Aspect-level Sentiment Classification Research Articles

Interactive memory networks based on syntactic dependencies for aspect-level sentiment classification

Interactive memory networks based on syntactic dependencies for aspect-level sentiment classification

Roaen: reversed dependency graph and orthogonal-gating strategy attention-enhanced network for aspect-level sentiment classification

Roaen: reversed dependency graph and orthogonal-gating strategy attention-enhanced network for aspect-level sentiment classification

Fusion Network for Aspect-Level Sentiment Classification Based on Graph Neural Networks—Enhanced Syntactics and Semantics

Aspect-level sentiment classification (ALSC) struggles with correctly trapping the aspects and corresponding sentiment polarity of a statement. Recently, several works have combined the syntactic structure and semantic information of sentences for more efficient analysis. The combination of sentence knowledge with graph neural networks has also proven effective at ALSC. However, there are still limitations on how to effectively fuse syntactic structure and semantic information when dealing with complex sentence structures and informal expressions. To deal with these problems, we propose an ALSC fusion network that combines graph neural networks with a simultaneous consideration of syntactic structure and semantic information. Specifically, our model is composed of a syntactic attention module and a semantic enhancement module. First, the syntactic attention module builds a dependency parse tree with the aspect term being the root, so that the model focuses better on the words closely related to the aspect terms, and captures the syntactic structure through a graph attention network. In addition, the semantic enhancement module generates the adjacency matrix through self-attention, which is processed by the graph convolutional network to obtain the semantic details. Lastly, the extracted features are merged to achieve sentiment classification. As verified by experiments, the model we propose can effectively enhance ALSC’s behavior.

MFSC: A Multimodal Aspect-Level Sentiment Classification Framework with Multi-Image Gate and Fusion Networks

Currently, there is a great deal of interest in multimodal aspect-level sentiment classification using both textual and visual information, which changes the traditional use of only single-modal to identify sentiment polarity. Considering that existing methods could be strengthened in terms of classification accuracy, we conducted a study on aspect-level multimodal sentiment classification with the aim of exploring the interaction between textual and visual features. Specifically, we construct a multimodal aspect-level sentiment classification framework with multi-image gate and fusion networks called MFSC. MFSC consists of four parts, i.e., text feature extraction, visual feature extraction, text feature enhancement, and multi-feature fusion. Firstly, a bidirectional long short-term memory network is adopted to extract the initial text feature. Based on this, a text feature enhancement strategy is designed, which uses text memory network and adaptive weights to extract the final text features. Meanwhile, a multi-image gate method is proposed for fusing features from multiple images and filtering out irrelevant noise. Finally, a text-visual feature fusion method based on an attention mechanism is proposed to better improve the classification performance by capturing the association between text and images. Experimental results show that MFSC has advantages in classification accuracy and macro-F1.

Enhancing aspect-based sentiment analysis with BERT-driven context generation and quality filtering

Fine-grained sentiment analysis, commonly referred to as aspect-based sentiment analysis (ABSA), has garnered substantial attention in both academic and industrial circles. ABSA focuses on unveiling the sentiment orientation associated with specific entities or attributes within textual data, resulting in a more precise depiction of intricate emotional nuances. However, due to the extensive range of applications for ABSA, certain domains face challenges such as constrained dataset sizes and the absence of exhaustive, high-quality corpora, leading to issues like few-shot learning and resource scarcity scenarios. To address the issue of limited training dataset sizes, one viable approach involves the utilization of text-based context generation to expand the dataset. In this study, we amalgamate Bert-based text generation with text filtering algorithms to formulate our model. Our model fully leverages contextual information using the Bert model, with a particular emphasis on the interrelationships between sentences. This approach effectively integrates the relationships between sentences and labels, resulting in the creation of an initial data augmentation corpus. Subsequently, filtering algorithms have been devised to enhance the quality of the initial augmentation corpus by eliminating low-quality generated data, ultimately yielding the final text-enhanced dataset. Experimental findings on the Semeval-2014 Laptop and Restaurant datasets demonstrate that the enhanced dataset enhances text quality and markedly boosts the performance of models for aspect-level sentiment classification.

Aspect-level sentiment classification with aspect-opinion sentence pattern connection graph convolutional networks

Aspect-level sentiment classification with aspect-opinion sentence pattern connection graph convolutional networks

Chinese text dual attention network for aspect-level sentiment classification.

