng Li, Jian Wei
Summary: Aspect-based sentiment analysis is a practical methodology for various fields. This paper proposes a method called heterogeneous graph neural networks (Hete_GNNs) to address the challenge of multiple aspect sentiment representation in sentences. Experimental results demonstrate the effectiveness of the proposed method in sentiment classification tasks.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Guangquan Lu, Jiecheng Li, Jian Wei
Summary: This paper discusses the practicality of aspect-based sentiment analysis technologies in various fields, and proposes a new method - heterogeneous graph neural networks (Hete_GNNs), to improve aspect sentiment classification results by encoding sentence syntax tree, words relations, and opinion dictionary information.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Mathematics, Interdisciplinary Applications
Huu-Thanh Duong, Tram-Anh Nguyen-Thi, Vinh Truong Hoang
Summary: This paper presents an approach for sentiment analysis under limited training data, achieving high-performance predictive models through data preprocessing and text augmentation techniques. The results show that data augmentation techniques enhance model accuracy.
Article
Computer Science, Information Systems
Ramalingaswamy Cheruku, Khaja Hussain, Ilaiah Kavati, A. Mallikarjuna Reddy, K. Sudheer Reddy
Summary: The paper proposes an improved model for sentiment analysis on social media platforms, specifically Twitter, using a modified RoBERTa model combined with RNN. The proposed model achieves higher accuracy, precision, recall, and F1-score compared to existing state-of-the-art models. Experimental results demonstrate significant improvements in performance. The proposed approach has a maximum accuracy of 84.6% and outperforms other models in terms of various evaluation measures.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Spyridon Kardakis, Isidoros Perikos, Foteini Grivokostopoulou, Ioannis Hatzilygeroudis
Summary: Attention-based methods have gained increased interest in recent years as they can enhance neural network performance in various tasks. This study focuses on attention-based models in sentiment analysis, comparing them with baseline models in text sentiment classification tasks and showing up to a 3.5% improvement in accuracy.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Zhong Zheng, Zijun Zhang
Summary: This paper proposes a temporal convolutional recurrent autoencoder framework for more effective time series compression. Experimental results show that the proposed method outperforms benchmarking models in terms of lower reconstruction errors with the same compression ratio, indicating its promising potential for various applications involving long time series data.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Interdisciplinary Applications
Aytug Onan
Summary: The study evaluated the predictive performance of conventional supervised learning methods, ensemble learning methods, and deep learning methods, as well as the efficiency of text representation and word-embedding schemes in sentiment analysis on MOOC evaluations. Analysis of a corpus containing 66,000 MOOC reviews indicated that deep learning-based architectures outperformed other methods for sentiment analysis on educational data mining. The highest predictive performance was achieved by long short-term memory networks combined with GloVe word-embedding scheme-based representation, with a classification accuracy of 95.80%.
COMPUTER APPLICATIONS IN ENGINEERING EDUCATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Aytug Onan, Mansur Alp Tocoglu
Summary: The study aims to use weighted word embeddings and clustering techniques to cluster MOOC discussion forum posts and identify question topics. By evaluating four word-embedding schemes, four weighting functions, and four clustering algorithms, it is found that weighted word-embedding schemes combined with clustering algorithms outperform conventional schemes.
COMPUTER APPLICATIONS IN ENGINEERING EDUCATION
(2021)
Article
Computer Science, Software Engineering
Aytug Onan
Summary: A deep learning architecture combining TF-IDF-weighted Glove word embedding with CNN-LSTM architecture outperforms conventional deep learning methods in sentiment analysis of product reviews from Twitter.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Engineering, Multidisciplinary
Hasan Bulut, Aytug Onan, Serdar Korukoglu
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2020)
Article
Computer Science, Artificial Intelligence
Gul Cihan Habek, Mansur Alp Tocoglu, Aytug Onan
Summary: With the growth of the cryptocurrency trading market, sentiment analysis of cryptocurrency comments has become crucial. A novel deep neural network architecture was introduced for sentiment classification, showing an accuracy of 93.77% in experimental results.
