AMFB: Attention based multimodal Factorized Bilinear Pooling for multimodal Fake News Detection

Kumari, Rina; Ekbal, Asif

doi:10.1016/j.eswa.2021.115412

Cited by 70 publications

(29 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, M ∗ = X S T X t can be obtained, and the base of the subspace of the source domain aligned to the subspace of the target domain can be expressed as X a = X s X S T X t . When comparing samples, the source domain sample γ s and the target domain sample γ t can be mapped to the corresponding subspace respectively, and then, the subspace can be aligned by the transformation matrix M ∗ , and the similarity function can be defined [ 13 , 14 ]:

where A = X S X S T X t X t T represents the importance of each part of the feature vector in the original space. Sim( γ s , γ t ) compares the similarity between the source domain sample γ s and the target domain sample γ t on the aligned subspace, so the K -nearest neighbor algorithm can be used directly for classification [ 15 ].…”

Section: Recognition and Prediction Of Premature Ovarian Failure By U...mentioning

confidence: 99%

Application of Transfer Learning and Feature Fusion Algorithms to Improve the Identification and Prediction Efficiency of Premature Ovarian Failure

Zhang

Hou

Wang

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Ultrasound imaging technology has the advantages of noninvasiveness, real-time, low price, and easy operation. It is one of the most used diagnostic tools for early detection and classification of premature ovarian failure. Although the rapid development of computer-aided diagnosis has provided a great help to the ultrasound diagnosis of premature ovarian failure, it still has many limitations and shortcomings, so this paper adopts transfer learning and feature fusion algorithms to improve the identification and prediction efficiency of premature ovarian failure. In this study, the POF group and the control group both adopted a unified scale. From the four aspects of sociological characteristics, past medical history, environmental factors, and living habits, a dedicated person asked and filled out the scale face to face. All patients participating in the experiment underwent ultrasound examinations. In this paper, the bottom-level feature fusion method is used to improve classification performance. The experiment uses 100 epochs. After each epoch training is completed, we used all the data and labels of the target domain to test. All experiments were performed five times, and the result is the average of five experiments. All the results of baseline and direct classification without migration use the average of five experimental results as the result. Migrating the features extracted by the InceptionV3 network has the best performance for predicting premature ovarian failure. Its classification accuracy is as high as 85.13%, and the F1 value is 0.78. The results show that the migration learning and feature fusion algorithms used in this paper can provide reliable predictive analysis and decision support for doctors in the diagnosis of premature ovarian failure.

show abstract

Section: Recognition and Prediction Of Premature Ovarian Failure By U...mentioning

confidence: 99%

Application of Transfer Learning and Feature Fusion Algorithms to Improve the Identification and Prediction Efficiency of Premature Ovarian Failure

Zhang

Hou

Wang

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…3. The shallow models are also known as traditional machine learning models that have included several algorithms like supervised learning and unsupervised learning, where unsupervised learning includes k-means (Zhang et al 2019) (Ozbay and Alatas February 2020;Huang and Chen November 2020;Silva et al May 2020;Reddy et al 2020;Jiang et al 2021;Javed et al 2021;Kumari andEkbal December 2021), ensemble voting (Mahabub 2020;Qureshi et al 2021), multi-level voting ensemble (Kaur et al 2020), CNN (Kaliyar et al June 2020;Umer et al 2020;Agarwal et al 2020;Kaliyar et al 2021a;Saleh et al 2021;Huu Do et al 2021;Mitra et al 2021;Samadi et al 2021;Meel and Vishwakarma September 2021;Dong et al Dec. 2020), MCNN , C-LSTM (Zervopoulos et al 2019), Coupled Con-vNet (Raj and, BerConvoNet (Choudhary et al 2021), MMCN (Ying et al 2021a), MVAN (Ni et al 2021), NN (Choudhary and Arora 2020;Jain et al 2021), Graph neural network (Song et al 2021, MTMN (Ying et al 2021b), DNN (Ali et al 2021;Kaliyar et al 2021c), Lyapunov function (Shrivastava et al Oct. 2020), social network graph (Sivasankari and Vadivu 2021;Taskin et al 2021), Xception (Han et al July 2021), XGBoost…”