English text has a clear and compact subject structure, which makes it easy to find dependency relationships between words. However, Chinese text often conveys information using situational settings, which results in loose sentence structures, and even most Chinese comments and experimental summary texts lack subjects. This makes it challenging to determine the dependency relationship between words in Chinese text, especially in aspect-level sentiment recognition. To solve this problem faced by Chinese text in the field of sentiment recognition, a Chinese text dual attention network for aspect-level sentiment recognition is proposed. First, Chinese syntactic dependency is proposed, and sentiment dictionary is introduced to quickly and accurately extract aspect-level sentiment words, opinion extraction and classification of sentimental trends in text. Additionally, in order to extract context-level features, the CNN-BILSTM model and position coding are also introduced. Finally, to better extract fine-grained aspect-level sentiment, a two-level attention mechanism is used. Compared with ten advanced baseline models, the model's capabilities are being further optimized for better performance, with Accuracy of 0.9180, 0.9080 and 0.8380 respectively. This method is being demonstrated by a vast array of experiments to achieve higher performance in aspect-level sentiment recognition in less time, and ablation experiments demonstrate the importance of each module of the model.

An Efficient Aspect-based Sentiment Classification with Hybrid Word Embeddings and CNN Framework

Background: As the e-commerce product reviews and social media posts are increasing enormously, the size of the database for polarity/ sentiment detection is a challenging task, and again, predicting polarities associated with respect to aspect terms end to end in a sentence is a havoc in real-time applications. Human behavior is influenced by the various opinions generated in society. Public opinion influences our decisions most often. Businesses and establishments always need to collect the opinion of the society, which they try to obtain using customer feedback forms and questionnaires or surveys, which help them to be aware of the shortcomings if any, and to use suggestions to improve quality. It works in the same way for customers as well and the opinions of other customers about a particular product can come in handy when deciding to buy a product. Objectives: In this work, an efficient Aspect-based Sentiment Classification technique has been introduced with a hybrid, multiple-word embedding methods and implemented using the CNN framework on large databases. Methods: Most of the traditional models have a limitation on the dependency for one or more similar types of aspect words for sentiment classification problem. However, these conventional models such as TF-ID, Word 2Vec and Glove method consumes much more time for word embedding process and Aspect terms generation and further process of aspect level sentiment classification. Further, these models are facing problems of high true negative rate and misclassification rate on large aspect databases in sentiment classification. In this article, we have introduced an efficient Proposed ensemble word embedding model in the CNN network and defined Hybrid Word2 Vec method, Hybrid Glove word embedding method and Hybrid Random Forest model for sentiment classification. Results: Experiments on a widely used benchmark prove that the proposed word embedding method- based classification technique results in to higher true positive rate with minimal misclassifications and also supports better runtime and accuracy than the traditional word embedding-based aspect level classification approaches. Conclusion: In this article, a hybrid ensemble feature ranking-based classification model is proposed on the large aspect databases. In this work, advanced multiple-word embedding methods are implemented to improve the essential feature extraction problem in the aspect level sentiment process. These multiple-word embedding methods are applied to the sentiment databases in the CNN framework.

A Sparse Self-Attention Enhanced Model for Aspect-Level Sentiment Classification

Aspect based sentiment analysis (ABSA) manifests the well refined work as Aspect-level sentiment classification (ASC) due to recent high attention and profound outcomes. This paper reveals the exorbitant relation of concerned aspect in determining the sentiment polarity of a sentence in addition to their content. Considering an instance, “The food is tasty but restaurant is untidy”, aspect food reveals the polarity as positive, while in case of restaurant, the polarity seems negative. Hence to scout relation between an aspect\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$aspect$$\\end{document} and context\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$context$$\\end{document} words present in sentence is much vital. In spite of the exceptional progress, the ASC experiences certain pitfalls as (1) The current attention based methods makes the given aspect to falsely relate syntactically unrelated words as related ones. (2) Single context-independent representation is only achieved by traditional Word2Vec or GloVe based embedding vectors. (3) Sentiments for multiple words that are inconsecutive remain insufficient for CNN based models. A Sparse-Self-Attention-based Gated Recurrent Unit with Aspect Embedding (SSA-GRU-AE) implementing BERT for ASC is proposed to solve these issues. The proposed SSA-GRU-AE mechanism is centralized on various portions of sentence as multiple aspects are taken as input. The experimental analysis on ASC datasets has proved that proposed model enhanced performance on ASC.