APPLIED ARTIFICIAL INTELLIGENCE
(2022)
Article
Engineering, Electrical & Electronic
Mahmut Agrali, Volkan Kilic, Aytug Onan, Esra Meltem Koc, Ali Murat Koc, Rasit Eren Buyuktoka, Turker Acar, Zehra Adibelli
Summary: The conventional approach for identifying GGO in medical imaging is CNN, which shows promising performance in COVID-19 detection. However, CNN has limitations in capturing the structured relationships of GGO. This paper proposes a novel framework called DeepChestNet that leverages structured relationships by performing segmentation and classification on lung, pulmonary lobe, and GGO, leading to enhanced detection and diagnosis of COVID-19.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Aytug Onan
Summary: We propose a novel hierarchical graph-based text classification framework that leverages contextual node embedding and BERT-based dynamic fusion to capture complex relationships between nodes in the hierarchy. The framework consists of seven stages: Linguistic Feature Extraction, Hierarchical Node Construction, Contextual Node Embedding, Multi-Level Graph Learning, Dynamic Text Sequential Feature Interaction, Attention-Based Graph Learning, and Dynamic Fusion with BERT. Experimental results on benchmark datasets demonstrate significant improvements in classification accuracy compared to state-of-the-art methods.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Aytug Onan
Summary: The process of creating high-quality labeled data is crucial but time-consuming. This paper proposes a text augmentation framework called SRL-ACO that leverages Semantic Role Labeling and Ant Colony Optimization techniques to enhance the accuracy of natural language processing models without requiring manual data annotation.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Proceedings Paper
Acoustics
Ozge Taylan Moral, Volkan Kilic, Aytug Onan, Wenwu Wang
Summary: Describing the semantic content of an image through natural language has attracted significant interest in computer vision and language processing. Existing image captioning approaches have limitations in generating accurate captions due to their inability to effectively use visual information. This paper proposes an improved method using multi-layer GRU to enhance the semantic coherence of captions, and experimental results demonstrate its superiority.
2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022)
(2022)
Proceedings Paper
Acoustics
Ozkan Cayli, Volkan Kilic, Aytug Onan, Wenwu Wang
Summary: Image captioning is the task of generating descriptive captions for visual content using natural language automatically. Recent advancements in deep neural networks have improved the generation of natural and semantic text in image captioning. However, maintaining gradient flow between neurons in consecutive layers becomes challenging with deeper networks. In this paper, the authors propose integrating an auxiliary classifier into the residual recurrent neural network to enhance caption generation by enabling gradient flow to reach bottom layers. Experiments on MSCOCO and VizWiz datasets demonstrate the superiority of the proposed approach over state-of-the-art methods in multiple performance metrics.
2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022)
(2022)
Proceedings Paper
Cell & Tissue Engineering
Duygu Degirmenci, Mehmet Akif Ozdemir, Onan Guren, Aytug Onan
Summary: This study aims to improve classification performance of EEG signals for MI tasks by extracting discriminative features with NMF from TFD obtained by WSST, achieving outstanding accuracy, kappa, and F1 score with various classifiers. WSST provides energy distributions with highly localization capability in TFD, offering a promising approach for MI task classification.
2022 MEDICAL TECHNOLOGIES CONGRESS (TIPTEKNO'22)
(2022)
Proceedings Paper
Engineering, Electrical & Electronic
Rumeysa Keskin, Ozge Taylan Moral, Volkan Kilic, Aytug Onan
Summary: The study introduces an automatic image captioning system for smartphones, utilizing advanced visual information and decoder structure to generate more meaningful image descriptions. The system performs well on the MSCOCO dataset and is integrated into a custom Android application, IMECA, for offline caption generation.
29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021)
(2021)
Article
Computer Science, Information Systems
Aytug Onan, Mansur A. L. P. Tocoglu
Summary: This research aims to present an effective sarcasm identification framework on social media data by utilizing neural language models and deep neural networks. The model includes a three-layer stacked bidirectional long short-term memory architecture and introduces an inverse gravity moment based term weighted word embedding model to preserve word-ordering information. The presented model achieves promising results with a classification accuracy of 95.30% for the sarcasm identification task.
Article
Computer Science, Artificial Intelligence
Aytug Onan, Mansur Alp Tocoglu
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
(2020)