Aspect-based Sentiment Analysis Task Research Articles

Generative Aspect Sentiment Quad Prediction with Self-Inference Template

Aspect Sentiment Quad Prediction is a research topic of paramount significance and complexity within the Aspect-Based Sentiment Analysis task. Leveraging the generative paradigm of the T5 model, we achieve end-to-end extraction of aspect sentiment elements by paraphrasing the original text into sentences predefined by templates. Current research predominantly confines templates to single sentences or directly concatenates sentiment elements using a few symbols, limiting the model’s reasoning opportunities. In this work, we introduce a Self-Inference Template (SIT) to guide the model in thoughtful reasoning, facilitating a step-by-step inference generation process. This approach enables the model to more accurately identify aspect sentiment elements and their interdependencies. Experimental results demonstrate a significant improvement in quadruplet prediction performance under constant time costs, effectively mitigating overfitting issues caused by limited data volume to some extent.

DualGCN: Exploring Syntactic and Semantic Information for Aspect-Based Sentiment Analysis.

The task of aspect-based sentiment analysis aims to identify sentiment polarities of given aspects in a sentence. Recent advances have demonstrated the advantage of incorporating the syntactic dependency structure with graph convolutional networks (GCNs). However, their performance of these GCN-based methods largely depends on the dependency parsers, which would produce diverse parsing results for a sentence. In this article, we propose a dual GCN (DualGCN) that jointly considers the syntax structures and semantic correlations. Our DualGCN model mainly comprises four modules: 1) SynGCN: instead of explicitly encoding syntactic structure, the SynGCN module uses the dependency probability matrix as a graph structure to implicitly integrate the syntactic information; 2) SemGCN: we design the SemGCN module with multihead attention to enhance the performance of the syntactic structure with the semantic information; 3) Regularizers: we propose orthogonal and differential regularizers to precisely capture semantic correlations between words by constraining attention scores in the SemGCN module; and 4) Mutual BiAffine: we use the BiAffine module to bridge relevant information between the SynGCN and SemGCN modules. Extensive experiments are conducted compared with up-to-date pretrained language encoders on two groups of datasets, one including Restaurant14, Laptop14, and Twitter and the other including Restaurant15 and Restaurant16. The experimental results demonstrate that the parsing results of various dependency parsers affect their performance of the GCN-based models. Our DualGCN model achieves superior performance compared with the state-of-the-art approaches. The source code and preprocessed datasets are provided and publicly available on GitHub (see https://github.com/CCChenhao997/DualGCN-ABSA).

Evaluating Graph Attention Networks as an Alternative to Transformers for ABSA Task in Low-Resource Languages

Opinions toward subjects and products hold immense relevance in business to guide decision-making processes. However, due to the increase in user-generated content, manual analysis is unrealistic. Techniques such as Sentiment Analysis are paramount to understanding and quantifying human emotion expressed in text data. Aspect-Based Sentiment Analysis aims to extract aspects from an opinionated text while identifying their underlying sentiment. Graph-based text representations have been shown to bring benefits to this task, as they explicitly represent structural relationships in text. While studies have demonstrated the effectiveness of this representation for Aspect-based Sentiment Analysis using Graph Neural Networks in English, there is only sparse evidence of improvement using these techniques for low-resource languages such as Portuguese. We develop a straightforward Graph Attention Network model for the Aspect-Based Sentiment Analysis task in Brazilian Portuguese. The proposed approach achieves a Balanced Accuracy score of 0.74, yielding competitive results and ranking third place in the ABSAPT competition. Furthermore, by leveraging sparse graph connections our model is less computationally demanding than a Transformer architecture in terms of training and inference.

Dual-channel relative position guided attention networks for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) aims to match sentiment tendencies for different aspects of a sentence to understand the product experience of the user. It is a pressing challenge for existing ABSA methods to synthesize sentences’ semantic relevance and syntactic dependency for more comprehensive sentiment representations. In this paper, we propose a Dual-Channel Relative Position Guided Attention Network (Dual-RPGA). Dual-RPGA deeply learns semantic and syntactic representations of sentiment to provide reliable knowledge for dynamic fusion and prediction of sentiment. First, we design a syntactic graph attention network (Syn-GAT) to learn the syntactic relative position between aspect and context, which guides the sentiment syntactic representation. Then, we build a semantic attention network (Sem-Attention). It computes semantic attention and similarity coefficients for aspects and contexts to enhance sentiment semantic expressions. Finally, we design a fusion network (Bi-Fusion) that realizes dynamic feature interactions of sentiment semantics and syntactics to perform sentiment prediction. We conduct extensive experiments on two groups of datasets to validate the performance of Dual-RPGA on the ABSA task. The results show that Dual-RPGA outperforms the optimal baseline by 0.58%∼1.49% of the Acc score, which verifies that Dual-RPGA performs better on the ABSA task.