Modeling Structured Dependency Tree with Graph Convolutional Networks for Aspect-Level Sentiment Classification.

Aspect-based sentiment analysis is a fine-grained task where the key goal is to predict sentiment polarities of one or more aspects in a given sentence. Currently, graph neural network models built upon dependency trees are widely employed for aspect-based sentiment analysis tasks. However, most existing models still contain a large amount of noisy nodes that cannot precisely capture the contextual relationships between specific aspects. Meanwhile, most studies do not consider the connections between nodes without direct dependency edges but play critical roles in determining the sentiment polarity of an aspect. To address the aforementioned limitations, we propose a Structured Dependency Tree-based Graph Convolutional Network (SDTGCN) model. Specifically, we explore construction of a structured syntactic dependency graph by incorporating positional information, sentiment commonsense knowledge, part-of-speech tags, syntactic dependency distances, etc., to assign arbitrary edge weights between nodes. This enhances the connections between aspect nodes and pivotal words while weakening irrelevant node links, enabling the model to sufficiently express sentiment dependencies between specific aspects and contextual information. We utilize part-of-speech tags and dependency distances to discover relationships between pivotal nodes without direct dependencies. Finally, we aggregate node information by fully considering their importance to obtain precise aspect representations. Experimental results on five publicly available datasets demonstrate the superiority of our proposed model over state-of-the-art approaches; furthermore, the accuracy and F1-score show a significant improvement on the majority of datasets, with increases of 0.74, 0.37, 0.65, and 0.79, 0.75, 1.17, respectively. This series of enhancements highlights the effective progress made by the STDGCN model in enhancing sentiment classification performance.

Syntactic Graph Attention Network for Aspect-Level Sentiment Analysis

Aspect-level sentiment classification (ASC) is designed to identify the sentiment orientation of given aspect terms in a sentence. Previous neural networks have used attention mechanisms to align context words with the appropriate aspect terms. Without considering syntactic dependencies, these models may erroneously focus on context words that are not related to the aspect terms. To address this issue, the graph convolution network (GCN) and the graph attention network (GAT) are proposed to build a graph based on the dependency parse tree, allowing the representations of context words to be propagated to the aspect terms according to their syntactic dependencies. However, these models consider all syntactic dependencies to be of the same type, and thus may result in inappropriate propagation of word representations in the graph. To further distinguish between the syntactic dependencies, this study proposes a syntactic graph attention network (SGAN) to incorporate the knowledge of dependency types into the graph attention network. The dependency types are modeled as edge embeddings to learn the attention weight of each edge according to its dependency type. By considering different dependency types and their weights, the proposed method can block inappropriate propagation to better associate the context words to aspect terms. To increase training process stability and enrich the diversity of graph representations, a weighted multihead attention is applied to compose the graph representations generated by different heads. The experimental results on five benchmark datasets show that the SGAN yields more accurate results than existing methods.

Aspect-level sentiment classification with fused local and global context

Sentiment analysis aims to determine the sentiment orientation of a text piece (sentence or document), but many practical applications require more in-depth analysis, which makes finer-grained sentiment classification the ideal solution. Aspect-level Sentiment Classification (ALSC) is a task that identifies the emotional polarity for aspect terms in a sentence. As the mainstream Transformer framework in sentiment classification, BERT-based models apply self-attention mechanism that extracts global semantic information for a given aspect, while a certain proportion of local information is missing in the process. Although recent ALSC models have achieved good performance, they suffer from robustness issues. In addition, uneven distribution of samples greatly hurts model performance. To address these issues, we present the PConvBERT (Prompt-ConvBERT) and PConvRoBERTa (Prompt-ConvRoBERTa) models, in which local context features learned by a Local Semantic Feature Extractor (LSFE) are fused with the BERT/RoBERTa global features. To deal with the robustness problem of many deep learning models, adversarial training is applied to increase model stability. Additionally, Focal Loss is applied to alleviate the impact of unbalanced sample distribution. To fully explore the ability of the pre-training model itself, we also propose natural language prompt approaches that better solve the ALSC problem. We utilize masked vector outputs of templates for sentiment classification. Extensive experiments on public datasets demonstrate the effectiveness of our model.

