Hybrid Deep Learning Model Research Articles

Ensemble based high performance deep learning models for fake news detection

Social media has emerged as a dominant platform where individuals freely share opinions and communicate globally. Its role in disseminating news worldwide is significant due to its easy accessibility. However, the increase in the use of these platforms presents severe risks for potentially misleading people. Our research aims to investigate different techniques within machine learning, deep learning, and ensemble learning frameworks in Arabic fake news detection. We integrated FastText word embeddings with various machine learning and deep learning methods. We then leveraged advanced transformer-based models, including BERT, XLNet, and RoBERTa, optimizing their performance through careful hyperparameter tuning. The research methodology involves utilizing two Arabic news article datasets, AFND and ARABICFAKETWEETS datasets, categorized into fake and real subsets and applying comprehensive preprocessing techniques to the text data. Four hybrid deep learning models are presented: CNN-LSTM, RNN-CNN, RNN-LSTM, and Bi-GRU-Bi-LSTM. The Bi-GRU-Bi-LSTM model demonstrated superior performance regarding the F1 score, accuracy, and loss metrics. The precision, recall, F1 score, and accuracy of the hybrid Bi-GRU-Bi-LSTM model on the AFND Dataset are 0.97, 0.97, 0.98, and 0.98, and on the ARABICFAKETWEETS dataset are 0.98, 0.98, 0.99, and 0.99 respectively. The study’s primary conclusion is that when spotting fake news in Arabic, the Bi-GRU-Bi-LSTM model outperforms other models by a significant margin. It significantly aids the global fight against false information by setting the stage for future research to expand fake news detection to multiple languages.

DeepLPos: a comprehensive hybrid deep learning model for lying position recognition using a tactile sensor array system

Abstract Unpredictable limb movements or turning motions can significantly disrupt the accurate extraction of physiological signals, such as respiratory and heart rates. In clinical environments, reliable detection of lying positions is crucial for continuous patient monitoring, particularly during sleep. In this paper, a smart sleeping position recognition system is proposed, which employs a tactile pressure sensor array based on the unique structure of ‘the electrostatic double-layer capacitors’. The sensor array, comprising 64 rows and 32 columns (2048 nodes), captures four types of healthy lying positions using an 8-bit AD module. Despite challenges arising from limited experimental samples for accurate training, we propose DeepLPos, a hybrid deep learning approach combining generative adversarial networks and the you only look once network. To tackle the differentiation challenge between supine and prone positions, we introduce an SPD Conv attention module to enhance the resolution of detailed descriptions in pressure images. The model is further pruned to optimize both structure and parameters, enabling efficient real-time detection. Evaluated on the SLP dataset, the proposed system achieves an accuracy of 97.5% with a real-time processing speed of 0.069 s per frame, demonstrating its potential for practical, high-precision measurement and monitoring applications in healthcare.

Enhancing IoT cyber attacks intrusion detection through GAN-based data augmentation and hybrid deep learning models for MQTT network protocol cyber attacks

Enhancing IoT cyber attacks intrusion detection through GAN-based data augmentation and hybrid deep learning models for MQTT network protocol cyber attacks

Detection of Android Malware Using Word2Vec and Deep Learning

To fortify Android devices against evolving threats, the project unfolds with a commitment to contribute to security endeavors significantly. The core purpose is to leverage machine-learning techniques, particularly deep-learning architectures, to construct robust mechanisms for identifying and classifying Android malware. A hybrid deep learning model combining Long Short-Term Memory (LSTM) networks with Convolutional Neural Networks (CNN) is employed to classify the applications as benign or malicious. The LSTM-CNN model is designed to effectively capture both temporal dependencies and spatial patterns within the feature vectors. Additionally, a Random Forest classifier is used to identify the most important features for classification, improving the performance and efficiency of the deep learning model. The proposed approach is evaluated on the CICMalDroid2020 dataset, demonstrating its ability to detect and classify Android malware accurately. This highlights the effectiveness of static feature analysis combined with advanced deep learning architectures for enhancing Android malware detection systems.