A syntactic features and interactive learning model for aspect-based sentiment analysis

The aspect-based sentiment analysis (ABSA) consists of two subtasks: aspect term extraction (AE) and aspect term sentiment classification (ASC). Previous research on the AE task has not adequately leveraged syntactic information and has overlooked the issue of multi-word aspect terms in text. Current researchers tend to focus on one of the two subtasks, neglecting the connection between the AE and ASC tasks. Moreover, the problem of error propagation easily occurs between two independent subtasks when performing the complete ABSA task. To address these issues, we present a unified ABSA model based on syntactic features and interactive learning. The proposed model is called syntactic interactive learning based aspect term sentiment classification model (SIASC). To overcome the problem of extracting multi-word aspect terms, the model utilizes part-of-speech features, words features, and dependency features as textual information. Meanwhile, we designs a unified ABSA structure based on the end-to-end framework, reducing the impact of error propagation issues. Interaction learning in the model can establish a connection between the AE task and the ASC task. The information from interactive learning contributes to improving the model’s performance on the ASC task. We conducted an extensive array of experiments on the Laptop14, Restaurant14, and Twitter datasets. The experimental results show that the SIASC model achieved average accuracy of 84.11%, 86.65%, and 78.42% on the AE task, respectively. Acquiring average accuracy of 81.35%, 86.71% and 76.56% on the ASC task, respectively. The SIASC model demonstrates superior performance compared to the baseline model.

Text Triplet Extraction Algorithm with Fused Graph Neural Networks and Improved Biaffine Attention Mechanism

In the realm of aspect-based sentiment analysis (ABSA), a paramount task is the extraction of triplets, which define aspect terms, opinion terms, and their respective sentiment orientations within text. This study introduces a novel extraction model, BiLSTM-BGAT-GCN, which seamlessly integrates graph neural networks with an enhanced biaffine attention mechanism. This model amalgamates the sophisticated capabilities of both graph attention and convolutional networks to process graph-structured data, substantially enhancing the interpretation and extraction of textual features. By optimizing the biaffine attention mechanism, the model adeptly uncovers the subtle interplay between aspect terms and emotional expressions, offering enhanced flexibility and superior contextual analysis through dynamic weight distribution. A series of comparative experiments confirm the model’s significant performance improvements across various metrics, underscoring its efficacy and refined effectiveness in ABSA tasks.

Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis

Despite having achieved notable success for aspect-based sentiment analysis (ABSA), deep neural networks are susceptible to spurious correlations between input features and output labels, leading to poor robustness. In this paper, we propose a novel Counterfactual-Enhanced Information Bottleneck framework (called CEIB) to reduce spurious correlations for ABSA. CEIB extends the information bottleneck (IB) principle to a factual-counterfactual balancing setting by integrating augmented counterfactual data, with the goal of learning a robust ABSA model. Concretely, we first devise a multi-pattern prompting method, which utilizes the large language model (LLM) to generate high-quality counterfactual samples from the original samples. Then, we employ the information bottleneck principle and separate the mutual information into factual and counterfactual parts. In this way, we can learn effective and robust representations for the ABSA task by balancing the predictive information of these two parts. Extensive experiments on five benchmark ABSA datasets show that our CEIB approach achieves superior prediction performance and robustness over the state-of-the-art baselines. Code and data to reproduce the results in this paper is available at: https://github.com/shesshan/CEIB.

TextGT: A Double-View Graph Transformer on Text for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is aimed at predicting the sentiment polarities of the aspects included in a sentence instead of the whole sentence itself, and is a fine-grained learning task compared to the conventional text classification. In recent years, on account of the ability to model the connectivity relationships between the words in one sentence, graph neural networks have been more and more popular to handle the natural language processing tasks, and meanwhile many works emerge for the ABSA task. However, most of the works utilizing graph convolution easily incur the over-smoothing problem, while graph Transformer for ABSA has not been explored yet. In addition, although some previous works are dedicated to using both GNN and Transformer to handle text, the methods of tightly combining graph view and sequence view of text is open to research. To address the above issues, we propose a double-view graph Transformer on text (TextGT) for ABSA. In TextGT, the procedure in graph view of text is handled by GNN layers, while Transformer layers deal with the sequence view, and these two processes are tightly coupled, alleviating the over-smoothing problem. Moreover, we propose an algorithm for implementing a kind of densely message passing graph convolution called TextGINConv, to employ edge features in graphs. Extensive experiments demonstrate the effectiveness of our TextGT over the state-of-the-art approaches, and validate the TextGINConv module. The source code is available at https://github.com/shuoyinn/TextGT.

