Sentiment classification with adversarial learning and attention mechanism

Under the background of the gradual development and popularization of mobile Internet information technology, this paper realizes network public opinion monitoring and emotion analysis based on the deep learning method, aiming at the research needs of people's ideological changes and emotional trends. Aiming at the shortcomings of sentiment dictionaries or machine learning methods in sentiment analysis tasks, this paper builds a sentiment classification model based on deep learning methods. First, the current main text preprocessing methods are introduced, and then a sentiment classification model, BCBL, is proposed, combining BERT, CNN, and Bi LSTM. Compared with traditional models, BCBL can better complete text sentiment classification tasks on standard datasets. Next, in view of the problem that BCBL does not consider the distribution of vocabulary weights, an attention mechanism is introduced to improve BCBL, and then the BCBL-Att model is proposed. Set up multiple sets of comparative experiments again and find that the classification effect and overall performance of BCBL-Att on standard datasets are better than BCBL, indicating that BCBL-Att has more advantages in text sentiment classification tasks.

Sentiment analysis also referred to as opinion mining, plays a significant role in automating the identification of negative, positive, or neutral sentiments expressed in textual data. The proliferation of social networks, review sites, and blogs has rendered these platforms valuable resources for mining opinions. Sentiment analysis finds applications in various domains and languages, including English and Arabic. However, Arabic presents unique challenges due to its complex morphology characterized by inflectional and derivation patterns. To effectively analyze sentiment in Arabic text, sentiment analysis techniques must account for this intricacy. This paper proposes a model designed using the transformer model and deep learning (DL) techniques. The word embedding is represented by Transformer-based Model for Arabic Language Understanding (ArabBert), and then passed to the AraBERT model. The output of AraBERT is subsequently fed into a Long Short-Term Memory (LSTM) model, followed by feedforward neural networks and an output layer. AraBERT is used to capture rich contextual information and LSTM to enhance sequence modeling and retain long-term dependencies within the text data. We compared the proposed model with machine learning (ML) algorithms and DL algorithms, as well as different vectorization techniques: term frequency-inverse document frequency (TF-IDF), ArabBert, Continuous Bag-of-Words (CBOW), and skipGrams using four Arabic benchmark datasets. Through extensive experimentation and evaluation of Arabic sentiment analysis datasets, we showcase the effectiveness of our approach. The results underscore significant improvements in sentiment analysis accuracy, highlighting the potential of leveraging transformer models for Arabic Sentiment Analysis. The outcomes of this research contribute to advancing Arabic sentiment analysis, enabling more accurate and reliable sentiment analysis in Arabic text. The findings reveal that the proposed framework exhibits exceptional performance in sentiment classification, achieving an impressive accuracy rate of over 97%.

Analog Switch Off (ASO) or migration program from analog television to digital television is a program issued by the Ministry of Communication and Informatics in Indonesia. Some people provide different responses and opinions on YouTube comments about ASO. There are those who give positive or neutral comments. However, there were also those who gave negative comments. Sentiment analysis is a process that is carried out automatically in studying, retrieving, and processing textual data to obtain information and see responses or opinions about an issue or object towards positive, neutral or negative opinions. Thus sentiment analysis can be used as a reference in making organizational decisions, improving a service, or as a review of a product. Sentiment analysis was performed using word embedding with Word2Vec, and sentiment classification using the Long Short-Term Memory (LSTM) method. The results of the evaluation test are 92% accuracy, 92% precision, 92% recall, and 92% f1-score.

Sentimental Analysis (SA) becomes a familiar topic among business people, which is commonly applied for the classification of sentiments from online reviews. It is generally treated as a sentiment classification (SC) problem where the online reviews are categorized into positive or negative polarities using the words that exist in the online reviews. With this motivation, this paper presents a new K-means clustering with hybrid metaheuristic algorithm (KMC-HMA) for SA and classification. The proposed KMC-HMA technique initially performs data preprocessing to remove the unwanted words from the product reviews. In addition, K-means clustering technique is used for the clustering of the massive quantity of the applied product reviews. Moreover, the clustered data are fed into the classification model based on hybrid ant colony optimization (ACO) with dragonfly algorithm (DFA). The ACO algorithm is used for the classification of product reviews and the performance of the ACO algorithm can be optimally tuned by the use of DFA. The performance validation of the KMC-HMA technique is validated using two datasets such as Canon and ipod. The experimental values pointed out the superior performance of the KMC-HMA technique over the recent state of art techniques.