Section: Algorithmic Classificationmentioning

confidence: 99%

A systematic literature review and existing challenges toward fake news detection models

Shah

Ganatra

2022

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Emerging of social media creates inconsistencies in online news, which causes confusion and uncertainty for consumers while making decisions regarding purchases. On the other hand, in existing studies, there is a lack of empirical and systematic examination observed in terms of inconsistency regarding reviews. The spreading of fake news and disinformation on social media platforms has adverse effects on stability and social harmony. Fake news is often emerging and spreading on social media day by day. It results in influencing or annoying and also misleading nations or societies. Several studies aim to recognize fake news from real news on online social media platforms. Accurate and timely detection of fake news prevents the propagation of fake news. This paper aims to conduct a review on fake news detection models that is contributed by a variety of machine learning and deep learning algorithms. The fundamental and well-performing approaches that existed in the past years are reviewed and categorized and described in different datasets. Further, the dataset utilized, simulation platforms, and recorded performance metrics are evaluated as an extended review model. Finally, the survey expedites the research findings and challenges that could have significant implications for the upcoming researchers and professionals to improve the trust worthiness of automated fake news detection models.

show abstract

“…Finally, another recent architecture proposed for multimodal fake news classification can be found in the work carried out by Kumari & Ekbal (2021). The authors propose a model that is made up of four modules: i) ABS-BiLSTM (attention based stacked BiLSTM) for extracting the textual features, ii) ABM-CNN-RNN (attention based CNN-RNN) to obtain the visual representations, ii) MFB (multimodal factorized bilinear pooling), where the feature representations obtained from the previous two modules are fused, and iv) MLP (multi-layer perceptron), which takes as input the fused feature representations provided by the MFB module, and then generates the probabilities for each class (true of fake).…”

Section: Singhmentioning

confidence: 99%

“…Most works have focused only on using textual information (unimodal approaches). Much less effort has been devoted to explore multimodal approaches (Singh et al, 2021;Giachanou et al, 2020;Kumari & Ekbal, 2021), which exploit both texts and images to detect the fake news, obtaining better results than the unimodal approaches. However, these studies typically address the problem of fake news detection as a binary classification task (that is, consisting on classifying news as either true or fake).…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fake News Detection

Alonso-Bartolome¹,

Segura-Bedmar²

2021

Preprint

View full text Add to dashboard Cite

Over the last years, there has been an unprecedented proliferation of fake news.As a consequence, we are more susceptible to the pernicious impact that misinformation and disinformation spreading can have in different segments of our society. Thus, the development of tools for automatic detection of fake news plays and important role in the prevention of its negative effects. Most attempts to detect and classify false content focus only on using textual information.Multimodal approaches are less frequent and they typically classify news either as true or fake. In this work, we perform a fine-grained classification of fake news on the Fakeddit dataset, using both unimodal and multimodal approaches.Our experiments show that the multimodal approach based on a Convolutional Neural Network (CNN) architecture combining text and image data achieves the best results, with an accuracy of 87%. Some fake news categories such as Manipulated content, Satire or False connection strongly benefit from the use of images. Using images also improves the results of the other categories, but with less impact. Regarding the unimodal approaches using only text, Bidirectional Encoder Representations from Transformers (BERT) is the best model with an accuracy of 78%. Therefore, exploiting both text and image data significantly improves the performance of fake news detection.

show abstract

AMFB: Attention based multimodal Factorized Bilinear Pooling for multimodal Fake News Detection

Cited by 70 publications

References 43 publications

Application of Transfer Learning and Feature Fusion Algorithms to Improve the Identification and Prediction Efficiency of Premature Ovarian Failure

Application of Transfer Learning and Feature Fusion Algorithms to Improve the Identification and Prediction Efficiency of Premature Ovarian Failure

A systematic literature review and existing challenges toward fake news detection models

Multimodal Fake News Detection

Contact Info

Product

Resources

About