Twin Towers End to End model for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) aims to conduct fine-grained sentiment analysis, necessitating the extraction of three key components: target entity, aspect category and sentiment polarity. These three components collectively form an integrated ABSA task known as TASD (Target-Aspect-Sentiment jointly Detection). Most of existing approaches on ABSA usually employ Recurrent neural networks(RNNs), Convolutional neural networks(CNNs) or pre-training models such as Bidirectional Encoder Representations from Transformers(BERT). However, they have some common weaknesses. First, most of the existing methods focus on one or two sub-tasks instead of triplet detection, thus they do not establish an end-to-end (training a complex learning system represented by a single model) ABSA model and cannot utilize the relevance of multiple ABSA sub-tasks during training. Second, they cannot achieve accuracy and efficiency simultaneously due to the coupling of context and given aspects. Third, they are poor in recognizing implicit targets. To tackle these limitations, this paper proposes a novel method named the Twin Towers End to End model (TTEE) to solve TASD task. It transforms complex TASD task into a simple end-to-end multi-task framework, simultaneously conducting target and aspect-sentiment detection. It builds twin towers system based on BERT or its updated versions to decouple context and given aspects, which can reduce redundant calculation to improve computational efficiency significantly. It offers great advantage to identify implicit target entity and its associated aspect-sentiment in the context without introducing extra model architecture. Experiments on three public datasets in different domains demonstrate that our approach not only achieves better performance on various evaluation metrics, but also has high efficiency in both training and inference phases, over a wide range of sample size and number of aspect categories.

Aspect Sentiment Triplet Extraction Based on Deep Relationship Enhancement Networks

The task of aspect-based sentiment analysis (ASBA) is to identify all the sentiment analyses expressed by specific aspect words in the text. How to identify specific objects (i.e., aspect words), describe the modifiers of the specific objects (i.e., opinion words), and judge the sentiment analysis expressed by opinion words (sentimental classification) in one step has become a focus of research in ASBA. ASTE (Aspect Sentiment Triplet Extraction) based on DREN (Deep Relationship Enhancement Networks) has been proposed in this paper. It aims to extract the aspect words and opinion words in the review text in one-step. They can judge the sentiment analysis expressed by the opinion words. Therefore, the study defines ten kinds of word relations; then, the study uses the parts of the speech feature, syntactic feature, relative position feature and tree distance relative feature to enhance the word representation relationship, which enriches the table of information in the relational matrix. Secondly, based on the word representation of BERT and GCN, the structural information of the texts are extracted; then, further extraction of higher-level word semantic information and word relationship information through SWDA (Sliding Window Dilated Attention) occurs, as SWDA can capture the multi-granularity relationship in words. Finally, the experimental results show that the proposed method is effective.

A cross-model hierarchical interactive fusion network for end-to-end multimodal aspect-based sentiment analysis

For the aspect-based sentiment analysis task, traditional works are only for text modality. However, in social media scenarios, texts often contain abbreviations, clerical errors, or grammatical errors, which invalidate traditional methods. In this study, the cross-model hierarchical interactive fusion network incorporating an end-to-end approach is proposed to address this challenge. In the network, a feature attention module and a feature fusion module are proposed to obtain the multimodal interaction feature between the image modality and the text modality. Through the attention mechanism and gated fusion mechanism, these two modules realize the auxiliary function of image in the text-based aspect-based sentiment analysis task. Meanwhile, a boundary auxiliary module is used to explore the dependencies between two core subtasks of the aspect-based sentiment analysis. Experimental results on two publicly available multi-modal aspect-based sentiment datasets validate the effectiveness of the proposed approach.

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.

A Pre-Trained Model for Aspect-based Sentiment Analysis Task: using Online Social Networking

Aspect-based sentiment analysis (ABSA) is a crucial part of Natural Language Processing (NLP) that focuses on identifying emotions related to specific elements in written material. ABSA has gained widespread interest due to its ability to provide precise insights into sentiment expressions across different domains. Social media provides a valuable resource for ABSA, containing user-created content with viewpoints and feedback. However, the informal nature of social media text poses challenges for ABSA. This study investigates the performance enhancement of baseline and proposed models in the ABSA task context. Both baseline and proposed models were evaluated for accuracy and F1 score improvements. The results showed that the suggested model performs better than other baseline models, with an improvement of 0.52% F1 score and an overall accuracy increase of 1.16%. However, specific analyses for laptops indicated limitations in the proposed model's performance, with accuracy scores ranging from 72.65% to 84.98%.