A hybrid BiLSTM-CNN deep learning model for Chinese sentiment analysis of online car reviews

Although sentiment analysis with datasets in English has achieved significant progress, there are still relatively few studies on sentiment analysis in the area of Chinesecar review texts. In addition, the existing Chinese text sentiment analysis methods cannot simultaneously extract the contextual features and the local semantic information from the review texts. To address the above issues, a hybrid deep learning model namely BiLSTM-CNN was designed and validated with Chinese car review texts. We trained word vectors with the CBOW model by combining the Chinese Wikipedia corpus with other open-source car-related corpora. Such word vectors include car-specific vocabulary, which improves sentimental classification accuracy. Experimental results show that the performance indices of the deep learning models (CNN, LSTM, BiLSTM) are much better than the KNN, SVM, Naïve Bayes, and RF model, which is attributed to deep learning's powerful feature extraction ability and nonlinear fitting ability. Furthermore, when compared to deep learning models such as CNN, LSTM, BiLSTM, and LSTM-CNN, the suggested hybrid BiLSTM-CNN model outperformed the others. The results may provide references for consumers to buy a car and for car companies to optimize their products.

Deep transfer learning with improved crayfish optimization algorithm for oral squamous cell carcinoma cancer recognition using histopathological images

Oral Squamous Cell Carcinoma (OSCC) causes a severe challenge in oncology due to the lack of diagnostic devices, leading to delays in detecting the disorder. The OSCC diagnosis through histopathology demands a pathologist expert because the cellular presentation is variable and highly complex. Existing diagnostic approaches for OSCC have specific efficiency and accuracy restrictions, highlighting the necessity for more reliable techniques. The increase of deep neural networks (DNN) model and their applications in medical imaging have been instrumental in disease diagnosis and detection. Automatic detection systems using deep learning (DL) approaches show tremendous promise in investigating medical imagery with speed, efficiency, and accuracy. In terms of OSCC, this system allows the diagnostic method to be streamlined, facilitating earlier diagnosis and enhancing survival rates. Automatic analysis of histopathological image (HI) can assist in accurately detecting and identifying tumorous tissue, reducing diagnostic turnaround times and increasing the efficacy of pathologists. This study presents a Squeeze-Excitation with Hybrid Deep Learning for Oral Squamous Cell Carcinoma Recognition (SEHDL-OSCCR) on HIs. The presented SEHDL-OSCCR technique mainly focuses on detecting oral cancer (OC) using hybrid DL models. The bilateral filtering (BF) technique is initially used to remove the noise. Next, the SEHDL-OSCCR technique employs the SE-CapsNet model to recognize the feature extractors. An improved crayfish optimization algorithm (ICOA) technique is utilized to improve the performance of the SE-CapsNet model. At last, the classification of the OSCC technique is performed by employing a convolutional neural network with a bidirectional long short-term memory (CNN-BiLSTM) model. The simulation results obtained using the SEHDL-OSCCR technique are investigated using a benchmark medical image dataset. The experimental validation of the SEHDL-OSCCR technique illustrated a greater accuracy outcome of 98.75% compared to recent approaches.

Hybrid deep models for parallel feature extraction and enhanced emotion state classification

Emotions play a vital role in recognizing a person’s thoughts and vary significantly with stress levels. Emotion and stress classification have gained considerable attention in robotics and artificial intelligence applications. While numerous methods based on machine learning techniques provide average classification performance, recent deep learning approaches offer enhanced results. This research presents a hybrid deep learning model that extracts features using AlexNet and DenseNet models, followed by feature fusion and dimensionality reduction via Principal Component Analysis (PCA). The reduced features are then classified using a multi-class Support Vector Machine (SVM) to categorize different types of emotions. The proposed model was evaluated using the DEAP and EEG Brainwave datasets, both well-suited for emotion analysis due to their comprehensive EEG signal recordings and diverse emotional stimuli. The DEAP dataset includes EEG signals from 32 participants who watched 40 one-minute music videos, while the EEG Brainwave dataset categorizes emotions into positive, negative, and neutral based on EEG recordings from participants exposed to six different film clips. The proposed model achieved an accuracy of 95.54% and 97.26% for valence and arousal categories in the DEAP dataset, respectively, and 98.42% for the EEG Brainwave dataset. These results significantly outperform existing methods, demonstrating the model’s superior performance in terms of precision, recall, F1-score, specificity, and Mathew correlation coefficient. The integration of AlexNet and DenseNet, combined with PCA and multi-class SVM, makes this approach particularly effective for capturing the intricate patterns in EEG data, highlighting its potential for applications in human-computer interaction and mental health monitoring, marking a significant advancement over traditional methods.

