Table of contentsLiterature reviewConvolutional neural networks (CNN)Recursive neural network (RNN) and recurrent neural network (Rec NN)Neural networks Deep Belief Networks (DBN)Hybrid Neural NetworksOther Neural NetworksObservationPositive ReviewNegative ReviewConclusionThe process of analyzing and classifying words based on the tags associated with the words is called sentiment analysis. As the above statement clearly states that we will use the lexicon based approach i.e. there is a dictionary containing the bag of words (tags) needed by the neural network to analyze whether the sentiment in the text is positive or negative. A. Sentiment analyzes have found their applications in many areas: analysis of movie reviews, spam detection, success of a product through trend prediction, etc. The Naïve Bayes classifier is a probabilistic classifier that analyzes the presence of a given sentiment in a sentence. A tokenizer is used to tokenize the sentence and transmit the value of the semantic vector to the neural network. The neural network then uses a Naïve Bayes classifier to determine whether the overall sentiment of the sentence is positive or negative. The dataset used is a corpus that contains a bag of labeled words. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get the original essay Peer-reviewed by the International Conference on Sustainable Computing in Science, Technology and Management. Research on sentiment analysis has continued through the ages and the main reason is that the data is easily available in the form of reviews, comments, etc. But this information can be used by a machine using a deep learning neural network. Deep learning code combined with a neural network makes the system more dynamic and adaptable. This helps the neural network to analyze various convoluted patterns and classify them also in the presence of noise. A neural network was designed based on the observation of the complexity present in the neurons of biological organisms. This neuron mainly consisted of 3 parts, namely the dendrites, the stoma and the terminal. There are different types of neural networks available and, depending on their structure and adaptability, they can be used for a multitude of activities. For example, a CNN is primarily used for shape detection and classification in an image, while an RNN is used for text due to its exhaustive iterations and high adaptability in the presence of noise. The neural network we will use in this project will be Naive. Bayesian classifier. The main reason we use Naïve Bayes is that it is designed for sentiment analysis of huge datasets. The naive Bayes classifier classifies each vector label based on its maximum likelihood. Since it is probabilistic, it considers the presence of a characteristic independent of another characteristic. Maximum likelihood is an estimate of the probability of a particular condition, that is, the probability that a particular event will occur. Since it uses a dictionary which in our case is a corpus, it follows supervised learning. Supervised learning is the process in which the neural network learns in the presence of a teacher (image, data, or in our case labels/labeled data in the bag of words). Based on the semantic vector classified by the neural network, the sentiment isanalyzed accordingly. Sentiment analyzes have found application in various applications such as text classification for spam detection, topic detection and recommendation, etc. Furthermore, sentiment analyzes when applied with the help of neural network combinations can perform various complex tasks like automated responses whose relevance increases with the decrease in unavailable time resource. Our proposed model was able to analyze the sentiments of the corpus dataset with an accuracy of 73%. Literature ReviewSentiment analysis has attracted the attention of many authors for two decades. In recent years, many researchers have contributed to different neural network models that are part of artificial neural networks (ANN). These models include convolutional neural networks (CNN), recursive neural networks (RNN), deep neural networks (DNN), recurrent neural networks (RNN), and deep belief networks (DBN).[1] .Convolutional Neural Networks (CNN)The Convolutional Neural Network (CNN) [25] includes layer pooling and sophistication as it gives a standard architecture for mapping variable-length sentences into fixed-size sparse vector sentences. Text sentiment analysis was carried out by the authors [27] on Twitter using deep learning. . They worked to avoid the requirement for the new feature by initializing the CNN parameter weights and it seemed critical to train the model. Neural language and a large group of unsupervised tweets were used for word initialization and training, respectively. Sentiment analysis was performed at the post level and at the sentence level and both resulted in an average rank of 1 across all test sets. Sentiment analysis on micro-blogs has been presented in detail by [28]. CNN has been used