Aspect-based Sentiment Analysis Model Research Articles

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.

Aspect-based sentiment analysis with metaphorical information

Aspect-Based Sentiment Analysis (ABSA) has been the focus of increasing study in recent years. Previous research has demonstrated that incorporating syntactic information, such as dependency trees, can enhance ABSA performance. Despite the widespread use of metaphors in daily life to express emotions more vividly, few studies have integrated this literary device into ABSA. In this paper, we propose a novel ABSA model that utilizes Metaphor Identification Procedure (MIP) to encode both the sentence and aspect word as a single unit, thereby overcoming these limitations. Our experimental results demonstrate that our model achieves competitive performance in ABSA.

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.

A Knowledge-Enhanced and Topic-Guided Domain Adaptation Model for Aspect-based Sentiment Analysis

A Knowledge-Enhanced and Topic-Guided Domain Adaptation Model for Aspect-based Sentiment Analysis

BERT-Based Model for Aspect-Based Sentiment Analysis for Analyzing Arabic Open-Ended Survey Responses: A Case Study

BERT-Based Model for Aspect-Based Sentiment Analysis for Analyzing Arabic Open-Ended Survey Responses: A Case Study

Implementation of IndoNLU Pre-Trained Model for Aspect-Based Sentiment Analysis of Indonesian Stock News

Investors in Indonesia are increasing from year to year, especially mutual fund investors managed by investment managers. News is one of the factors considered by investment managers in making stock investment decisions. Very diverse news sources and different writing styles can make it difficult to retrieve information on each issuer in the news. In this research, the aspect-based sentiment analysis (ABSA) method is implemented to extract news specifically on each aspect (issuer) in the news and evaluate the issuer. The model used is a pre-trained Indonesian Bidirectional Encoder Representations from Transformers (BERT) model, IndoNLU, because the object of research is Indonesian-language stock news. The results show that with a combination of hyperparameters consisting of batch size 8, learning rate 0.00002, and epoch 8 for the IndoNLU model can produce an average evaluation metric value consisting of precision, recall, f1-score, and accuracy of 90%.

A hybrid model for aspect-based sentiment analysis on customer feedback: research on the mobile commerce sector in Vietnam

Feedback and comments on mobile commerce applications are extremely useful and valuable information sources that reflect the quality of products or services to determine whether data is positive or negative and help businesses monitor brand and product sentiment in customers’ feedback and understand customers’ needs. However, the increasing number of comments makes it increasingly difficult to understand customers using manual methods. To solve this problem, this study builds a hybrid research model based on aspect mining and comment classification for aspect-based sentiment analysis (ABSA) to deeply comprehend the customer and their experiences. Based on previous classification results, we first construct a dictionary of positive and negative words in the e-commerce field. Then, the POS tagging technique is applied for word classification in Vietnamese to extract aspects of model commerce related to positive or negative words. The model is implemented with machine and deep learning methods on a corpus comprising more than 1,000,000 customer opinions collected from Vietnam's four largest mobile commerce applications. Experimental results show that the Bi-LSTM method has the highest accuracy with 92.01%; it is selected for the proposed model to analyze the viewpoint of words on real data. The findings are that the proposed hybrid model can be applied to monitor online customer experience in real time, enable administrators to make timely and accurate decisions, and improve the quality of products and services to take a competitive advantage.

Fusing Syntactic Structure Information and Lexical Semantic Information for End-to-End Aspect-Based Sentiment Analysis

The aspect-based sentiment analysis (ABSA) consists of two subtasks-aspect term extraction and aspect sentiment prediction. Most methods conduct the ABSA task by handling the subtasks in a pipeline manner, whereby problems in performance and real application emerge. In this study, we propose an end-to-end ABSA model, namely, SSi-LSi, which fuses the syntactic structure information and the lexical semantic information, to address the limitation that existing end-to-end methods do not fully exploit the text information. Through two network branches, the model extracts syntactic structure information and lexical semantic information, which integrates the part of speech, sememes, and context, respectively. Then, on the basis of an attention mechanism, the model further realizes the fusion of the syntactic structure information and the lexical semantic information to obtain higher quality ABSA results, in which way the text information is fully used. Subsequent experiments demonstrate that the SSi-LSi model has certain advantages in using different text information.