Base on contextual phrases with cross-correlation attention for aspect-level sentiment analysis

In recent years, sentiment analysis has emerged as a prominent area of research within the field of natural language processing. Particularly, aspect-level sentiment classification has gained significant attention for its focus on discerning and analyzing sentiment expressed towards specific aspects within sentences. Existing methods primarily rely on extracting keywords from sentence contexts to determine sentiment polarity, yielding satisfactory results. However, a notable limitation of these approaches is their inability to consider the crucial information contained within key phrases in sentences, which plays a vital role in sentiment analysis. To address this limitation, we propose a novel deformable convolutional network model designed to leverage the power of phrases for aspect-level sentiment analysis. By utilizing deformable convolutions with adaptive receptive fields, our model effectively extracts phrase representations at various contextual distances. Furthermore, a cross-correlation attention mechanism is incorporated to capture interdependencies between phrases and words in the context. To evaluate the effectiveness of our approach, we conduct comprehensive evaluations across widely used datasets, demonstrating the promising performance of our model in enhancing sentiment classification tasks. Our model outperforms the model based on CNN, which also leverages phrase extraction, by improving accuracy by 1.71%, 2.5%, and 1.89%, respectively, on the Laptop, Restaurant, and Twitter datasets. Additionally, it surpasses the performance of the latest models.

Retrieval Contrastive Learning for Aspect-Level Sentiment Classification

Aspect-Level Sentiment Classification (ALSC) aims to assign specific sentiments to a sentence toward different aspects, which is one of the crucial challenges in the field of Natural Language Processing (NLP). Despite numerous approaches being proposed and obtaining prominent results, the majority of them focus on leveraging the relationships between the aspect and opinion words in a single instance while ignoring correlations with other instances, which will make models inevitably become trapped in local optima due to the absence of a global viewpoint. Instance representation derived from a single instance, on the one hand, the contained information is insufficient due to the lack of descriptions from other perspectives; on the other hand, its stored knowledge is redundant since the inability to filter extraneous content. To obtain a polished instance representation, we developed a Retrieval Contrastive Learning (RCL) framework to subtly extract intrinsic knowledge across instances. RCL consists of two modules: (a) obtaining retrieval instances by sparse retriever and dense retriever, and (b) extracting and learning the knowledge of the retrieval instances by using Contrastive Learning (CL). To demonstrate the superiority of RCL, five ALSC models are employed to conduct comprehensive experiments on three widely-known benchmarks. Compared with the baselines, ALSC models achieve substantial improvements when trained with RCL. Especially, ABSA-DeBERTa with RCL obtains new state-of-the-art results, which outperform the advanced methods by 0.92%, 0.23%, and 0.47% in terms of Macro F1 gains on Laptops, Restaurants, and Twitter, respectively.

A hybrid multi-source data fusion for word, sentence, aspect, and document-level sentiment analysis on real-time databases

Sentiment analysis (SA)at the sentence, aspect, and document levels determines the sentiment of particular aspect phrases in a given sentence. Due to their capacity to extract sentiment information from text in aspect-level sentiment classification, neural networks (NNs) have achieved significant success. Generally speaking, sufficiently sizable training corpora are necessary for NNs to be effective. The performance of NN-based systems is reduced by the small size of the aspect-level corpora currently available. In this research, we suggest a gated bilateral recurrent neural network (G-Bi-RNN) as a foundation for multi-source data fusion, their system offers sentiment information that several sources. We develop a uniform architecture specifically to include information from sentimental lexicons, including aspect- and sentence-level corpora. To further provide aspect-specific phrase representations for SA, we use G-Bi-RNN, a deep bilateral Transformer-based pre-trained language model. We assess our methods using SemEval 2014 datasets for laptops and restaurants. According to experimental findings, our method consistently outperforms cutting-edge techniques on all datasets. We use a number of well-known aspect-level SA datasets to assess the efficacy of our model. Experiments show that when compared to baseline models, the suggested model can produce state-of-the-art results.

Performance analysis of aspect-level sentiment classification task based on different deep learning models.

Aspect-level sentiment classification task (ASCT) is a natural language processing task that aims to correctly identify specific aspects and determine their sentiment polarity from a given target sentence. Deep learning models have been proven to be effective in aspect-based sentiment classification tasks, and the mainstream Aspect-level sentiment classification (ASC) models currently constructed generally assume that the training and test datasets are Gaussian distribution (e.g., the same language). Once the data distribution changes, the ASC model must be retrained on the new distribution data to achieve good performance. However, acquiring a large amount of labeled data again typically requires a lot of manpower and money, which seems unlikely, especially for the ASC task, as it requires aspect-level annotation. This article analyzes the performance of sequence-based models, graph-based convolutional neural networks, and pre-training language models on the aspect-level sentiment classification task using two sets of comment datasets in Chinese and English, from four perspectives: classification performance, performance with different aspect numbers, specific case performance, and computational cost. In this article, we design a state-of-the-art ASC-based classification method and conduct a systematic study on eight public standard English and Chinese datasets with various commonly used assessment measures that provide directions for cross-language migration. Finally, we discuss the limitations of the study as well as future research directions.