Opinion Mining and Sentiment Analysis acts as a pivotal role in facilitating businesses to actively operate on enhancing the business strategies and accomplish detailed insights of the consumer’s feedback regarding the products. In recent times, deep learning (DL)technique has been used for many sentiment analysis tasks and has attained effective outcomes. Huge quantity of product reviews is being posted by the customer on different e-commerce and social networking platforms which can assist the developers to improve the quality of the products. The study focuses on the design of Sentiment Classification on Online Product Reviews using Dwarf Mongoose Optimization with Attention based Deep Learning (DMO-ABDL) model. The proposed DMO-ABDL technique analyzes the product reviews for the identification of sentiments. To accomplish this, the DMO-ABDL technique performs different stages of preprocessing to transform the actual data into suitable format. Furthermore, the Glove technique is employed for word embedding process. Moreover, attention based long short-term memory (ALSTM) approach was exploited for sentiment classification and its hyperparameters can be optimally chosen by the DMO technique. A comprehensive set of experiments were performed in order to guarantee the enhanced sentiment classification performance of the DMO-ABDL algorithm. A brief comparative study highlighted the supremacy of the DMO-ABDL technique over other existing approaches under different measures.

Sentiment analysis is an important natural language processing task that helps people understand the emotional information conveyed in texts. This paper aims to propose a sentiment classification model based on the combination of Word2Vec and LSTM (Long Short Term Memory). This paper will introduce two key technologies, Word2Vec and LSTM, combining them to build an effective sentiment analysis model. We conducted a comparative analysis between our model and other state-of-the-art methods including CNN, BiLSTM+CNN, Word2vec+SVM, among others. Through rigorous experimental evaluation, this paper showcases the effectiveness and superior performance of the proposed model in sentiment classification tasks. Our method attains an F1 score of 78.2% on benchmark dataset, indicating its strong performance in the task.

Online education is becoming more and more popular with the development of the Internet. In particular, due to the COVID-19 pandemic, many countries around the world are increasing the popularity of online education, which makes the research on sentiment classification of course reviews of online education websites an important research direction in natural language processing tasks. Traditional sentiment classification models are mostly based on English. Unlike English, Chinese characters are based on pictograms. Radicals of Chinese characters can also express certain semantics, and characters with the same radical often have similar meanings. Therefore, RSCOEWR, a word-level and radical-level based sentiment classification model for course reviews of Chinese online education websites is proposed, which solves the problem of data sparsity of reviews by feature extraction of multiple dimensions. In addition, a deep learning model based on CNN, BILSTM, BIGRU and Attention is constructed to solve the problem of high dimension and assigning the same attention to context of traditional sentiment classification model. Extensive comparative experiment results show that RSCOEWR outperforms the state-of-the-art sentiment classification models, and the experimental results on public Chinese sentiment classification datasets prove the generalization ability of RSCOEWR.

IntroductionSeveral attempts have been made to enhance text-based sentiment analysis’s performance. The classifiers and word embedding models have been among the most prominent attempts. This work aims to develop a hybrid deep learning approach that combines the advantages of transformer models and sequence models with the elimination of sequence models’ shortcomings.MethodsIn this paper, we present a hybrid model based on the transformer model and deep learning models to enhance sentiment classification process. Robustly optimized BERT (RoBERTa) was selected for the representative vectors of the input sentences and the Long Short-Term Memory (LSTM) model in conjunction with the Convolutional Neural Networks (CNN) model was used to improve the suggested model’s ability to comprehend the semantics and context of each input sentence. We tested the proposed model with two datasets with different topics. The first dataset is a Twitter review of US airlines and the second is the IMDb movie reviews dataset. We propose using word embeddings in conjunction with the SMOTE technique to overcome the challenge of imbalanced classes of the Twitter dataset.ResultsWith an accuracy of 96.28% on the IMDb reviews dataset and 94.2% on the Twitter reviews dataset, the hybrid model that has been suggested outperforms the standard methods.DiscussionIt is clear from these results that the proposed hybrid RoBERTa–(CNN+ LSTM) method is an effective model in sentiment classification.