SA-ASBA: a hybrid model for aspect-based sentiment analysis using synthetic attention in pre-trained language BERT model with extreme gradient boosting

SA-ASBA: a hybrid model for aspect-based sentiment analysis using synthetic attention in pre-trained language BERT model with extreme gradient boosting

The Case of Aspect in Sentiment Analysis: Seeking Attention or Co-Dependency?

(1) Background: Aspect-based sentiment analysis (SA) is a natural language processing task, the aim of which is to classify the sentiment associated with a specific aspect of a written text. The performance of SA methods applied to texts related to health and well-being lags behind that of other domains. (2) Methods: In this study, we present an approach to aspect-based SA of drug reviews. Specifically, we analysed signs and symptoms, which were extracted automatically using the Unified Medical Language System. This information was then passed onto the BERT language model, which was extended by two layers to fine-tune the model for aspect-based SA. The interpretability of the model was analysed using an axiomatic attribution method. We performed a correlation analysis between the attribution scores and syntactic dependencies. (3) Results: Our fine-tuned model achieved accuracy of approximately 95% on a well-balanced test set. It outperformed our previous approach, which used syntactic information to guide the operation of a neural network and achieved an accuracy of approximately 82%. (4) Conclusions: We demonstrated that a BERT-based model of SA overcomes the negative bias associated with health-related aspects and closes the performance gap against the state-of-the-art in other domains.

Complete quadruple extraction using a two-stage neural model for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) is a fine-grained task which aims to identify the emotional polarity of a specific aspect in a text or sentence. Aspect term extraction (ATE), opinion term extraction (OTE) and aspect polarity classification (APC) are three main subtasks of the ABSA task. Nowadays, researchers mainly focus on a single task or a joint task composed of these three subtasks, and such investigation on the sentiment analysis is not sufficient. In this paper, we firstly introduce a complete aspect sentiment analysis task, called Aspect Sentiment Quadruple Extraction, which also includes the category detection beside ATE, OTE and APC. Then we propose a two-stage neural network model composed of several modules, including BiLSTM, simple gated self-attention and position encoding for this joint task. In the first stage, the proposed model extracts aspect and opinion terms as well as their categories and polarities. Moreover, the second stage mainly includes a relation classifier to validate the aspect-opinion pairs and then finalizes the complete quadruple extraction. The experimental results, evaluated on a benchmark dataset of Chinese product reviews, show that our proposed model outperforms other baseline methods and achieves the start-of-art performance.

Aspect-based sentiment analysis with graph convolution over syntactic dependencies

Aspect-based sentiment analysis is a natural language processing task whose aim is to automatically classify the sentiment associated with a specific aspect of a written text. In this study, we propose a novel model for aspect-based sentiment analysis, which exploits the dependency parse tree of a sentence using graph convolution to classify the sentiment of a given aspect. To evaluate this model in the domain of health and well-being, where this task is biased toward negative sentiment, we used a corpus of drug reviews. Specific aspects were grounded in the Unified Medical Language System, a large repository of inter-related biomedical concepts and the corresponding terminology. Our experiments demonstrated that graph convolution approach outperforms standard deep learning architectures on the task of aspect-based sentiment analysis. Moreover, graph convolution over dependency parse trees (F-score of 0.8179) outperforms the same approach over a flat sequence representation of sentences (F-score of 0.7332). These results bring the performance of sentiment analysis in health and well-being in line with the state of the art in other domains.

An Efficient Aspect based Sentiment Analysis Model by the Hybrid Fusion of Speech and Text Aspects

Aspect-based Sentiment Analysis (ABSA) is treated to be a challenging task in the domain of speech, as it needs the fusion of acoustic features and Linguistic features for information retrieval and decision making. The existing studies in speech are limited to speech and emotion recognition. The main objective of this work is to combine acoustic features in speech with linguistic features in text for ABSA. A deep learning and language model is implemented for acoustic feature extraction in speech. Different variants of text feature extraction techniques are used for aspect extraction in text. Trained Lexicons, Latent Dirichlet Allocation (LDA) model, Rule based approach and Efficient Named Entity Recognition (E-NER) guided dependency parsing approach has been used for aspect extraction. Sentiment with respect to the extracted aspect is analyzed using Natural Language Processing (NLP) techniques. The experimental results of the proposed model proved the effectiveness of hybrid level fusion by yielding improved results of 5.7% WER and 3% CER when compared with the traditional baseline individual linguistic and acoustic feature models.