A hybrid transformer and attention based recurrent neural network for robust and interpretable sentiment analysis of tweets

Sentiment analysis is a pivotal tool in understanding public opinion, consumer behavior, and social trends, underpinning applications ranging from market research to political analysis. However, existing sentiment analysis models frequently encounter challenges related to linguistic diversity, model generalizability, explainability, and limited availability of labeled datasets. To address these shortcomings, we propose the Transformer and Attention-based Bidirectional LSTM for Sentiment Analysis (TRABSA) model, a novel hybrid sentiment analysis framework that integrates transformer-based architecture, attention mechanism, and recurrent neural networks like BiLSTM. The TRABSA model leverages the powerful RoBERTa-based transformer model for initial feature extraction, capturing complex linguistic nuances from a vast corpus of tweets. This is followed by an attention mechanism that highlights the most informative parts of the text, enhancing the model’s focus on critical sentiment-bearing elements. Finally, the BiLSTM networks process these refined features, capturing temporal dependencies and improving the overall sentiment classification into positive, neutral, and negative classes. Leveraging the latest RoBERTa-based transformer model trained on a vast corpus of 124M tweets, our research bridges existing gaps in sentiment analysis benchmarks, ensuring state-of-the-art accuracy and relevance. Furthermore, we contribute to data diversity by augmenting existing datasets with 411,885 tweets from 32 English-speaking countries and 7,500 tweets from various US states. This study also compares six word-embedding techniques, identifying the most robust preprocessing and embedding methodologies crucial for accurate sentiment analysis and model performance. We meticulously label tweets into positive, neutral, and negative classes using three distinct lexicon-based approaches and select the best one, ensuring optimal sentiment analysis outcomes and model efficacy. Here, we demonstrate that the TRABSA model outperforms the current seven traditional machine learning models, four stacking models, and four hybrid deep learning models, yielding notable gain in accuracy (94%) and effectiveness with a macro average precision of 94%, recall of 93%, and F1-score of 94%. Our further evaluation involves two extended and four external datasets, demonstrating the model’s consistent superiority, robustness, and generalizability across diverse contexts and datasets. Finally, by conducting a thorough study with SHAP and LIME explainable visualization approaches, we offer insights into the interpretability of the TRABSA model, improving comprehension and confidence in the model’s predictions. Our study results make it easier to analyze how citizens respond to resources and events during pandemics since they are integrated into a decision-support system. Applications of this system provide essential assistance for efficient pandemic management, such as resource planning, crowd control, policy formation, vaccination tactics, and quick reaction programs.

CDO-TCN-BiGRU: An Optimized Hybrid Deep Learning Model for Shared Bicycles Demand Forecasting

<div>Accurate prediction of the demand for shared bicycles is not only conducive to the operation of relevant enterprises, but also conducive to improving the image of the city, facilitating people’s travel, and solving the balance between supply and demand of bicycles in the region. To precisely predict the demand of shared bicycles, a model combining temporal convolution network (TCN) and bidirectional gating recurrent unit (BiGRU) model is proposed, and the Chernobyl disaster optimizer (CDO) is used to optimize its hyperparameters. It has the ability of TCN to extract sequence features and gated recurrent unit (GRU) to mine time series data and combine the characteristics of CDO with fast convergence and high global search ability, so as to reduce the influence of model hyperparameters. This article selects the shared bicycles travel data in Washington, analyzes its multi-characteristics, and trains it as the input characteristics of the model. In the experiments, we performed comparison study and ablation study. The results show that the prediction error of the proposed model is less than other comparative models. Therefore, CDO-TCN-BiGRU model has the characteristics of high prediction precision and good stability.</div>

Interpretable multi-step hybrid deep learning model for karst spring discharge prediction: Integrating temporal fusion transformers with ensemble empirical mode decomposition

