Aspect Sentiment Classification Research Articles

Neural multi-task learning for end-to-end Arabic aspect-based sentiment analysis

Most existing aspect-based sentiment analysis (ABSA) methods perform the tasks of aspect extraction and sentiment classification independently, assuming that the aspect terms are already determined when handling the aspect sentiment classification task. However, such settings are neither practical nor appropriate in real-life applications, as aspects must be extracted prior to sentiment classification. This study aims to overcome this shortcoming by jointly identifying aspect terms and the corresponding sentiments using a multi-task learning approach based on a unified tagging scheme. The proposed model uses the Bidirectional Encoder Representations from Transformers (BERT) model to produce the input representations, followed by a Bidirectional Gated Recurrent Unit (BiGRU) layer for further contextual and semantic coding. An attention layer is added on top of BiGRU to force the model to focus on the important parts of the sentence. Finally, a Conditional Random Fields (CRF) layer is used to handle inter-label dependencies. Experiments conducted on a reference Arabic hotel dataset show that the proposed model significantly outperforms the baseline and related work models.

Aspect category sentiment analysis based on multiple attention mechanisms and pre-trained models

Aspect category sentiment analysis based on multiple attention mechanisms and pre-trained models

Aspect-Level Sentiment Analysis of Customer Reviews Based on Neural Multi-task Learning

In the era of big data, major e-commerce platforms are facing the challenge of an exponential growth in the number of user comments. Effectively utilizing these comments has become an urgent issue. Traditional manual statistical methods are no longer able to meet the demands for accuracy and real-time analysis. The rise of artificial intelligence-based text mining techniques provides a new approach to address this problem. By building deep learning analysis models, it is possible to uncover user preferences and product characteristics, helping businesses proactively adjust sales strategies, improve product and service quality, and achieve precise marketing. Text sentiment analysis is one of the important research directions in the field of text mining. Its basic idea is to transform subjective texts with emotional color into structured data, and then use machine learning, deep learning, and other artificial intelligence technologies to extract emotional features and discover knowledge patterns. This article proposes a deep learning-based sentiment analysis model, which includes a shared sentiment prediction layer used to transfer emotional knowledge between different aspect categories and alleviate the problem of insufficient data. The model consists of two parts: the Aspect Category Detection (ACD) classifier based on attention mechanism and the Aspect Category Sentiment Analysis (ACSA) classifier. The ACD part generates word weights using attention mechanism, while the ACSA part predicts the sentiment of words and combines weights to determine the sentiment of aspect categories within sentences.

MACSA: A multimodal aspect-category sentiment analysis dataset with multimodal fine-grained aligned annotations

MACSA: A multimodal aspect-category sentiment analysis dataset with multimodal fine-grained aligned annotations

A novel self-supervised contrastive learning based sentence-level attribute induction method for online satisfaction evaluation

Satisfaction evaluation provides valuable support for procurement decisions and product improvement on e-commerce platforms. As an important task of satisfaction evaluation, attribute induction is essential to identify relevant aspects and demands of user-generated evaluations. However, previous methods have often directly predicted typical attributes using individual words, neglecting valuable sentence-level information that could significantly enhance effectiveness. To alleviate this issue, this article introduces the concept of representations of potential attributes (PARs) to explicitly capture sentence-level information regarding product attributes in customer reviews. It further develops a novel self-supervised contrastive learning based sentence-level attribute induction method (SSCL-SAI) to train these PARs. Recognizing that sentences are the basic units of human expression, this approach mitigates information loss. Then, an aspect-category sentiment analysis model is used to transform the unstructured online textual reviews into linguistic 2-tuple for obtaining final satisfaction evaluation result. These 2-tuples provide a representation of sentiment orientations on a continuous numerical scale, enabling precise linguistic operations. Afterwards, an illustrative example conducted on real-world laptop product satisfaction analysis testify the validity of the approach. Finally, the comparative analysis shows the effectiveness of the proposed SSCL-SAI, and experiments on the impact of hyperparameter settings demonstrate that SSCL-SAI can be applied in various scenarios.