Prompted representation joint contrastive learning for aspect-based sentiment analysis

As a fine-grained and challenging subtask in the natural language processing (NLP) community, aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards a given aspect term. In previous ABSA research, most works utilized the pre-trained language model (PLM) as the backbone of their proposed methods, without any specific task-related instructions. Besides, some works focused on learning the dependency information or the external knowledge-enhanced dependency information separately, which lacked the exploitation of the mutual interaction between the normal dependency and knowledge-enhanced dependency. Therefore, we propose a novel ABSA method namely prompted representation joint contrastive learning enhanced graph convolutional networks (PRCL-GCN) to strengthen the robustness of the ABSA model. Specifically, to achieve the task-oriented contextual representation, we design the task-specific prompt template to guide the fine-tuning process of PLM in the ABSA task. And a biaffine attention mechanism is employed to further extract the essential sentiment feature from the prompted representation. Moreover, we introduce the syntax dependency graph as prior knowledge, and construct an affective syntactic dependency graph by injecting the affective knowledge from SenticNet into the graph. Then, we utilize the multi-layer GCNs to process the above two syntactic graphs independently, which aims to learn multi-granularity syntactic features. Subsequently, a novel designed attention variant is leveraged to integrate these syntax features with the guided contextual representation, separately. Eventually, through designing a Kullback–Leibler divergence-based contrastive learning to encourage the model’s learning, we improve the model’s accuracy in modeling contextual representation by integrating the designed dual-ways information. Extensive experiments are conducted on five benchmark datasets, and the outstanding experiment results validate the effectiveness of our proposed model.

IIM: an information interaction mechanism for aspect-based sentiment analysis

ABSTRACT Term polarity co-extraction is an aspect-based sentiment analysis task, which has been widely used in the fields of user opinions extraction. It consists of two subtasks: aspect term extraction and aspect sentiment classification. Most existing studies solve aforesaid subtasks as independent tasks or simply unify the two subtasks without making full use of the relationship between tasks to mine the interaction of text information, which leads to low performance for practical applications. Meanwhile, the learning framework for these studies has a label drift phenomenon (LDP) in the process of predictive learning, increasing the learning error rate. To address the above problems, this study unifies subtasks and proposes a Unified framework based on the information interaction mechanism framework, called IIM. Specifically, we design an Information Interaction Channel (IIC) to construct closer semantic features to extract preliminary term-polarity unified labels from the perspective of basic semantics. For label inconsistency between aspect terms, a Position-aware Module (SAM) is proposed to alleviate the Label Drift Phenomenon (LDP). Moreover, we introduce a syntax-attention graph neural network (Syn-AttGCN) to model the syntactic structure of text and strengthen the emotional connection between aspect terms. The experimental results show that IIM outperforms most baselines. Meanwhile, the SAM module has a certain slowing effect on LDP.

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been attracting considerable interest in the last decade. To handle ABSA in different scenarios, various tasks are introduced for analyzing different sentiment elements and their relations, including the aspect term, aspect category, opinion term, and sentiment polarity. Unlike early ABSA works focusing on a single sentiment element, many compound ABSA tasks involving multiple elements have been studied in recent years for capturing more complete aspect-level sentiment information. However, a systematic review of various ABSA tasks and their corresponding solutions is still lacking, which we aim to fill in this survey. More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks. From the perspective of solutions, we summarize the utilization of pre-trained language models for ABSA, which improved the performance of ABSA to a new stage. Besides, techniques for building more practical ABSA systems in cross-domain/lingual scenarios are discussed. Finally, we review some emerging topics and discuss some open challenges to outlook potential future directions of ABSA.

