Multimodal sentimental analysis for social media applications: A comprehensive review
01 Sep 2021-Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery (John Wiley & Sons, Ltd)-Vol. 11, Iss: 5
TL;DR: This work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them.
Abstract: The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text‐based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.
Citations
More filters
TL;DR: In this article , the authors proposed a method to detect the leaf diseases in the tomato plant using support vector machine (SVM), convolutional neural network (CNN), and K-Nearest Neighbor (K-NN).
Abstract: Agriculture provides food to all the human beings even in case of rapid increase in the population. It is recommended to predict the plant diseases at their early stage in the field of agriculture is essential to cater the food to the overall population. But it unfortunate to predict the diseases at the early stage of the crops. The idea behind the paper is to bring awareness amongst the farmers about the cutting-edge technologies to reduces diseases in plant leaf. Since tomato is merely available vegetable, the approaches of machine learning and image processing with an accurate algorithm is identified to detect the leaf diseases in the tomato plant. In this investigation, the samples of tomato leaves having disorders are considered. With these disorder samples of tomato leaves, the farmers will easily find the diseases based on the early symptoms. Firstly, the samples of tomato leaves are resized to 256 × 256 pixels and then Histogram Equalization is used to improve the quality of tomato samples. The K-means clustering is introduced for partitioning of dataspace into Voronoi cells. The boundary of leaf samples is extracted using contour tracing. The multiple descriptors viz., Discrete Wavelet Transform, Principal Component Analysis and Grey Level Co-occurrence Matrix are used to extract the informative features of the leaf samples. Finally, the extracted features are classified using machine learning approaches such as Support Vector Machine (SVM), Convolutional Neural Network (CNN) and K-Nearest Neighbor (K-NN). The accuracy of the proposed model is tested using SVM (88%), K-NN (97%) and CNN (99.6%) on tomato disordered samples.
54 citations
01 Nov 2021
TL;DR: The result shows that MobileNetV2 performance is relatively better than other pre trained models and in the future enhancement transfer learning may be used for natural language processing to obtain highest accuracy.
Abstract: Transfer learning is used to reuse the pre-trained model. Transfer learning uses the knowledge which was gained from the previous task. Transfer learning is most generally used in image classification, image prediction and natural language processing. Some of the example for the natural language processing it includes sentiment analysis, text auto complete etc. The literature shows that deep learning performance is relatively more when compared with machine learning technique for the large data set. In this paper pre trained models such as MobileNet, MobileNetV2, VGG16, VGG19 and ResNet50 has been used for image classification and prediction. For the image classification and prediction Google Colab notebook has been used. The performance of the system depends on the GPU system hence results are tested in Google colab notebook. The result shows that MobileNetV2 performance is relatively better than other pre trained models. MobileNetV2 uses the less number of parameters as compared with other trained model. ResNet50 accuracy is more when it compared with other trained model with the ImageNet dataset. In the future enhancement transfer learning may be used for natural language processing to obtain highest accuracy.
33 citations
29 citations
TL;DR: In this paper, a business decision making system (BDMS) is proposed to develop business using social media data analytics, which provides a clear understanding of the key principles, issues and functionality, and big social data developments.
Abstract: For the past few years, business intelligence has been a major field that uses data analysis to produce key information as part of business decision-making. Data collected from social media sites and blogs are analyzed to make business decisions, a process called social media analytics (SMA). This method, which goes beyond ordinary monitoring or a basic analysis of retweets, develops an in-depth insight into the social consumer. After reading the whole report, add the pertinent figures to the table. Add pertinent data from the Brand24 report to the table. During a social media audit, any followers, impressions, engagement, copy/traffic, and brand mentions are key parameters to analyze. For companies and research institutions, the great interest is to analyse and gain knowledge from user-produced data. These data contain useful knowledge, including customer perceptions feedback and product/service suggestions. Due to content saturation, social media's true meaning regarding business data is hardly ever found. Therefore, in this paper, the business decision making system (BDMS) has been proposed to develop business using social media data analytics. BDMS provides a clear understanding of the key principles, issues and functionality, and big social data developments. Besides, BDMS concentrates on marketing and describes an operational approach for obtaining valuable information from social data. BDMS performs a short and precise description of current use scenarios from the evidence, as per the help of decisions and investment opportunities companies get when using social data analytics. The experimental result shows that BDMS achieves the highest competitive results. With greater accuracy, system dependability, F-1 measurement, and deviation rate of 85.5%, the BDMS system guarantees 93.7%, 86.8%, and 7.0%.
