Transfer-based adaptive tree for multimodal sentiment analysis based on user latent aspects

Rahmani, Sana; Hosseini, Saeid; Zall, Raziyeh; Kangavari, Mohammad Reza; Kamran, Sara; Hua, Wen

doi:10.1016/j.knosys.2022.110219

Cited by 11 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the SoulMate method [50] is specifically designed to measure short-text similarities, taking into account information about the authors. Moreover, we can take into account the personalities of the authors and predict their probability of spreading fake news, adapting the idea described in [51].…”

Section: Methods Based On External Featuresmentioning

confidence: 99%

Multiverse: Multilingual Evidence for Fake News Detection

2023

View full text Add to dashboard Cite

The rapid spread of deceptive information on the internet can have severe and irreparable consequences. As a result, it is important to develop technology that can detect fake news. Although significant progress has been made in this area, current methods are limited because they focus only on one language and do not incorporate multilingual information. In this work, we propose Multiverse—a new feature based on multilingual evidence that can be used for fake news detection and improve existing approaches. Our hypothesis that cross-lingual evidence can be used as a feature for fake news detection is supported by manual experiments based on a set of true (legit) and fake news. Furthermore, we compared our fake news classification system based on the proposed feature with several baselines on two multi-domain datasets of general-topic news and one fake COVID-19 news dataset, showing that (in combination with linguistic features) it yields significant improvements over the baseline models, bringing additional useful signals to the classifier.

show abstract

Section: Methods Based On External Featuresmentioning

confidence: 99%

Multiverse: Multilingual Evidence for Fake News Detection

2023

View full text Add to dashboard Cite

show abstract

“…It has multiple uses in a variety of contexts and industries, including risk assessment, psychological profiling, public opinion research, and product review analysis. However, irony and hyperbole are more difficult to understand when only text is provided [7]. To provide a more robust analytical framework, multimodal sentiment analysis (MSA) blends textual data with visual and audio input.…”

Section: Insights Into Multimodal Sentiment Analysis and Its Inherent...mentioning

confidence: 99%

Optimized Queuing Modeling in Multimodal Sentiment Analysis: An Examination and Application

2024

HSET

View full text Add to dashboard Cite

This paper introduces an innovative queuing model tailored for multimodal sentiment analysis, designed to swiftly generate a preliminary score by prioritizing influential factors from the most valuable modalities. In a bid to yield reliable results in a compressed timeframe, this model meticulously processes data from the modality possessing the paramount effect factor, concurrently trimming down processing time by omitting data from lesser impactful modalities. This discerning approach allows for a dynamic adjustment of the weights assigned to various modalities based on their respective impact variables, culminating in precise and credible sentiment analysis outcomes. In an era where expediency and accuracy are at a premium, the proposed model stands out by ensuring that the sentiment analysis is not just rapid, but also robust and reliable, reflecting the true emotional tonality with a high degree of reliability. The model’s adaptability to fluctuating modalities, ensures its utility across diverse platforms and applications, making it a valuable tool for contemporary sentiment analysis tasks. Amidst a digital landscape that continually evolves, this queuing model for sentiment analysis exemplifies a significant leap forward, proffering enhanced efficiency, accuracy, and reliability in sentiment analysis endeavors.

show abstract

“…This model constructed an adaptive tree by hierarchical partitioning of users, and then trained sub models of Long Short Term Memory (LSTM), utilizing attention-based fusion to transfer cognitive oriented-knowledge within the tree. This algorithm could better use potential clues and promote prediction results compared to other ensemble methods [6]. Middya et al explored various fusion strategies, including early fusion, late fusion, and attention mechanisms, to effectively combine and utilize complementary data from diverse modalities [7].…”

Section: Related Workmentioning

confidence: 99%

The Performance of a Temporal Multi-Modal Sentiment Analysis Model Based on Multitask Learning in Social Networks

He,

2024

ijacsa

View full text Add to dashboard Cite

When conducting sentiment analysis on social networks, facing the challenge of temporal and multi-modal data, it is necessary to enable the model to deeply mine and combine information from various modalities. Therefore, this study constructs an emotion analysis model based on multitask learning. This model utilizes a comprehensive framework of convolutional networks, bidirectional gated recurrent units, and multi head selfattention mechanisms to represent single modal temporal features in an innovative way, and adopts a cross modal feature fusion strategy. The experiment showed that the model accomplished 0.83 average precision and a 0.83 F1-value, respectively. In contrast with multi-scale attention (0.69, 0.70), aspect-based sentiment analysis (0.78, 0.74), and long short-term memory network (0.71, 0.78) models, this model demonstrated higher robustness and classification accuracy. Especially in terms of parallel computing efficiency, the acceleration ratio of the model reached 1.61, which is the highest among all compared models, highlighting the potential for time savings in large data volumes. This study has shown good performance in sentiment analysis in social networks, providing a novel perspective for solving complex sentiment classification problems.

show abstract

Transfer-based adaptive tree for multimodal sentiment analysis based on user latent aspects

Cited by 11 publications

References 48 publications

Multiverse: Multilingual Evidence for Fake News Detection

Multiverse: Multilingual Evidence for Fake News Detection

Optimized Queuing Modeling in Multimodal Sentiment Analysis: An Examination and Application

The Performance of a Temporal Multi-Modal Sentiment Analysis Model Based on Multitask Learning in Social Networks

Contact Info

Product

Resources

About