Karst groundwater is a critical freshwater resource for numerous regions worldwide. Monitoring and predicting karst spring discharge is essential for effective groundwater management and the preservation of karst ecosystems. However, the high heterogeneity and karstification pose significant challenges to physics-based models in providing robust predictions of karst spring discharge. In this study, an interpretable multi-step hybrid deep learning model called selective EEMD-TFT is proposed, which adaptively integrates temporal fusion transformers (TFT) with ensemble empirical mode decomposition (EEMD) for predicting karst spring discharge. The selective EEMD-TFT hybrid model leverages the strengths of both EEMD and TFT techniques to learn inherent patterns and temporal dynamics from nonlinear and nonstationary signals, eliminate redundant components, and emphasize useful characteristics of input variables, leading to the improvement of prediction performance and efficiency. It consists of two stages: in the first stage, the daily precipitation data is decomposed into multiple intrinsic mode functions using EEMD to extract valuable information from nonlinear and nonstationary signals. All decomposed components, temperature and categorical date features are then fed into the TFT model, which is an attention-based deep learning model that combines high-performance multi-horizon prediction and interpretable insights into temporal dynamics. The importance of input variables will be quantified and ranked. In the second stage, the decomposed precipitation components with high importance are selected to serve as the TFT model’s input features along with temperature and categorical date variables for the final prediction. Results indicate that the selective EEMD-TFT model outperforms other sequence-to-sequence deep learning models, such as LSTM and single TFT models, delivering reliable and robust prediction performance. Notably, it maintains more consistent prediction performance at longer forecast horizons compared to other sequence-to-sequence models, highlighting its capacity to learn complex patterns from the input data and efficiently extract valuable information for karst spring prediction. An interpretable analysis of the selective EEMD-TFT model is conducted to gain insights into relationships among various hydrological processes and analyze temporal patterns.

A hybrid deep learning network for automatic diagnosis of cardiac arrhythmia based on 12-lead ECG

Cardiac arrhythmias are the leading cause of death and pose a huge health and economic burden globally. Electrocardiography (ECG) is an effective technique for the diagnosis of cardiovascular diseases because of its noninvasive and cost-effective advantages. However, traditional ECG analysis relies heavily on the clinical experience of physicians, which can be challenging and time-consuming to produce valid diagnostic results. This work proposes a new hybrid deep learning model that combines convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) with multi-head attention (CBGM model). Specifically, the model consists of seven convolutional layers with varying filter sizes (4, 16, 32, and 64) and three pooling layers, respectively, while the BiGRU module includes two layers with 64 units each followed by multi-head attention (8-heads). The combination of CNN and BiGRU effectively captures spatio-temporal features of ECG signals, with multi-head attention comprehensively extracted global correlations among multiple segments of ECG signals. The validation in the MIT-BIH arrhythmia database achieved an accuracy of 99.41%, a precision of 99.15%, a specificity of 99.68%, and an F1-Score of 99.21%, indicating its robust performance across different evaluation metrics. Additionally, the model’s performance was evaluated on the PTB Diagnostic ECG Database, where it achieved an accuracy of 98.82%, demonstrating its generalization capability. Comparative analysis against previous methods revealed that our proposed CBGM model exhibits more higher performance in automatic classification of arrhythmia and can be helpful for assisting clinicians by enabling real-time detection of cardiac arrhythmias during routine ECG screenings.

Hybrid Deep Learning Model for Vegetable Price Forecasting Based on Principal Component Analysis and Attention Mechanism

Abstract With the aim of enhancing the accuracy of current models for forecasting vegetable prices and improving market structures, this study focuses on the prices of bell peppers at the Nanhuanqiao Market in Suzhou. In this paper, we propose a hybrid Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) model for vegetable price forecasting based on Principal Component Analysis (PCA) and Attention Mechanism (ATT). Initially, we utilized the Pearson correlation coefficient to filter out the factors impacting prices. Then, we applied PCA to reduce dimensionality, extracting key price features. Next, we captured local sequence patterns with CNN, while handling time-series features with GRU. Finally, these outputs were integrated via ATT to generate the final prediction. Our results indicate that the hybrid CNN-GRU model, enhanced by PCA and ATT, achieved a Root Mean Square Error (RMSE) as low as 0.16. This performance is 11.11%, 11.11%, and 15.79% better than that of the PCA-CNN, PCA-GRU, and CNN-GRU-ATT models, respectively. Furthermore, in order to prove the effectiveness of our proposed model, the proposed model is compared with the state-of-the-art models and classical machine learning algorithms under the same dataset, the results indicate that our proposed hybrid deep learning model based on PCA and ATT shows the best performance. Consequently, our model offers a valuable reference for vegetable price prediction.