Hybrid Regularizations for Multi-Aspect Category Sentiment Analysis

Aspect level sentiment classification aims to identify the sentiment polarity towards a particular aspect in a sentence. Previous attention-based methods generate an aspect-specific representation for each aspect and employ it to classify the sentiment polarity. However, normalized attention scores scatter over every word in the sentence, resulting in two issues. First, the attention may inherently introduce noise and downgrade the performance. Second, the opinion words may be “diluted” by other words, while the opinion feature should dominate for sentiment analysis. The issues become more severe in multi-aspect sentences. In this paper, we address the above two issues via hybrid regularizations, i.e., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">aspect-level</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">task-level regularizations</i> . Concretely, the aspect-level regularizations constrain the attention weights to alleviate noise. Among them, orthogonal regularization is designed for multi-aspect sentences and sparse regularization is for single-aspect sentences. To extract sentiment-dominant features, task-level regularization is proposed by introducing an orthogonal auxiliary task, i.e., aspect category detection. This regularization can allocate task-oriented context information for specific downstream tasks. Extensive experimental results on three public datasets demonstrate the effectiveness of the proposed approach in both single-task and multi-task scenarios.

Syntactic Structure-Enhanced Dual Graph Convolutional Network for Aspect-Level Sentiment Classification

Aspect-level sentiment classification (ALSC) is a fine-grained sentiment analysis task that aims to predict the sentiment of the given aspect in a sentence. Recent studies mainly focus on using the Graph Convolutional Networks (GCN) to deal with both the semantics and the syntax of a sentence. However, the improvement is limited since the syntax dependency trees are not aspect-oriented and the exploitation of syntax structure information is inadequate. In this paper, we propose a Syntactic Structure-Enhanced Dual Graph Convolutional Network (SSEDGCN) model for an ALSC task. Firstly, to enhance the relation between aspect and its opinion words, we propose an aspect-wise dependency tree by reconstructing the basic syntax dependency tree. Then, we propose a syntax-aware GCN to encode the new tree. For semantics information learning, a semantic-aware GCN is established. In order to exploit syntactic structure information, we design a syntax-guided contrastive learning objective that makes the model aware of syntactic structure and improves the quality of the feature representation of the aspect. The experimental results on three benchmark datasets show that our model significantly outperforms the baseline models and verifies the effectiveness of our model.

Part-of-speech- and syntactic-aware graph convolutional network for aspect-level sentiment classification

Part-of-speech- and syntactic-aware graph convolutional network for aspect-level sentiment classification

Fusing sentiment knowledge and inter-aspect dependency based on gated mechanism for aspect-level sentiment classification

Aspect level sentiment classification is a fine-grained sentiment analysis task that aims to identify the sentiment polarity of one or more given aspects in a sentence. In natural language, words frequently carry certain sentimental tendencies, which can be beneficial in obtaining the features between aspects and contexts. On the other hand, the dependencies between different aspects in a sentence can provide sufficient information for the sentiment polarity discrimination of a target aspect. However, existing models tend to focus on sentiment knowledge or aspect interactions individually without leveraging their converged information. Therefore, we propose a model based on Gated Mechanism Fusing Sentiment Knowledge and Inter-Aspect dependency (GMF-SKIA) for Aspect-level Sentiment Classification in this paper, aiming to dynamically fuse sentiment knowledge information of words and inter-aspect dependency. Specifically, the model uses the SenticNet sentiment dictionary to add sentiment knowledge information to words during dependency tree construction, and then we introduce a graph convolutional network to obtain sentiment information of dependency tree. We utilize an aspect-related multiheaded self-attention mechanism to model the inter-aspect interactions. Moreover, we design an information gate based on gated mechanism to fuse sentiment knowledge and inter-aspect features. We performed experiments on four publicly available datasets, our model outperforms the best benchmark model by an average of 2.1% and achieves the highest accuracy of 91.56% on the Rest16 dataset.