Aspect Term Extraction Research Articles

Fusing semantic and syntactic information for aspect sentiment triplet extraction

Aspect Sentiment Triplet Extraction (ASTE) aims to extract aspect terms, sentiment polarity and opinion terms explaining the reason for the sentiment from a sentence in the form of triplets. Many existing studies model the context by graph neural networks to learn relevant information from the generated graphs. However, some sentences may have syntactic errors or lack significant grammar, which may lead to poor results on the dataset of the model. In this paper, we propose the Fusing Semantic and Syntactic Information for Aspect Sentiment Triplet Extraction (FSSI) model, which incorporates both syntactic structure and semantic relevance in the context. Specifically, we construct a syntactic graph convolutional network to obtain comprehensive syntactic structure information and a semantic graph convolutional network to obtain global semantic relevance of sentences using the self-attention mechanism. Furthermore, we concatenate the graph representations generated by the two graph convolution networks to obtain the final enhanced representation. Finally, we apply an effective inference strategy to extract triplets. Extensive experimental results on benchmark datasets show that our model outperforms state-of-the-art approaches.

Optimizing Aspect Term Extraction and Sentiment Classification through Attention Mechanism and Sparse Attention Techniques

Optimizing Aspect Term Extraction and Sentiment Classification through Attention Mechanism and Sparse Attention Techniques

Aspect Based Feature Extraction in Sentiment Analysis using Bi-GRU-LSTM Model

In Natural Language Processing (NLP), Sentiment Analysis (SA) is a fundamental process which predicts the sentiment expressed in sentences. In contrast to conventional sentiment analysis, Aspect-Based Sentiment Analysis (ABSA) employs a more nuanced approach to assess the sentiment of individual aspects or components within a document or sentence. Its objective is to identify the sentiment polarity, such as positive, neutral, or negative, associated with particular elements disclosed within a sentence. This research introduces a novel sentiment analysis technique that proves to be more efficient in sentiment analysis compared to current methods. The suggested sentiment analysis method undergoes three key phases: 1. Pre-processing 2. Extraction of aspect sentiment and 3. Sentiment analysis classification. The input text data undergoes pre-processing through the implementation of four typical text normalization techniques, which include stemming, stop word elimination, lemmatization, and tokenization. By employing these methods, the provided text data is prepared and fed into the aspect sentiment extraction phase. During the aspect sentiment extraction phase, features are obtained through a series of steps, including enhanced ATE (Aspect Term Extraction), assessment of word length, and determination of cosine similarity. By following these steps, the relevant features are extracted on the basis of aspects and sentiments involved in the text data. Further, a hybrid classification model is proposed to classify sentiments. In this work, two of the Deep Learning (DL) classifiers, Bi-directional Gated Recurrent Unit (Bi-GRU) and Long Short-Term memory (LSTM) are used in proposing a hybrid classification model which classifies the sentiments effectively and provides accurate final predicted results. Moreover, the performance of proposed sentiment analysis technique is analyzed experimentally to show its efficacy over other models.

Hybrid HAN‐CNN with aspect term extraction for sentiment analysis using product review

AbstractIn this article, an intensive sentiment analysis approach termed Hierarchical attention‐convolutional neural network (HAN‐CNN) has been proposed using product reviews. Firstly, the input product review is subjected to Bidirectional Encoder Representation from Transformers (BERT) tokenization, where the input data of each sentence are partitioned into little bits of words. Thereafter, Aspect Term Extraction (ATE) is carried out and feature extraction is completed utilizing some features. Finally, sentiment analysis is accomplished by the developed HAN‐CNN, which is formed by combining a Hierarchical Attention Network (HAN) and a Convolutional Neural Network (CNN). Moreover, the proposed HAN‐CNN achieved a greater performance with maximum accuracy, recall and F1‐Score of 91.70%, 90.60% and 91.20%, respectively.