Prompt template construction by Average Gradient Search with External Knowledge for aspect sentimental analysis

Aspect-based Sentiment Analysis (ABSA) aims to predict the sentiment polarity towards a particular aspect in a sentence. Most of the existing methods construct neural networks or fine-tune the pre-trained language models. However, it is difficult to fully utilize the knowledge of language model learned during pretraining process, and it usually performs worse in few-shot experiment. Prompt learning can alleviate the above problems effectively. Manual prompt template construction methods are adopted usually but it leads to high costs and low efficiency, and there are seldom prompt templates applicable to ABSA task. We propose a method for ABSA prompt template construction, named Average Gradient Search with External Knowledge Based on KNN. The vocabulary list of the pre-trained language model is built as a KD-Tree, and the KNN algorithm is used to search the best prompt template on KD-Tree. For the sentiment polarity prediction, the best prompt template is used to wrap the ABSA data, converting the classification task to generative task, which enables the language model to fully leverage the learned knowledge from the pre-training stage. Moreover, the constructed verbalizer incorporates external knowledge to provide label words of each class with extensive semantic coverage and lower subjective bias. The comparison experimental results on SemEval2014 Restaurant and Laptop datasets demonstrate that the proposed method outperforms the existing SOTA models. Further, the few-shot experimental results indicate that, with only a small number of training samples, the proposed method achieves comparable or even better performance than the baseline model trained on the full dataset.

PSAN: Prompt Semantic Augmented Network for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task. The model is influenced by irrelevant context and complex structure when modeling the relationship between aspect and sentiment expression. Existing studies mainly improve the performance of the ABSA task by fine-tuning the pre-trained language model(PLM) and extracting valid information(e.g., syntax and context). However, these approaches fail to exploit the performance of PLM and ignore the rich semantic knowledge contained in PLM. To alleviate these problems, we propose a Prompt Semantic Augmented Network (PSAN), which improves the performance of ABSA by fine-tuning the PLM and leveraging the semantic knowledge contained in the PLM. Specifically, we propose semantic augmented prompt tuning (SAPT), which obtains a more relevant representation of the task by constructing prompt templates for the input sentences. Meanwhile, we construct corresponding label templates for the prompt templates and use them as the labels of the prompt templates, by which the sentence information containing the real labels is introduced into the model as a prior knowledge. Meanwhile, we use self-attention and graph convolutional networks (GCN) to obtain contextual and syntactic information. And finally, we aggregate these three types of information to perform the ABSA task. Experiments show that our SAPT can improve the performance of the PLM compared to classical fine-tuning, resulting in better results. Our proposed SAPT can obtain richer prompt semantic information than prompt tuning. Experimental results on three public benchmark datasets show that our model outperforms state-of-the-art methods.

Local Dependency-Enhanced Graph Convolutional Network for Aspect-Based Sentiment Analysis

The task of aspect-based sentiment analysis (ABSA) is to detect the sentiment polarity toward given aspects. Contemporary methods predominantly utilize graph neural networks and incorporate attention mechanisms to dynamically connect aspect terms with their surrounding contexts, resulting in more informative feature representations. However, these methods only consider whether there are dependencies between words when introducing dependencies, ignoring that dependencies between different sentiment words have different effects. Neglecting this could introduce noise and negatively impact the model’s performance. To overcome this limitation, we introduce a novel approach called the local dependency-enhanced graph convolutional network (LDEGCN). Our method combines semantic information and dependency relationships to better capture the affective relationships between words. Specifically, we integrate sentiment knowledge from SenticNet to enrich the sentence’s dependency graph and thoroughly explore the dependency types between contexts and aspects to focus on particular dependency types. The local context weight (LCW) method is employed on the dependency-enhanced graph to emphasize the importance of local contexts, thereby mitigating the issue of long-distance dependencies. Through extensive evaluations of five public datasets, the LDEGCN model demonstrates significant improvements over mainstream models.

A Systematic Literature Review on Vietnamese Aspect-based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is one of the principal tasks in the automatic deep understanding of texts, widely applied in a broad range of real-world applications. Many studies have been performed on different tasks and datasets for other languages (e.g., English, Chinese) to address this topic. For Vietnamese language, this topic has been attracting considerable interest in recent years. However, we found that many studies tend to repeat the research instead of inheriting and extending the previous works. Moreover, previous studies’ methods of comparison or evaluation metrics have not shown consistency and connection. This might restrict the development of future studies on this research topic. To the best of our knowledge, no research has been conducted to overview the existing studies for the ABSA research in Vietnamese language. The primary objective of this study is to provide a systematic and comprehensive review of the current Vietnamese ABSA research. More specifically, we analyze the early approaches, evaluation metrics, and available published benchmark datasets used in the Vietnamese ABSA task. We also discuss the challenge and recommend potential future directions for Vietnamese ABSA. This work is expected to provide readers with a wealth of knowledge, the research gap, and the challenges in the Vietnamese ABSA field.