CAT: Continual Adapter Tuning for aspect sentiment classification

Humans can continually acquire, improve, and transfer knowledge throughout their lifespan so that they can accurately identify sentiment polarities of the data attributed to different domains. However, the continual learning of incrementally available aspect sentiment classification (ASC) tasks from different domains with non-stationary data distributions remains a long-standing challenge for learning-based models due to the catastrophic forgetting problem, which is the tendency to completely and abruptly forget previously learned knowledge upon learning new knowledge. In this work, we present Continual Adapter Tuning (CAT), a parameter-efficient framework that not only avoids catastrophic forgetting but also enables knowledge transfer from learned ASC tasks to new ASC tasks. To avoid catastrophic forgetting, we only learn and store a task-specific adapter for each ASC task while freezing the backbone pre-trained model. To promote new task learning, we propose a continual adapter initialization technique to transfer knowledge from preceding tasks. Besides, we also develop a novel label-aware contrastive learning to simultaneously learn the features of input samples and the parameters of classifiers in the same space so that we can efficiently classify a sample with the help of label semantics. To eliminate the need for task IDs in testing, we propose a simple yet efficient majority sentiment polarity voting strategy to obtain final sentiment polarities according to the polarities predicted by all reasoning paths in the adapter architecture. Experimental results show the high effectiveness of our CAT by achieving new state-of-the-art performance.

Metric-Free Learning Network with Dual Relations Propagation for Few-Shot Aspect Category Sentiment Analysis

Abstract Few-shot Aspect Category Sentiment Analysis (ACSA) is a crucial task for aspect-based sentiment analysis, which aims to detect sentiment polarity for a given aspect category in a sentence with limited data. However, few-shot learning methods focus on distance metrics between the query and support sets to classify queries, heavily relying on aspect distributions in the embedding space. Thus, they suffer from overlapping distributions of aspect embeddings caused by irrelevant sentiment noise among sentences with multiple sentiment aspects, leading to misclassifications. To solve the above issues, we propose a metric-free method for few-shot ACSA, which models the associated relations among the aspects of support and query sentences by Dual Relations Propagation (DRP), addressing the passive effect of overlapping distributions. Specifically, DRP uses the dual relations (similarity and diversity) among the aspects of support and query sentences to explore intra-cluster commonality and inter-cluster uniqueness for alleviating sentiment noise and enhancing aspect features. Additionally, the dual relations are transformed from support-query to class-query to promote query inference by learning class knowledge. Experiments show that we achieve convincing performance on few-shot ACSA, especially an average improvement of 2.93% accuracy and 2.10% F1 score in the 3-way 1-shot setting.

Multi-modal online review driven product improvement design based on scientific effects knowledge graph

Online reviews serve as significant channels for users to express their preferences, constituting an essential data source for enterprises to identify product requirements. However, with the widespread adoption of smartphones, the act of capturing spontaneous photographs has become a habitual practice for the majority, resulting in the increasing prevalence of supplementary visual expressions within online reviews. Therefore, an important research question emerges: How can product requirements be effectively extracted from multimodal online reviews and subsequently translated into product design proposals? In this paper, we establish a framework, seamlessly integrating aspect-based sentiment analysis, product requirement identification, and requirement mapping based on a scientific effect knowledge graph. Firstly, we conduct aspect term extraction on the online reviews, followed by aspect sentiment classification. Subsequently, we delve deeper into the analyzed results obtained from aspect-based sentiment analysis to identify preferences in product requirements. Finally, we employ requirement mapping based on a scientific effect knowledge graph to generate proposals for product design improvements. To validate the efficacy of our approach, we conducted experiments and the results demonstrate that our method outperforms alternative approaches, while the requirement mapping based on a scientific effect knowledge graph efficiently facilitates the realisation of product design improvements.

A Model of Continual and Deep Learning for Aspect Based in Sentiment Analysis

Sentiment Analysis is a useful tool in several social and business contexts. Aspect Sentiment Classification is a subtask in Sentiment Analysis that gives information about features or aspects of people, entities, products, or services present in reviews. Different Deep Learning models have been proposed to solve Aspect Sentiment Classification focus on a specific domain such as restaurant,hotel, or laptop reviews. However, there are few proposals for creating a single model with high performance in multiple domains. The Continual Learning approach with neural networks has been used to solve aspect classification in multiple domains. However, avoid low aspect classification performance in Continual Learning is challenging. As a consequence, potential neural networkweight shifts in the learning process in different domains or datasets.In this paper, a novel Aspect Sentiment Classification approach is proposed. Our approach combines a Transformer Deep Learning technique with a Continual Learning algorithm in different domains. The input layer used is the pre‐trained model Bidirectional Encoder Representations from Transformers. The experiments show the efficacy of our proposal with 78 .