Knowledge complementation based dual-table filling approach for aspect sentiment triplet extraction

Aspect Sentiment Triplet Extraction (ASTE) task aims to extract aspect terms, opinion terms, and the corresponding sentiment polarity of aspect-opinion pairs from review sentences. Current outperforming table-filling approaches focus on enhancing the relation representation within a single table, with various algorithms designed to exploit deeper information and additional knowledge. However, due to the sequential execution of these algorithms on a single table, the granularity of the knowledge evolves unidirectionally, inevitably leading to the loss of knowledge at different granularities from the previous stage of the entire process. To overcome this limitation, we propose a simple yet effective end-to-end model for the ASTE task, namely Dual-Table Filling (DTF), which constructs two complementary tables instead of just one to capture different granularities of knowledge in a sentence. Specifically, the main table exploits latent knowledge and hidden dependencies, while the assistant table captures more fine-grained contextual knowledge. This structure allows the model to utilize knowledge at multiple granularities more efficiently while maintaining simplicity. In addition, a Syntactic Enhanced Encoder (SEE) is developed to acquire syntactic-enhanced knowledge from sentences, enhancing the comprehension of sentence structure and word relationships. Experimental results on public benchmark datasets show the effectiveness and exceptional performance of our proposed model.

Aspect-based sentiment analysis: A dual-task learning architecture using imbalanced maximized-area under the curve proximate support vector machine and reinforcement learning

Aspect-based sentiment analysis (ABSA) deals with understanding sentiments about specific attributes. Aspect term extraction (ATE) plays an essential role in aspect sentiment classification (ASC) by specifying the main aspects for sentiment accuracy. This paper introduces a dual-task framework for ATE and ASC models in which, the ATE model uses the imbalanced maximized-area under the curve proximate support vector machine (ImAUC-PSVM) method to mitigate the imbalance problem and the output of ATE serves as the reward in the training process of ASC supported by RL (reinforcement learning). The ImAUC-PSVM uses the conventional PSVM (proximate support vector machine) strength for sentiment tasks and the AUC (area under the curve) optimization for imbalance addressing. The ASC model employs multiple kernels for word embedding, with a transductive long short-term memory (TLSTM) for sentence representation that considers samples near the test point for better model refinement. The policy of the RL-based training strategy of the ASC model is represented by a multilayer perceptron (MLP) that categorizes sentences into positive, negative and neutral sentiments. In this RL context, aspect terms serve as rewards in the training process. The scope loss function (SLF) is also integrated within RL to rectify dataset imbalances. To optimize ATE and ASC models, an artificial bee colony (ABC) technique is incorporated for hyperparameter optimization. Experiments and evaluations conducted on English (Restaurant and Laptop) and Hindi datasets show the superiority of the proposed model over existing models of the literature. Moreover, transfer learning (TL) is applied to a Twitter dataset to assess its effect on ATE. The F-measures of the ATE model are obtained as 90.12 and 84.10 and the accuracies of the ASC model are calculated as 84.10 and 82.02 on Restaurant and Laptop datasets, respectively.

Retraction notice: Sentiment analysis in aspect term extraction for mobile phone tweets using machine learning techniques

Retraction notice: Sentiment analysis in aspect term extraction for mobile phone tweets using machine learning techniques

MCPL: Multi-model co-guided progressive learning for multimodal aspect-based sentiment analysis

Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to combine image and text information to extract aspect terms from sentences and predict aspect-based sentiment polarities. Previous joint approaches have either viewed this task as collapsed label sequence annotation or modelled each subtask as a unified index sequence generation task, overlooking the explicit relation among its subtasks. This type of method cannot effectively integrate the strengths of task-specific models and adapt to difficult joint prediction tasks. To address this problem, we propose a Multi-model Co-guided Progressive Learning (MCPL) strategy that leverages task-specific models and the correlations among downstream tasks to expand high-quality training datasets, and provides progressive supervision signals to enhance the model’s ability to adapt from simple to difficult tasks. Based on MCPL, we construct a Phase-wise Progressive Learning (PPL) module for MABSA, in which three Task Affinity-based Pseudo-label Generation (TAPG) modules are proposed for task-specific label expansion. The TAPG modules leverage the task correlations among three MABSA downstream tasks for co-guided teaching, and the PPL module utilises their gradual relationship from aspect term extraction to perform sentiment classification and then joint prediction for progressive learning. Experiments on widely used public datasets demonstrate that the proposed MCPL method achieves excellent performance on the three subtasks of MABSA and outperforms most state-of-the-art methods. The source code is publicly available at https://github.com/qujiaqi-babu/MCPL.