28 citations
TL;DR: In this article, a Big Data-assisted Social Media Analytics for Business (BD-SMAB) model is proposed to increase awareness and affect decision-makers in marketing strategies.
Abstract: Business is based on manufacturing, purchasing, selling a product, and earning or making profits. Social media analytics collect and analyze data from various social networks such as Facebook, Instagram, and Twitter. Social media data analysis can help companies identify consumer desires and preferences, improve customer service and market analytics on social networks, and smarter product development and marketing investments. The business decision-making process is a step-by-step process that enables employees to resolve challenges by weighing evidence, evaluating possible solutions, and selecting a route. In this paper, Big Data-assisted Social Media Analytics for Business (BD-SMAB) Model increases awareness and affects decision-makers in marketing strategies. Companies can use big data analytics in many ways to enhance management. It can evaluate its competitors in real-time and change prices, make deals better than its competitors' sales, analyze competitors' unfavorable feedback and see if they can outperform that competitor. The proposed method examines social media analysis impacts on different areas such as real estate, organizations, and beauty trade fairs. This diversity of these companies shows the effects of social media and how positive decisions can be developed. Take better marketing decisions and develop a strategic approach. As a result, the BD-SMAB method enhance customer satisfaction and experience and develop brand awareness.
25 citations
References
More filters
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Abstract: We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.
15,055 citations
"Multimodal sentimental analysis for..." refers methods in this paper
...The first model of restricted Boltzmann machine (RBM) was introduced by the author of Smolensky (1986) and later modified by the author of Hinton, Osindero, and Teh (2006)....
[...]
TL;DR: Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
Abstract: The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
14,377 citations
"Multimodal sentimental analysis for..." refers background in this paper
...The concept of deep learning is an advanced field of machine learning as indicated by the author in Silver et al. (2016) that uses multiple layers of networks that overcome the obstacles of CNNs....
[...]
Proceedings Article•
01 Oct 2013TL;DR: A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
Abstract: Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. Further progress towards understanding compositionality in tasks such as sentiment detection requires richer supervised training and evaluation resources and more powerful models of composition. To remedy this, we introduce a Sentiment Treebank. It includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality. To address them, we introduce the Recursive Neural Tensor Network. When trained on the new treebank, this model outperforms all previous methods on several metrics. It pushes the state of the art in single sentence positive/negative classification from 80% up to 85.4%. The accuracy of predicting fine-grained sentiment labels for all phrases reaches 80.7%, an improvement of 9.7% over bag of features baselines. Lastly, it is the only model that can accurately capture the effects of negation and its scope at various tree levels for both positive and negative phrases.
6,792 citations
"Multimodal sentimental analysis for..." refers methods in this paper
...3 Socher et al. (2013) Movie review textual dataset The RNTN model got 87% accuracy in the sentiment prediction task 16 of 28 CHANDRASEKARAN ET AL....
[...]
01 Jan 2010
TL;DR: This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
Abstract: We explore an original strategy for building deep networks, based on stacking layers of denoising autoencoders which are trained locally to denoise corrupted versions of their inputs. The resulting algorithm is a straightforward variation on the stacking of ordinary autoencoders. It is however shown on a benchmark of classification problems to yield significantly lower classification error, thus bridging the performance gap with deep belief networks (DBN), and in several cases surpassing it. Higher level representations learnt in this purely unsupervised fashion also help boost the performance of subsequent SVM classifiers. Qualitative experiments show that, contrary to ordinary autoencoders, denoising autoencoders are able to learn Gabor-like edge detectors from natural image patches and larger stroke detectors from digit images. This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
5,303 citations
Journal Article•
TL;DR: Denoising autoencoders as mentioned in this paper are trained locally to denoise corrupted versions of their inputs, which is a straightforward variation on the stacking of ordinary autoencoder.
Abstract: We explore an original strategy for building deep networks, based on stacking layers of denoising autoencoders which are trained locally to denoise corrupted versions of their inputs. The resulting algorithm is a straightforward variation on the stacking of ordinary autoencoders. It is however shown on a benchmark of classification problems to yield significantly lower classification error, thus bridging the performance gap with deep belief networks (DBN), and in several cases surpassing it. Higher level representations learnt in this purely unsupervised fashion also help boost the performance of subsequent SVM classifiers. Qualitative experiments show that, contrary to ordinary autoencoders, denoising autoencoders are able to learn Gabor-like edge detectors from natural image patches and larger stroke detectors from digit images. This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
4,814 citations