A Model of Continual and Deep Learning for Aspect Based in Sentiment Analysis

Sentiment Analysis is a useful tool in several social and business contexts. Aspect Sentiment Classification is a subtask in Sentiment Analysis that gives information about features or aspects of people, entities, products, or services present in reviews. Different Deep Learning models have been proposed to solve Aspect Sentiment Classification focus on a specific domain such as restaurant,hotel, or laptop reviews. However, there are few proposals for creating a single model with high performance in multiple domains. The Continual Learning approach with neural networks has been used to solve aspect classification in multiple domains. However, avoid low aspect classification performance in Continual Learning is challenging. As a consequence, potential neural networkweight shifts in the learning process in different domains or datasets.In this paper, a novel Aspect Sentiment Classification approach is proposed. Our approach combines a Transformer Deep Learning technique with a Continual Learning algorithm in different domains. The input layer used is the pre‐trained model Bidirectional Encoder Representations from Transformers. The experiments show the efficacy of our proposal with 78 .

Knowledge-enhanced graph convolutional networks for Arabic aspect sentiment classification

Knowledge-enhanced graph convolutional networks for Arabic aspect sentiment classification

An interactive multi-head self-attention capsule network model for aspect sentiment classification

An interactive multi-head self-attention capsule network model for aspect sentiment classification

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.

Detection of Aspect Category and Aspect-Based Sentiment Analysis on Restaurant Customers' Feedbacks

Günümüzde tüketicilerin ürün ve hizmetler konusunda fikir paylaşabilecekleri birçok mecra bulunmaktadır. Bu fikirler, geri bildirimin yapısı itibariyle genellikle metin formatındadır. Duygu analizi, metin tabanlı bilgi kaynaklarında son yıllarda önem kazanan bir konudur. Daha hassas bir duygu analiz türü olan Hedef Tabanlı Duygu Analizi bir cümle içerisinde hedef terim, hedef kategori ve duygu sınıfının belirlenmesi işidir. Bu çalışmada Semeval ABSA yarışmasında yarışmacılara sunulan restoran müşterilerine ait yorumlardan oluşan bir veri seti kullanılmıştır. Word2vec, Glove, Fastext ve Bert yöntemleri kullanılarak veri seti üzerinde hedef terim, hedef kategori ve duygu sınıfının belirlenmesi işlemi gerçekleştirilmiştir. Kelimeyi vektörü ile cümle vektörünün birleştirilmesi ABSA için sınıflandırma başarısını artırıp artıramayacağı hipotezi test edilmiştir. Dört farklı vektör yöntemi ile yapılan sınıflandırmada hedef terim için 0,78 F1 skoru ile Fasttext yöntemi, hedef kategori için 0,57 F1 skoru ile Fasttext ve duygu sınıfı için 0,76 F1 skoru ile Bert yöntemi en başarılı sonuçları vermiştir. Bu sonuçlar literatürde farklı veri setleri ve farklı diller için yapılan çalışmalarla kıyaslanmıştır. Sonuç olarak Fasttext ve Bert temsil yöntemlerinin hedef tabanlı Türkçe dilindeki metinlerin duygu analizinde başarılı sonuçlar verdiği tespit edilmiştir.

Aspect category sentiment analysis based on prompt-based learning with attention mechanism

Aspect category sentiment analysis (ACSA) excels at identifying the aspect categories and corresponding sentiments involved in a sentence, regardless of whether the aspect terms are explicitly mentioned or not. However, current methods tend to overinflate the original data, resulting in the introduction of unnecessary information, and fail to capture the inter-task relationship sufficiently. This paper presents a new method termed the prompt-based joint model (PBJM) to address these complications. PBJM treats the sentiment polarity prediction as binary classification and leverages a natural language prompt template, a concise sentence that guides the model to perform aspect category identification subtask and curtails the need for data augmentation. The two subtasks are jointly trained in pre-trained language models (PLMs) to capture their correlation. Further, the attention mechanism for aspect categories enables the model to concentrate selectively on significant features such as phrases and words during the predictions. In addition, the verbalizer employs a set of parameters to balance the weight of each label word while projecting between the label space and the label words space. Through experiments on four datasets, our model demonstrated remarkable performance in detecting category-sentiment pairs.

