SDEGCN: Syntactic dependency enhanced and integrated graph convolutional network for aspect-based sentiment analysis

Sentiment interaction and multi-graph perception with graph convolutional networks for aspect-based sentiment analysis

With the amount of user-generated information on the Web, identifying the sentiment polarity of the given aspect provides more complete and in-depth results for businesses and customers. Aspect based sentiment analysis has gained increasing attention in decade years, but it remains a daunting task. Recently, approaches based on recurrent neural networks and convolutional neural networks have shown competitive results in this field. However, they don’t take fully account of the entire text structure and the relation between words in a given document. In this paper, we propose a novel neural network method to address this problem, in which the text is treated as a graph and the aspect is the specific area of the graph. For the first time, we apply graph convolutional neural networks and structural attention model to aspect based sentiment analysis. Experiments on public-available datasets demonstrate the efficiency and effectiveness of our model.

Aspect-Based Sentiment Analysis (ABSA) represents a fine-grained approach to sentiment analysis, aiming to pinpoint and evaluate sentiments associated with specific aspects within a text. ABSA encompasses a set of sub-tasks that together facilitate a detailed understanding of the multifaceted sentiment expressions. These tasks include aspect and opinion terms extraction (ATE and OTE), classification of sentiment at the aspect level (ALSC), the coupling of aspect and opinion terms extraction (AOE and AOPE), and the challenging integration of these elements into sentiment triplets (ASTE). Our research introduces a comprehensive framework capable of addressing the entire gamut of ABSA sub-tasks. This framework leverages the contextual strengths of BERT for nuanced language comprehension and employs a biaffine attention mechanism for the precise delineation of word relationships. To address the relational complexity inherent in ABSA, we incorporate a Multi-Layered Enhanced Graph Convolutional Network (MLEGCN) that utilizes advanced linguistic features to refine the model’s interpretive capabilities. We also introduce a systematic refinement approach within MLEGCN to enhance word-pair representations, which leverages the implicit outcomes of aspect and opinion extractions to ascertain the compatibility of word pairs. We conduct extensive experiments on benchmark datasets, where our model significantly outperforms existing approaches. Our contributions establish a new paradigm for sentiment analysis, offering a robust tool for the nuanced extraction of sentiment information across diverse text corpora. This work is anticipated to have significant implications for the advancement of sentiment analysis technology, providing deeper insights into consumer preferences and opinions for a wide range of applications.

In the ever-expanding digital landscape, the abundance of user-generated content on consumer platforms such as Booking and TripAdvisor offers a rich source of information for both travellers and hoteliers. Sentiment analysis, a fundamental research task of natural language processing (NLP) is used for mining sentiments and opinions within this vast reservoir of text reviews. A more specific type of sentiment analysis, i.e., aspect-based sentiment analysis (ABSA), is used when processing customer reviews is required. In ABSA, we aim to capture aspect-level sentiments and intricate relationships between various aspects within reviews. This article proposes a novel approach to ABSA by introducing a novel technique of word sense disambiguation (WSD) and integrating it with the Transformer architecture bidirectional encoder representations from Transformers (BERT) and graph convolutional networks (GCNs). The proposed approach resolves the intriguing ambiguities of the words and represents the review data as a complex graph structure, facilitating the modeling of intricate relationships between different aspects. The combination of bidirectional long short-term memory (BiLSTM) and GCN proves effective in capturing inter-dependencies among various aspects, providing a nuanced understanding of customer sentiments. The experiments are conducted on the RABSA dataset (an enhanced and richer hotel review data collection), and results demonstrate that our approach outperforms previous baselines, showcasing the effectiveness of integrating WSD in ABSA. Furthermore, an ablation study confirms the significant contribution of the WSD module to the overall performance. Moreover, we explore different similarity measures and find that cosine similarity yields the best results when identifying the real sense of a word in a given sentence using WordNet. The findings of our work and future work related to our work create lots of interest for people in the tourism and hospitality industry. This research gives another boost to the concept of the potential of NLP techniques in sentiment analysis. It emphasizes that if we combine the potential of NLP techniques along with state-of-the-art machine learning frameworks, we can shape the future of this field.

Aspect-based sentiment analysis (ABSA) is a task in natural language processing (NLP) that involves predicting the sentiment polarity towards a specific aspect in text. Graph neural networks (GNNs) have been shown to be effective tools for sentiment analysis tasks, but current research often overlooks affective information in the text, leading to irrelevant information being learned for specific aspects. To address this issue, we propose a novel GNN model, MHAKE-GCN, which is based on the graph convolutional neural network (GCN) and multi-head attention (MHA). Our model incorporates external sentiment knowledge into the GCN and fully extracts semantic and syntactic information from a sentence using MHA. By adding weights to sentiment words associated with aspect words, our model can better learn sentiment expressions related to specific aspects. Our model was evaluated on four publicly benchmark datasets and compared against twelve other methods. The results of the experiments demonstrate the effectiveness of the proposed model for the task of aspect-based sentiment analysis.