Sentiment analysis in aspect term extraction for mobile phone tweets using machine learning techniques

PurposeThis paper aims to focus on extracting aspect terms on mobile phone (iPhone and Samsung) tweets using NLTK techniques on multiple aspect extraction is one of the challenges. Then, also machine learning techniques are used that can be trained on supervised strategies to predict and classify sentiment present in mobile phone tweets. This paper also presents the proposed architecture for the extraction of aspect terms and sentiment polarity from customer tweets.Design/methodology/approachIn the aspect-based sentiment analysis aspect, term extraction is one of the key challenges where different aspects are extracted from online user-generated content. This study focuses on customer tweets/reviews on different mobile products which is an important form of opinionated content by looking at different aspects. Different deep learning techniques are used to extract all aspects from customer tweets which are extracted using Twitter API.FindingsThe comparison of the results with traditional machine learning methods such as random forest algorithm, K-nearest neighbour and support vector machine using two data sets iPhone tweets and Samsung tweets have been presented for better accuracy.Originality/valueIn this paper, the authors have focused on extracting aspect terms on mobile phone (iPhone and Samsung) tweets using NLTK techniques on multi-aspect extraction is one of the challenges. Then, also machine learning techniques are used that can be trained on supervised strategies to predict and classify sentiment present in mobile phone tweets. This paper also presents the proposed architecture for the extraction of aspect terms and sentiment polarity from customer tweets.

A Knowledge-Driven Approach for Automatic Semantic Aspect Term Extraction Using the Semantic Power of Linked Open Data

Aspect-Based Sentiment Analysis (ABSA) is a crucial process for assessing customer feedback and gauging satisfaction with products or services. It typically consists of three stages: Aspect Term Extraction (ATE), Aspect Categorization Extraction (ACE), and Sentiment Analysis (SA). Various techniques have been proposed for ATE, including unsupervised, supervised, and hybrid methods. However, many studies face challenges in detecting aspect terms due to reliance on training data, which may not cover all multiple aspect terms and relate semantic aspect terms effectively. This study presents a knowledge-driven approach to automatic semantic aspect term extraction from customer feedback using Linked Open Data (LOD) to enrich aspect extraction outcomes in the training dataset. Additionally, it utilizes the N-gram model to capture complex text patterns and relationships, facilitating accurate classification and analysis of multiple-word terms for each aspect. To assess the effectiveness of the proposed model, experiments were conducted on three benchmark datasets: SemEval 2014, 2015, and 2016. Comparative evaluations with contemporary unsupervised, supervised, and hybrid methods on these datasets yielded F-measures of 0.80, 0.76, and 0.77, respectively.

Aspect term extraction from multi-source domain using enhanced latent Dirichlet allocation

This study presents a comprehensive exploration of sentiment analysis across diverse domains through the introduction of a multi-source domain dataset encompassing hospitals, laptops, restaurants, cell phones, and electronics. Leveraging this extensive dataset, an enhanced latent Dirichlet allocation (E-LDA) model is proposed for topic modeling and aspect extraction, demonstrating superior performance with a remarkable coherence score of 0.5727. Comparative analyses with traditional LDA and other existing models showcase the efficacy of E-LDA in capturing sentiments and specific attributes within different domains. The extracted topics and aspects reveal valuable insights into domain-specific sentiments and aspects, contributing to the advancement of sentiment analysis methodologies. The findings underscore the significance of considering multi-source datasets for a more holistic understanding of sentiment in diverse text corpora.

Unifying aspect-based sentiment analysis BERT and multi-layered graph convolutional networks for comprehensive sentiment dissection

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.

A robust approach for aspect-based sentiment analysis using deep learning and domain ontologies

PurposeThe purpose of this research study is to improve sentiment analysis (SA) at the aspect level, which is accomplished through two independent goals of aspect term and opinion extraction and subsequent sentiment classification.Design/methodology/approachThe proposed architecture uses neighborhood and dependency tree-based relations for target opinion extraction, a domain–ontology-based knowledge management system for aspect term extraction, and deep learning techniques for classification.FindingsThe authors use different deep learning architectures to test the proposed approach of both review and aspect levels. It is reported that Vanilla recurrent neural network has an accuracy of 83.22%, long short-term memory (LSTM) is 89.87% accurate, Bi-LSTM is 91.57% accurate, gated recurrent unit is 65.57% accurate and convolutional neural network is 82.33% accurate. For the aspect level analysis, ρaspect comes out to be 0.712 and Δ2aspect is 0.384, indicating a marked improvement over previously reported results.Originality/valueThis study suggests a novel method for aspect-based SA that makes use of deep learning and domain ontologies. The use of domain ontologies allows for enhanced aspect identification, and the use of deep learning algorithms enhances the accuracy of the SA task.