An Interactive Learning Network That Maintains Sentiment Consistency in End-to-End Aspect-Based Sentiment Analysis

Most of the aspect-based sentiment analysis research completes the two subtasks (aspect terms extraction and aspect sentiment classification) separately, and it cannot see the full picture and actual effect of the complete aspect-based sentiment analysis. The purpose of end-to-end aspect-based sentiment analysis is to complete the two subtasks of aspect terms extraction and aspect sentiment classification at the same time, and the current research in this area focuses on the connection between the two subtasks and uses the connection between them to construct the model. However, they rarely pay attention to the connection between different aspects and ignore the sentiment inconsistency within the aspects caused by the end-to-end model. Therefore, we propose an interactive learning network to maintain sentiment consistency, first using the multi-head attention mechanism to achieve the interaction between aspects and subtasks and then using the gate mechanism to design an auxiliary module to maintain sentiment consistency within aspect items. The experimental results on the datasets Laptop14, Restaurant14, and Twitter showed that, compared with the optimal benchmark method, the F1 values of the proposed method increased by 0.4%, 1.21%, and 5.22%, respectively. This indicates that the proposed method can effectively consider the relationships between aspect items and maintain emotional consistency within the aspect items.

An efficient multiple-word embedding-based cross-domain feature extraction and aspect sentiment classification

As the size of the feature space and data size increases, it is difficult to find the essential key features for cross-domain classification problems. Traditional word embedding and feature selection models use limited-sized data and dimensions for feature ranking and classification processes. To overcome these challenges, a hybrid cross-domain classification (CDC) based feature selection has been proposed to improve the efficiency of aspect sentiment classification on large databases. Initially, the crawled data from the Amazon product dataset to the cloud web server. In the data filtering approach, each record is pre-processed for the noise removal process. In the CNN framework, the different word-embedded models are used to ensemble the features from the training data. Here, TF-ID+Word2Vec, Hybrid Glove, and Skipgram are used to select the relevant key features from the training data. On the local side, remote IoT-based devices data distributed processing. For in-depth analysis of the sentiments IOT sensors have been used for automation. The filtered key features are given to the proposed feature extraction measure to select the essential features for the cross-domain classification model, it classifies the positive or negative. The proposed CDC model achieves overall precision and recall is 0.96 and 0.97 respectively. Experimental results proved that the proposed cross-domain feature selection-based classification approach has a better overall true positive than the conventional approaches.

A Self-Attention-Based Multi-Level Fusion Network for Aspect Category Sentiment Analysis

A Self-Attention-Based Multi-Level Fusion Network for Aspect Category Sentiment Analysis

An aspect sentiment classification model for graph attention networks incorporating syntactic, semantic, and knowledge

Aspect sentiment classification tasks aim to identify the aspect in a sentence and express the sentiment polarities of the aspect. In existing studies, combining different deep learning models has achieved good results in aspectual sentiment classification tasks; however, problems such as complex syntactic parsing relationships, insensitivity to syntactic structure information and lack of exploitation of external sentiment knowledge. We propose a graph attention network (SSK-GAT) model incorporating syntactic, semantic and knowledge that considers reshaped syntactic dependencies, multi-head self-attention to capture semantic information of context and introduction of an emotion knowledge base to enhance aspect-related emotional information. In previous studies, aspect and context were modeled separately. Hence, to enhance the representation of sentiment between the aspect and contexts, we use the interactive modeling of aspect and context at the output layer to obtain deeper information through mutual learning. Our SSK-GAT model improved on three publicly available datasets compared to the baseline approaches.

BERT-PG: a two-branch associative feature gated filtering network for aspect sentiment classification

Aspect sentiment classification is an important branch of sentiment classification that has gained increasing attention recently. Existing aspect sentiment classification methods typically use different network branches to encode context and aspect words separately, and then use an attention mechanism to capture their associations. This attention-based approach cannot completely ignore the contexts unrelated to the current aspect words, which brings noise interference. In this paper, a gated filtering network based on BERT is suggested as a solution to this issue. We employ BERT to encode the text semantics of contexts and sentence pairs consisting of context and aspect words respectively, and to extract lexical features as well as associative features of context and aspect words. Based on this, we designed a gating module that, unlike the attention mechanism, uses association features to precisely filter irrelevant contexts. Additionally, because the BERT network parameters are so big, there is a tendency to over-fitting during training. To effectively combat this problem, we developed a loss function with a threshold. We carried out extensive experiments using three benchmark datasets to verify the performance of our proposed model. The experimental results show that the method improves the accuracy by 0.5%, 1.39% and 2.57% on the Laptop, Restaurant and Twitter datasets respectively, and 1.564%, 2.36% and 4.144% on Macro-F1 respectively, compared to the recent RA-CNN (BERT), proving that our method is effective in improving the presentation of aspect sentiment classification in comparison to other cutting-edge sentiment classification methods.