Due to the vast amount of reviews available on the Web, in the past decades, a growing share of work has focused on sentiment analysis. Aspect-based sentiment classification is the subtask that seeks to detect the sentiment expressed by the content creators towards a defined target within a sentence. This paper introduces three novel unsupervised attentional neural network models for aspect-based sentiment classification, and tests them on English restaurant reviews. The first model employs an autoencoder-like structure to learn a sentiment embedding matrix where each row of the matrix represents the embedding for one sentiment. To improve the model, a target-based attention mechanism is included that de-emphasizes irrelevant words. Last, a redundancy and a seed regularization term constrain the sentiment embedding matrix. The second model extends the first by including a Bi-LSTM layer in the attention mechanism to exploit contextual information. The third model further adapts a Left-Center-Right separated neural network with Rotatory attention structure from the supervised realm to an unsupervised setting. Although all three models construct meaningful sentiment embeddings, experimental results indicate that the inclusion of the Bi-LSTM in the attention mechanism leads to a more precise attention mechanism and, thus, better predictions. The best model, i.e., the second, outperforms all investigated unsupervised and weakly supervised algorithms for aspect-based sentiment classification from the literature.

Sentiment analysis of product reviews plays a crucial role in understanding consumer feedback, improving customer experience and making informed business decisions. This paper explores the application of machine learning and deep learning algorithms to effectively classify and analyse the sentiment of product reviews. Traditional machine learning techniques, such as Naïve Bayes, Support Vector Machines (SVM) and Random Forests are employed for sentiment classification based on manually engineered features. Simultaneously, deep learning approaches like Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks are leveraged to automatically learn complex representations from raw text data. The study compares the performance of these methods in terms of accuracy, precision, recall and F1-score. Additionally, pre-trained language models such as BERT are incorporated to enhance contextual understanding. Experimental results demonstrate that deep learning models particularly LSTM and BERT, outperform traditional machine learning techniques in capturing sentiments. This analysis provides valuable insights into the effectiveness of different algorithms in sentiment analysis tasks, paving the way for more advanced applications in natural language processing and customer sentiment evaluation.

Korean is the native and official language spoken by Chinese-Korean people, and Weibo is a social media software with a huge number of users in China. Currently, there is few studies related to sentiment analysis of Korean-language Weibo texts posted by Chinese-Korean users. In this paper, we propose a sentiment classification method for Chinese-Korean Weibo based on pre-trained language model and transfer learning. Firstly, we crawled the Chinese-Korean Weibo data from Sina Weibo and label them with sentiment to get the Chinese-Korean Weibo sentiment analysis (CKWSA) dataset. Secondly, to solve the problem of few training samples of the Chinese-Korean Weibo sentiment analysis dataset, we fine-tune the classifier based on the pre-trained Korean language model on the Korean Twitter sentiment analysis dataset to obtain the Korean Twitter sentiment classification model; and further fine-tune the model on CKWSA dataset to get Chinese-Korean Weibo sentiment classification model. The experiments show that the proposed classification method based on pre-trained language model and transfer learning has great performance, and there is an improvement compared other baselines on the Chinese-Korean Weibo sentiment analysis dataset.

