Semi-Supervised Multimodal Deep Learning Model for Polarity Detection in Arguments

Tato, Ange; Nkambou, Roger; Dufresne, Aude; Frasson, Claude

doi:10.1109/ijcnn.2018.8489342

Cited by 7 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Personalized learning recommendation based on recurrent neural networks: Zhou et al [16] clustered learners and used the LSTM model to predict learning paths and achievement, and finally recommended personalized and complete learning paths for learners. To extract the emotional factors expressed in the text, Ange et al used the usersensitive deep multimodal structure and extracted the rich potential data representation of users, which improved the effect of text classification [17]. Wang et al [18] proposed to extract features by using learners' behavior and history, combining attention mechanisms and the difference between predicted and actual values of neural networks to improve recommendation performance.…”

Section: Course Recommendation In the Field Of Deep Learningmentioning

confidence: 99%

A Deep Learning Framework for Multimodal Course Recommendation Based on LSTM+Attention

et al. 2022

View full text Add to dashboard Cite

With the impact of COVID-19 on education, online education is booming, enabling learners to access various courses. However, due to the overload of courses and redundant information, it is challenging for users to quickly locate courses they are interested in when faced with a massive number of courses. To solve this problem, we propose a deep course recommendation model with multimodal feature extraction based on the Long- and Short-Term Memory network (LSTM) and Attention mechanism. The model uses course video, audio, and title and introduction for multimodal fusion. To build a complete learner portrait, user demographic information, explicit and implicit feedback data were added. We conducted extensive and exhaustive experiments based on real datasets, and the results show that the AUC obtained a score of 79.89%, which is significantly higher than similar algorithms and can provide users with more accurate recommendation results in course recommendation scenarios.

show abstract

Section: Course Recommendation In the Field Of Deep Learningmentioning

confidence: 99%

A Deep Learning Framework for Multimodal Course Recommendation Based on LSTM+Attention

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Generalizing from stance classification problems, some work explored ideology as a variable that changes within a range [8]. It was postulated that human stances on issues can be predicted from a low-dimensional model [4,11,15,50]. Ange et al [4] developed a semi-supervised deep learning model based on multi-modal data for polarity detection.…”

Section: Related Workmentioning

confidence: 99%

“…It was postulated that human stances on issues can be predicted from a low-dimensional model [4,11,15,50]. Ange et al [4] developed a semi-supervised deep learning model based on multi-modal data for polarity detection. After that, Darwish et al [15] adopted an unsupervised stance detection model that maps users into a low dimensional space based on their similarity.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders

Li,

Shao,

Sun

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper develops a novel unsupervised algorithm for belief representation learning in polarized networks that (i) uncovers the latent dimensions of the underlying belief space and (ii) jointly embeds users and content items (that they interact with) into that space in a manner that facilitates a number of downstream tasks, such as stance detection, stance prediction, and ideology mapping.Inspired by total correlation in information theory, we propose a novel Information-Theoretic Variational Graph Auto-Encoder (In-foVGAE) that learns to project both users and content items (e.g., posts that represent user views) into an appropriate disentangled latent space. In order to better disentangle orthogonal latent variables in that space, we develop total correlation regularization, PI control module, and adopt rectified Gaussian Distribution for the latent space. The latent representation of users and content can then be used to quantify their ideological leaning and detect/predict their stances on issues. We evaluate the performance of the proposed InfoVGAE on three real-world datasets, of which two are collected from Twitter and one from U.S. Congress voting records. The evaluation results show that our model outperforms state-of-the-art unsupervised models and produce comparable result with supervised models. We also discuss stance prediction and user ranking within ideological groups. The code and datasets are available at https://github.com/happydeadline/InfoVGAE.

show abstract

“…However, single modality is insufficient for image sentiment analysis. Ange [13] proposed a user-sensitive deep multimodal architecture, which takes advantage of deep learning and user data to extract a rich latent representation of a user. The architecture consists of a combination of a long short-term memory (LSTM), LSTM-AutoEncoder, CNN, and multiple deep neural networks (DNNs).…”

Section: A Image Sentiment Analysismentioning

confidence: 99%

Multidimensional Extra Evidence Mining for Image Sentiment Analysis

Zhang

Shi

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Image sentiment analysis is a hot research topic in the field of computer vision. However, two key issues need to be addressed. First, high-quality training samples are scarce. There are numerous ambiguous images in the original datasets owing to diverse subjective cognitions from different annotators. Second, the cross-modal sentimental semantics among heterogeneous image features has not been fully explored. To alleviate these problems, we propose a novel model called multidimensional extra evidence mining (ME 2 M) for image sentiment analysis, it involves sample-refinement and cross-modal sentimental semantics mining. A new soft voting-based sample-refinement strategy is designed to address the former problem, whereas the state-of-the-art discriminant correlation analysis (DCA) model is used to completely mine the cross-modal sentimental semantics among diverse image features. Image sentiment analysis is conducted based on the cross-modal sentimental semantics and a general classifier. The experimental results verify that the ME 2 M model is effective and robust and that it outperforms the most competitive baselines on two well-known datasets. Furthermore, it is versatile owing to its flexible structure.

show abstract

Semi-Supervised Multimodal Deep Learning Model for Polarity Detection in Arguments

Cited by 7 publications

References 19 publications

A Deep Learning Framework for Multimodal Course Recommendation Based on LSTM+Attention

A Deep Learning Framework for Multimodal Course Recommendation Based on LSTM+Attention

Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders

Multidimensional Extra Evidence Mining for Image Sentiment Analysis

Contact Info

Product

Resources

About