Multi‐level feature optimization and multimodal contextual fusion for sentiment analysis and emotion classification

Huddar, Mahesh G.; Sannakki, Sanjeev S.; Rajpurohit, Vijay S.

doi:10.1111/coin.12274

Cited by 20 publications

(8 citation statements)

References 32 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[1] propose a deep learning network for sentiment analysis. There are also some research and application of sentiment analysis, such as Sánchez et al [4] introduce an open-source service framework for sentiment analysis, Huddar et al [5] propose a multi-level feature optimization model for sentiment analysis, Chen et al [7] propose a personalized recommendation model based on sentiment analysis, Machová et al [8] study sentiment analysis in conversation content.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis of News Reports in the Period of New Coronavirus

Li¹,

Pan²

2021

dtcse

View full text Add to dashboard Cite

The spread of new coronavirus has a significant impact on the world. To protect people from viruses, a large number of personnel and substances in research, production, medical treatment, and other aspects are used to deal with the virus. News reporting is an important way for people to obtain information about the coronavirus. Objective and immediate news reports can provide people with accurate information and correct response methods, thus playing their due role in defeating the coronavirus. In order to compare the emotional characteristics of news reports, the methods of natural language processing are used to conduct sentiment analysis on news reports, including the subjectivity and the polarity of news reports. We select the news websites of BBC and CNN, that have an important influence in the world, for comparative analysis. The results show that BBC news reports are more positive than CNN, and in terms of subjective, BBC News is more factual than CNN.

show abstract

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis of News Reports in the Period of New Coronavirus

Li¹,

Pan²

2021

dtcse

View full text Add to dashboard Cite

show abstract

“…In order to fuse these numerous features, several research works regarding multimodal sentiment analysis are developed at different vectors having different modalities. 17 Generally, the multimodal sentiment analysis in videos comprises emotions, expressions, feelings, etc which is considered as a complicated task to find the best optimal feature. The most common issues in the existing multimodal sentiment analysis are portrayed by fusing features with large number namely auditory features, video features, and a textual feature there occurs a dimensionality problem that stops achieving the better optimal feature selection with better precision and low computational cost.…”

Section: Background and Motivationmentioning

confidence: 99%

“…The most significant trouble that arises in multimodal sentiment analysis involves the fusing various features such as audio, video, and text. In order to fuse these numerous features, several research works regarding multimodal sentiment analysis are developed at different vectors having different modalities 17 …”

Section: Introductionmentioning

confidence: 99%

Hybrid grass bee optimization‐multikernal extreme learning classifier: Multimodular fusion strategy and optimal feature selection for multimodal sentiment analysis in social media videos

Alqahtani

Pandiaraj²,

Murali³

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Presently, large recordings like audio and video are uploaded each day on the public networks particularly Facebook, YouTube, etc. Such postings generate unlimited data via the Internet. Over the next few decades adapting and dealing with data mining to obtain relevant details from social media is considered as a difficult task. To tackle these challenges, a novel text-audio-video consistency-driven multimodal sentiment analysis method is proposed in this paper. This proposed system examines the correlation among the text, audio and video followed by multimodal sentiment analysis.A different set of features are extracted and then the extracted features are chosen optimally by employing a new hybrid grass bee optimization algorithm (HGBEE) thus obtaining a feature set containing an optimal value for better precision and low computational time. Then an utterance level multimodular fusion regarding text, audio, and video features is developed. Finally, the proposed multikernal extreme learning classifier (MKELM) is employed for sentiment classification. Then the proposed system is evaluated by testing with three multimodal datasets in terms of precision, accuracy, recall, and F-measure, respectively. From the simulation, it is clear that the proposed system accomplishes the maximum classification accuracy value of 98.3% with minimum computation time. The implementation of our proposed approach is done under the MATLAB platform. K E Y W O R D Saccuracy and computation time, feature level fusion, grass bee, kernal extreme learning classifier, multimodal sentiment analysis Recently, the public network facilitates gathering information for posting and sharing various types of multimodal features in social media without knowing much detail regarding the network topology and architecture. 1 Individuals are now widely utilizing the internet-based life condition, for example, YouTube, Facebook, Blog, and Microblog so as to express their opinions. 2 Here, sentiment analysis acts as a key for unlocking huge data since

show abstract

“…One is intra-modal temporal information extraction, and the other is inter-modal interaction information extraction. For the former, the common methods are to use LSTM [6] or CNN [11] to obtain the timing information and context information [17,30,10]. For the latter, some fusion methods proposed can be divided into three categories.…”

Section: Related Workmentioning

confidence: 99%

Video Sentiment Analysis with Bimodal Information-augmented Multi-Head Attention

Wu,

Peng,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Sentiment analysis is the basis of intelligent human-computer interaction. As one of the frontier research directions of artificial intelligence, it can help computers better identify human intentions and emotional states so that provide more personalized services. However, as human present sentiments by spoken words, gestures, facial expressions and others which involve variable forms of data including text, audio, video, etc., it poses many challenges to this study.Due to the limitations of unimodal sentiment analysis, recent research has focused on the sentiment analysis of videos containing time series data of multiple modalities. When analyzing videos with multimodal data, the key problem is how to fuse these heterogeneous data. In consideration that the contribution of each modality is different, current fusion methods tend to extract the important information of single modality prior to fusion, which ignores the consistency and complementarity of bimodal interaction and has influences on the final decision. To solve this problem, a video sentiment analysis method using multi-head attention with bimodal information augmented is proposed. Based on bimodal interaction, more important bimodal features are assigned larger weights. In this way, different feature representations are adaptively assigned

show abstract

Multi‐level feature optimization and multimodal contextual fusion for sentiment analysis and emotion classification

Cited by 20 publications

References 32 publications

Sentiment Analysis of News Reports in the Period of New Coronavirus

Sentiment Analysis of News Reports in the Period of New Coronavirus

Hybrid grass bee optimization‐multikernal extreme learning classifier: Multimodular fusion strategy and optimal feature selection for multimodal sentiment analysis in social media videos

Video Sentiment Analysis with Bimodal Information-augmented Multi-Head Attention

Contact Info

Product

Resources

About