Deep Learning is a promising domain. It has different applications in different areas of life, and its application on the stock market is widely used due to its efficiency. Long Short-Term Memory (LSTM) proved its efficiency in dealing with time series data due to the unique hidden unit structure. This paper integrated LSTM with Attention Mechanism and sentiment analysis to forecast the closing price of two stocks, namely APPL and TSLA, from the NASDAQ stock market. We compared our hybrid model with LSTM, LSTM with sentiment analysis, and LSTM with Attention Mechanism. Three benchmarks are used to measure the performance of the models, the first one is Mean Square Error (MSE), the second one is Root Mean Square Error (RMSE), and the third one is Mean Absolute Error (MAE). The results show that the hybridization is more accurate compared to only LSTM model.

Aspect-based sentiment classification (ABSC) (also called fine-grained sentiment analysis) is an essential and challenging task among sentiment analysis tasks. Aspect level sentiment analysis overcomes the limitation of the document and sentence level when multiple aspects appear in a review. Recently, neural network approaches like LSTM has achieved better results in ABSC than traditional machine learning algorithms. Aspect extraction and polarity detection for specific aspects in the review becoming an important task in aspect level sentiment analysis. Therefore, the paper aims to predict the sentiment polarity of each aspect in the review into 3 classes by developing the multi-aspect attention (MAA) model and combine it with the BiLSTM neural network, called MAA-BLSTM. Unlike unidirectional LSTM, the BiLSTM network runs the input in two directions: forward and backward, therefore, it can understand the context better than LSTM. In this paper, the hyperparameter tuning approach is also considered to be the high-performing model. Experiments are tested on restaurant and laptop data from SemEval (2014, 2015, and 2016) datasets and compare the result with other LSTM-based methods. Finally, the result proves that the accuracy of the proposed sentiment model reaches 89.9 on the restaurant dataset and 82.1 on the laptop dataset which are higher than other LSTM approaches.

Text sentiment analysis is used to find out how much the public’s appreciation and preferences for specific events or objects. In order to effectively extract the deep emotional features of words, this paper proposes two sentiment analysis methods, which are emotion adjustment method based on semantic similarity and skip-gram model. In these two methods, word vectors containing semantic information obtained from Word2vec and emotional seeds are used to adjust the sentiment orientation of the words so that word vectors can trained both the semantic information and the sentiment contents. And the TF-IDF method is used to calculate the word’s weight in the text, the vector of the whole text is represented by adding the weighted word vectors. Experiments show that the emotion-adjusted word vector improves the accuracy of the text sentiment analysis more effectively than the traditional method, and proves the validity of these two methods in the sentiment analysis task. At the same time, the emotion adjustment method based on skip-gram model is more effective than the method based on semantic similarity.

This study addresses the accuracy challenges in e-commerce sentiment classification and thus provides valuable insight for businesses to enrich strategies toward the interpretation of customer feedback and improvement of product development. This article elaborately contrasts long short-term memory (LSTM)-based models with traditional machine learning models, like support vector machines (SVM), random forest, and Naive Bayes classifiers. The authors have used a large dataset of customer reviews from famous e-commerce websites, pre-processed for noise reduction and standardization of the input. Our LSTM models were implemented using state-of-the-art deep learning frameworks, with special consideration while performing hyperparameter tuning. The results showed that the bidirectional LSTM model had the best performance of 92.1% in accuracy, 91.8% in precision, 92.0% in recall, and an F1-score of 91.9%. In comparison, traditional machine learning approaches gave accuracies: 86.5% for SVM, 85.1% for random forest, and 82% for Naive Bayes. Hyperparameter tuning returned the best configurations for the LSTM models: 128 LSTM units, a dropout of 0.3, with learning rates 0.001 for LSTM and 0.0001 for bidirectional LSTM. These optimizations contributed hugely to the performance improvements observed in these models. Error analysis gave insights into the challenges that the models faced. Sarcasm and irony accounted for 22% of the classification errors, while mixed sentiment accounted for 18%, and implicit accounted for 15%. To sum up, this research has shown the efficiency of LSTM models on e-commerce user review sentiment analysis, especially bidirectional LSTM. These models show a much better result in sentiment classification compared to traditional machine learning techniques, which proves them to have huge potential for improving the accuracy of the task in real-world applications.