Combination of Convolutional Neural Network and Gated Recurrent Unit for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) aims to identify views and sentiment polarities towards a given aspect in reviews. Compared with general sentiment analysis, ABSA can provide more detailed and complete information. Recently, ABSA has become an important task for natural language understanding and has attracted considerable attention from both academic and industry fields. The sentiment polarity of a sentence is not only decided by its content but also has a relatively significant correlation with the targeted aspect. For this reason, we propose a model for aspect-based sentiment analysis which is a combination of Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU), utilizing the local features generated by CNN and the long-term dependency learned by GRU. Extensive experiments have been conducted on datasets of hotels and cars, and results show that the proposed model achieves excellent performance in terms of aspect extraction and sentiment classification. Experiments also demonstrate the great domain expansion capability of the model.

Multifeature Interactive Fusion Model for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis technology. In recent years, neural networks are widely used to extract features of aspects and contexts and proven to have a dramatic improvement in retrieving the sentiment feature from comments. However, due to the increasing complexity of comment information, only considering sentence or word features, respectively, may cause the loss of key text information. Besides, characters have more microscopic features, so the fusion of features between three different levels, such as sentences, words, and characters, should be taken into consideration for exploring their internal relationship among different granularities. According to the above analysis, we propose a multifeature interactive fusion model for aspect-based sentiment analysis. Firstly, the text is divided into two parts: contexts and aspects; then word embedding and character embedding are associated to further explore the potential features. Secondly, to establish a close relationship between contexts and aspects, features fusion of both aspects and contexts are exploited in our model. Moreover, we apply the attention mechanism to calculate fusion weight of features, so that the key features information plays a more significant role in the sentiment analysis. Finally, we experimented on the three datasets of SemEval2014. The results of experiment showed that our model has a better performance compared with the baseline models.

Towards a sentiment analysis model based on semantic relation analysis

In this paper, we propose an effective model for aspect-based sentiment analysis. First, we combined a sentiment dictionary and syntactic dependency rules to extract reliable word pairs (sentiment — aspect). Then, thanks to ontology, we grouped those aspects and determined the sentiment polarity of each. When we conducted experiments on real reviews, the system showed positive results.

Integrating word status for joint detection of sentiment and aspect in reviews

A crucial task in sentiment analysis is aspect detection: the step of selecting the aspects on which opinions are expressed. This step anticipates the step of determining whether the opinions on aspects are positive or negative. This article proposes a novel probabilistic generative topic model for aspect-based sentiment analysis which is able to discover the latent structure of a large collection of review documents. The proposed joint sentiment-aspect detection model (SAM) is a generative topic model that incorporates the structure of review sentences for detecting aspects and sentiments simultaneously. The intuitions behind the SAM are that from generating documents by latent single- and multi-word topics, modelling the word distribution for each topic and learning of the prior distribution over topics in sentences of documents. SAM introduces word status so that the model can decide when to sample from a bigram distribution or a unigram distribution and integrates all these components into one combined model for aspect-based sentiment analysis. We evaluate SAM both qualitatively and quantitatively to show that the model is indeed able to perform the task effectively and improves significantly over standard joint sentiment-aspect models. The proposed model can easily be transformed between domains or languages and can detect the polarity of text data at various levels. However, for the quantitative analysis, we mainly focus on presenting the results for the document-level sentiment classification.

Towards a Sentiment Analysis Model Based on Semantic Relation Analysis

Sentiment analysis is an important new field of research that has attracted the attention not only of researchers, but also businesses and organizations. In this article, the authors propose an effective model for aspect-based sentiment analysis for Vietnamese. First, sentiment dictionaries and syntactic dependency rules were combined to extract reliable word pairs (sentiment - aspect). They then relied on ontology to group these aspects and determine the sentiment polarity of each. They introduce two novel approaches in this work: 1) in order to “smooth” the sentiment scaling (rather than using discrete categories of 1, 0, and -1) for fined-grained classification, then extract multi-word sentiment phrases instead of sentiment words, and 2) the focus is not only on adjectives but also nouns and verbs. Initial evaluations of the system using real reviews show promising results.