A study on hyperspectral soil total nitrogen inversion using a hybrid deep learning model CBiResNet-BiLSTM

Rapid, accurate and non-destructive acquisition of soil total nitrogen (TN) content in the black soil zone is significant for achieving precise fertilization. In this study, the soil types of corn and soybean fields in Jilin Agricultural University, China, were selected as the study area. A total of 162 soil samples were collected using a five-point mixed sampling method. Then, spectral data were obtained and the noisy edge were initially eliminated. Subsequently, the denoised spectral data underwent smoothing by using the Savitzky–Golay (SG) method. After performing the first-order difference (FD) and second-order difference (SD) transformations on the data, it was input to the model. In this study, a hybrid deep learning model, CBiResNet-BiLSTM, was designed for precise prediction of soil TN content. This model was optimized based on ResNet34, and its capabilities were enhanced by incorporating CBAM in the residual module to facilitate additional eigenvalue extraction. Also, Bidirectional Long Short-Term Memory (BiLSTM) was integrated to enhance model accuracy. Besides, partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and back propagation neural network (BP), as well as ResNet(18, 34, 50, 101, 152) models were taken for comparative experiments. The results indicated that the traditional machine learning model PLSR achieved good performance, with R2 of 0.883, and the hybrid deep learning model CBiResNet-BiLSTM had the best inversion capability with R2 of 0.937, with the R2 being improved by 5.4%, compared with the PLSR model. On this basis, we present the LUCAS dataset to demonstrate the generalisability of the model. Therefore, the CBiResNet-BiLSTM model is a fast and feasible hyperspectral estimation method for soil TN content.Graphical abstract

An Efficient Deep Learning Mechanism for Predicting Fake News/Reviews in Twitter Data

Recently, social media platforms have been widely utilized as information sources due to their effortless accessibility and reduced costs. However, online platforms like Instagram, Twitter and Facebook get influenced by their users via fake news/reviews. The main intention of spreading fake news is to mislead other network users, which highly affects businesses, political parties, etc. Thus, an effective methodology is needed to predict fake news from social media automatically. The major objective of this proposed study is to identify and classify the given Twitter input data as real or fake through deep learning mechanisms. The proposed study involves four stages: pre-processing, embedded word analysis, feature extraction, and fake news/reviews prediction. Initially, pre-processing is performed to enhance the quality of data with the help of tokenization, stemming and stop word removal. Embedded word analysis is done using Advanced Word2Vec and GloVe modeling to enhance the performance of a proposed prediction model. Then, the hybrid deep learning model named Dense Convolutional assisted Gannet Optimal Bi-directional Network (DC_GO_BiNet) is introduced for feature extraction and prediction. A Dense Convolutional Neural Network (DCNN) is hybridized with a bi-directional long-short-term memory (Bi-LSTM) model to extract the essential features and predict fake news from the given input text. Also, the proposed model’s parameters are fine-tuned by adopting a gannet optimization (GO) algorithm. The proposed study used three different datasets and obtained higher classification accuracy as 99.5% in Fake News Detection on Twitter EDA, 99.59% in FakeNewsNet and 99.51% in ISOT. The analysis proves that the proposed model attains higher prediction results for each dataset than others.

Hybrid Deep-Learning Model for Deepfake Detection in Video using Transfer Learning Approach

Hybrid Deep-Learning Model for Deepfake Detection in Video using Transfer Learning Approach

Book recommendation using sentiment analysis and ensembling hybrid deep learning models

Book recommendation using sentiment analysis and ensembling hybrid deep learning models

Malware Detection Based on API Call Sequence Analysis: A Gated Recurrent Unit–Generative Adversarial Network Model Approach

Malware remains a major threat to computer systems, with a vast number of new samples being identified and documented regularly. Windows systems are particularly vulnerable to malicious programs like viruses, worms, and trojans. Dynamic analysis, which involves observing malware behavior during execution in a controlled environment, has emerged as a powerful technique for detection. This approach often focuses on analyzing Application Programming Interface (API) calls, which represent the interactions between the malware and the operating system. Recent advances in deep learning have shown promise in improving malware detection accuracy using API call sequence data. However, the potential of Generative Adversarial Networks (GANs) for this purpose remains largely unexplored. This paper proposes a novel hybrid deep learning model combining Gated Recurrent Units (GRUs) and GANs to enhance malware detection based on API call sequences from Windows portable executable files. We evaluate our GRU–GAN model against other approaches like Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU) on multiple datasets. Results demonstrated the superior performance of our hybrid model, achieving 98.9% accuracy on the most challenging dataset. It outperformed existing models in resource utilization, with faster training and testing times and low memory usage.