Aspect-based sentiment analysis (ABSA) aims to mine the sentiment tendencies expressed by specific aspect terms. The studies of ABSA mainly focus on the attention-based approaches and the graph neural network approaches based on dependency trees. However, the attention-based methods usually face difficulties in capturing long-distance syntactic dependencies. Additionally, existing approaches using graph neural networks have not made sufficient exploit the syntactic dependencies among aspects and opinions. In this paper, we propose a novel Syntactic Dependency Graph Convolutional Network (SD-GCN) model for ABSA. We employ the Biaffine Attention to model the sentence syntactic dependencies and build syntactic dependency graphs from aspects and emotional words. This allows our SD-GCN to learn both the semantic relationships of aspects and the overall semantic meaning. According to these graphs, the long-distance syntactic dependency relationships are captured by GCNs, which facilitates SD-GCN to capture the syntactic dependencies between aspects and viewpoints more comprehensively, and consequently yields enhanced aspect features. We conduct extensive experiments on four aspect-level sentiment datasets. The experimental results show that our SD-GCN outperforms other methodologies. Moreover, ablation experiments and visualization of attention further substantiate the effectiveness of SD-GCN.

Enhanced UrduAspectNet: Leveraging Biaffine Attention for superior Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) aims to judge the sentiment polarity of specific aspects in text reviews, and is a fine-grained sentiment analysis task. In the current e-commerce era, ABSA based on user reviews is of great significance to consumers, producers and sellers. In order to make full use of the dependency information in the text, we propose a dependency graph convolutional network model for ABSA. Two graph convolutional networks are used to encode the dependency edge and the dependency tag respectively, and then a biaffine module is used to realize the interaction between the two. The experimental results show that the proposed model outperforms all other comparison models on 8 datasets in Chinese and English, including CMPR, SemEval 2014 Task4, Twitter, etc.

As the amount of user-generated content on the web continues to increase, a great interest has been shown in aspect-level sentiment analysis, which provides more detailed information than general sentiment analysis. In recent years, neural-based models have achieved success in this task because of their powerful representation learning capabilities. However, they ignore that the sentiment polarity of the target is related to the entire text structure. In this paper, we present a method based on graph convolutional neural networks named GCNDA, in which the given text is considered as a graph and the target is the specific region of the graph. Dual graph-based attention models are used to concentrate on the relation between words and certain regions of the graph. We conduct comprehensive experiments on publicly accessible datasets, and results demonstrate that our model outperforms the state-of-the-art baselines.

Sentiment analysis or opinion mining used to capture the community's attitude who have experienced the specific service/product. Sentiment analysis usually concentrates to classify the opinion of whole document or sentence. However, in most comments, users often express their opinions on different aspects of the mentioned entity rather than express general sentiments on entire document. In this case, using aspect-based sentiment analysis (ABSA) is a solution. ABSA emphases on extracting and synthesizing sentiments on particular aspects of entities in opinion text. The previous studies have difficulty working with aspect extraction and sentiment polarity classification in multiple domains of review. We offer an innovative deep learning approach with the integrated construction of bidirectional Long Short Term Memory (BiLSTM) and Convolutional Neural Network (CNN) for multidomain ABSA in this article. Our system finished the following tasks: domain classification, aspect extraction and opinion determination of aspect in the document. Besides applying GloVe word embedding for input sentences from mixed Laptop_Restaurant domain of the SemEval 2016 dataset, we also use the additional layer of POS to pick out the word morphological attributes before feeding to the CNN_BiLSTM architecture to enhance the flexibility and precision of our suggested model. Through experiment, we found that our proposed model has performed the above mentioned tasks of domain classification, aspect and sentiment extraction concurrently on a mixed domain dataset and achieved the positive results compared to previous models that were performed only on separated domain dataset.

Learning graph structure via graph convolutional networks

The automatic identification of disease types of edible mushroom crops and poisonous crops is of great significance for improving crop yield and quality. Based on the graph convolutional neural network theory, this paper constructs a graph convolutional network model for the identification of poisonous crops and edible fungi. By constructing 6 graph convolutional networks with different depths, the model uses the training mechanism of graph convolutional networks to analyze the results of disease identification and completes the automatic extraction of the disease characteristics of the poisonous crops by overfitting problem. During the simulation, firstly, the relevant PlantVillage dataset is used to obtain the pretrained model, and the parameters are adjusted to fit the dataset. The network framework is trained and parameterized with prior knowledge learned from large datasets and finally synthesized by training multiple neural network models and using direct averaging and weighting to synthesize their predictions. The experimental results show that the graph convolutional neural network model that integrates multi-scale category relationships and dense links can use dense connection technology to improve the representation ability and generalization ability of the model, and the accuracy rate generally increases by 1%–10%. The average recognition rate is about 91%, which greatly promotes the ability to identify the diseases of poisonous crops.

Syntax-enhanced aspect-based sentiment analysis with multi-layer attention

Integrating external knowledge into aspect-based sentiment analysis using graph neural network

Lots of research has been done on the domain of Sentiment Analysis, for example, research that conducted by Bing Liu's (2012) [1]. Other research conducted in a SemEval competition, the domain of sentiment analysis research has been developed further up to the aspect or commonly called Aspect Based Sentiment Analysis (ABSA) [2]. The domain problem of Aspect Based Sentiment Analysis (ABSA) from SemEval is quite diverse, all of those problems arise mostly from the real data provided. Some existing problems include Implicit, Multi-label, Out Of Vocabulary (OOV), Expression extraction, and the detection of aspects and polarities. This research only focuses on classification aspect and classification of sentiment. This study uses an existing method of Convolution Neural Network (CNN) method, which was introduced again by Alex K. The study by Alex K reduces the error rate by 15%, compared in the previous year the decrease was only 5%. This research would like to propose CNN methods that have been optimized, and use Threshold (CNN-T) to select the best data in training data. This method can produce more than one aspect using one data test. The average result of this experiment using CNN-T got better F-Measure compared to CNN and 3 classic Machine Learning method, i.e. SVM, Naive Bayes, and KNN. The overall F1 score of CNN-T is 0.71, which is greater than the other comparable methods.