to gather user opinions and attitudes regarding hot-button events. The problem of explicit feature extraction was solved through the use of CNN. Implicit learning was carried out by CNN. To collect the target data, input URL and targeted crawler were used, 1000-1500 blog comments/reviews were collected as a corpus and divided into three labels, it i.e. neutral feeling, negative feeling and positive feeling. The proposed model was compared with previous studies as these used CRF, SVM and other traditional algorithms to perform sentiment analysis at a high cost. However, the performance proves that the proposed model is reasonable and sufficient to improve the accuracy in terms of sentiment analysis. The combined textual and visual sentiment analysis proposed by the researchers in [29] motivated the need to control comprehensive social multimedia content. A convolutional neural network (CNN) is one of the neural networks that performs brilliantly when it comes to processing images. This model was a rule-based sentiment classifier called “VADER”. Tweets were collected via the Twitter API. Sentiment labels for the chosen tweets were made using Mechanical Turk (AMT) and crowd intelligence. The results recommend that the joint textual-visual model performed better than the single visual and textual sentiment analysis models. In the study of [15], researchers represented a seven-layer framework to analyze the sentiments of sentences. This framework depends on CNN and Word2vec for sentiment analysis and to calculate vector representation, respectively. Dropout technology, standardization andthe rectified parametric linear unit (PRLU) were used to progress towards the accuracy and generalizability of the proposed model. The framework was verified on the rottentomatoes.com dataset which contains the corpus of film review excerpts. The dataset consists of five labels that are positive, somewhat positive, neutral, negative, and somewhat negative. Comparing the proposed PRLU model with the previously mentioned models such as Matrix-Vector Recursive Neural Network (MV-RNN) and Recursive Neural Network (RNN), we can observe that the proposed PRLU model outperforms the previous Matrix-Vector models with an accuracy of 45.5%. .Recursive Neural Network (RNN) and Recurrent Neural Network (Rec NN)Recursive Neural Network (RNN) [25] lies in supervised learning. It has a tree structure that sets up before training and the nodes have random matrices. There is no need to reconstruct the inputs in RNN. In the study [31], Sentiment Treebank was introduced. It includes fine-grained sentiment labels for expressions in sentence parse trees. To address this, the recursive neural tensor network was introduced. When the proposed model is trained on the new Treebank, this model outperforms all the previously mentioned methods. The combination of a new model and data results in a single-sentence sentiment detection system that pushes the state-of-the-art by 5.4% for positive/negative sentence classification. In addition to this standard setting, the dataset also poses significant new challenges and enables new evaluation measures. For example, RNTN achieves 80.7% accuracy on fine prediction of sentiments in all sentences used and also captures the negation of different sentiments. The research of [25], the idea of ​​sentiment analysis using different recursive architectures – Recurrent neural networks have been proposed. They separated each sentence from each other during revision and fed them to a recursive neural network (RNN). From there, the class is decided and the average semantic vector is then analyzed by the neural network to find the sentiment of the statement. This research paper has compared various techniques and the conclusion is drawn that Support Vector Machine (SVM) – Linear classifier is more accurate than RNN and RecNN i.e. Recursive and recurrent neural network architecture respectively. Deep Neural Networks (DNN) In this study [33], the author proposed a sentiment analysis model taking into account both visual and textual content of social networks. This new scheme used a deep neural network model such as denoising autoencoders and gram skipping which is the basic scheme of the Continuous Bag-Of-Words (CBOW) model. The proposed model included two parts CBOW-LR (logistic regression) for textual content analyzes which were later extended to CBOW-DA-LR. This model was able to classify feelings based on the polarity of visual and textual information. Four datasets were evaluated, namely Sanders Corpus dataset, Sentiment140, SemEval2013 and SentiBank Twitter, from which the proposed model outperformed CBOWS+SVM and FSLM (fully supervised probabilistic language model). Perhaps the fully supervised extended probabilistic language model in terms of small training data had outperformed the current model. As expected, feature learning and gram jumps required large datasets to achieve optimal performance. Deep Belief Networks (DBN) Deep belief networks (DBN) [38] include several.