Predictive models for properties of hybrid blended modified sustainable concrete incorporating nano-silica, basalt fibers, and recycled aggregates: Application of advanced artificial intelligence techniques

The main objective of this work is to improve the compressive strength of concrete, specially in sustainable construction is to develop more precise predictive modeling techniques. The compressive strength prediction of basalt fiber reinforced concrete filled with nano-silica and recycled aggregates can be done using a hybrid deep learning model suggesting the use of the combination of Convolutional Neural Networks and Long Short-Term Memory networks. The CNN captures microstructural features from SEM images, while the LSTM models temporal dependencies from sequential curing data samples. To enhance the prediction accuracy, PCA was performed on feature dimensionality reduction and GA optimized hyperparameters both for the model as well as the concrete mix design for improved strength with cost effectiveness. With an R² value of 0.92–0.95, the performance results of the presented model came out better than the baseline models, as well as reducing the MAE by 20 %. Besides, there existed a 5–8 % better compressive strength in GA-optimized mix designs. Robustness comes into play with the model that shows steady strength predictions, regardless of conditions of curing under multiple conditions and at different material composition levels. Furthermore, the reutilization of recycled aggregates and nano-silica gives a real environmental benefit as less waste is produced but the material performance is maximized. This kind of outcome indicates how the proposed model can be practically applied in optimizing concrete design in terms of strength and sustainability features, thus providing an accessible instrument for decision-making in the construction field. It is an effective tool to improve the performance of concrete while minimizing environmental and material wastes.

Towards Improving E-Commerce Customer Review Analysis for Arabic Language Opinion Mining

In recent years, the rapid development of Internet-related technologies has facilitated the widespread adoption of online purchasing as a convenient means of satisfying consumer needs. Conducting sentiment analysis on user reviews on e-commerce platforms can substantially improve customer satisfaction. In order to resolve this issue, we propose a novel model for sentiment analysis that employs hybrid deep learning ensembles, combining RNN and TreeLSTM with AraBERT as the word embedding. Our research concentrates on creating a hybrid deep-learning model to predict Arabic sentiment accurately. We employ deep learning models with various word embeddings, such as RNN, LSTM, BiLSTM, TreeLSTM, RNN-LSTM, RNN-BiLSTM, and RNN-TreeLSTM. Multiple open-access datasets are used to evaluate the efficacy of the proposed model, including the BRAD dataset, the ARD dataset, and merged datasets containing 610,600 items. The experimental findings indicate that our proposed model is well-suited for evaluating the sentiments expressed in Arabic texts. Our strategy starts with extracting features using the Arabert model, followed by developing and training five hybrid deep-learning models. We attained a significant accuracy improvement of 0.9409 when comparing our method to traditional and hybrid deep learning techniques. This demonstrates that our proposed model precisely analyzes sentiment. These findings are important for enhancing the comprehension of emotions conveyed in Arabic text and have practical implications for various applications, especially e-commerce. By accurately assessing sentiment, businesses can better comprehend customer preferences and enhance consumer satisfaction by enhancing their offerings.

A deep learning-based model for stock price prediction under consideration of financial news publishers

Stock price prediction with financial news is beneficial for making correct investment decisions. Recent researches mainly focus on extracting sentiments from news. The publishers as a crucial part of news, which can reflect the authority and reliability, but are usually neglected. In this paper, we propose a novel hybrid deep learning model for stock price prediction that considers the financial news publishers. Specifically, a novel feature about financial news publishers is constructed by classifying financial news publishers. Furthermore, a novel hybrid model named 2d-CNN-AM-LSTM is proposed by combining Convolutional Neural Network (CNN), Attention Mechanism (AM) and Long Short-term Memory, so that it can fuse textual and numerical data in-depth. To verify the superiority of the proposed model, numerous baselines are employed to conduct experiments with representative stock datasets. The experimental analysis demonstrates that the proposed model considering financial news publishers surpasses other benchmarks and achieves outstanding prediction performance.