Quality achhi hai (is good), satisfied! Towards aspect based sentiment analysis in code-mixed language

Social media, e-commerce, and other online platforms have witnessed tremendous growth in multilingual users. This requires addressing the code-mixing phenomenon, i.e. mixing of more than one language for providing a rich native user experience. User reviews and comments may benefit service providers in terms of customer management. Aspect based Sentiment Analysis (ABSA) provides a fine-grained analysis of these reviews by identifying the aspects mentioned and classifies the polarities (i.e., positive, negative, neutral, and conflict). The research in this direction has mainly focused on resource-rich monolingual languages like English, which does not suffice for analyzing multilingual code-mixed reviews. In this paper, we introduce a new task to facilitate the research on code-mixed ABSA. We offer a benchmark setup by creating a code-mixed Hinglish (i.e., mixing of Hindi and English) dataset for ABSA, which is annotated with aspect terms and their sentiment values. To demonstrate the effective usage of the dataset, we develop several deep learning based models for aspect term extraction and sentiment analysis, and establish them as the baselines for further research in this direction. 11Codes and the complete dataset have been made available on https://www.iitp.ac.in/~ai-nlp-ml/resources.html and at Github repository: https://github.com/20118/ABSA-MIX.

Improving span-based Aspect Sentiment Triplet Extraction with part-of-speech filtering and contrastive learning

Aspect Sentiment Triple Extraction (ASTE), a subtask of fine-grained sentiment analysis, aims to extract aspect terms, opinion terms, and their corresponding sentiment polarities from sentences. Previous methods often enumerated all possible spans of aspects and opinions as candidate spans that contain many invalid and irrelevant spans. This made the model training and prediction more difficult due to noised spans, leading to poor performance. To address this issue, we first propose a novel span-level approach that explicitly considers prior grammatical knowledge to generate possible candidate spans by part-of-speech filtering. In this way, our approach can make the model easier to be trained and achieve higher performance at the test stage. Besides, the quality of span-level representation of aspects and opinions is crucial for predicting their sentiment relation. To build a high-quality span-level representation of aspects and opinions, we first incorporate the contextual embedding of the entire sequence into span-level representations. Then, we introduce an auxiliary loss based on contrastive learning to make a more compact representation of the same polarities. Experimental evaluations on the 14Lap, 14Res, 15Res, and 16Res datasets demonstrate the effectiveness of our model, achieving state-of-the-art performance in span-based triplet extraction.

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.

MTL-AraBERT: An Enhanced Multi-Task Learning Model for Arabic Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is a fine-grained type of sentiment analysis; it works on an aspect level. It mainly focuses on extracting aspect terms from text or reviews, categorizing the aspect terms, and classifying the sentiment polarities toward each aspect term and aspect category. Aspect term extraction (ATE) and aspect category detection (ACD) are interdependent and closely associated tasks. However, the majority of the current literature on Arabic aspect-based sentiment analysis (ABSA) deals with these tasks individually, assumes that aspect terms are already identified, or employs a pipeline model. Pipeline solutions employ single models for each task, where the output of the ATE model is utilized as the input for the ACD model. This sequential process can lead to the propagation of errors across different stages, as the performance of the ACD model is influenced by any errors produced by the ATE model. Therefore, the primary objective of this study was to investigate a multi-task learning approach based on transfer learning and transformers. We propose a multi-task learning model (MTL) that utilizes the pre-trained language model (AraBERT), namely, the MTL-AraBERT model, for extracting Arabic aspect terms and aspect categories simultaneously. Specifically, we focused on training a single model that simultaneously and jointly addressed both subtasks. Moreover, this paper also proposes a model integrating AraBERT, single pair classification, and BiLSTM/BiGRU that can be applied to aspect term polarity classification (APC) and aspect category polarity classification (ACPC). All proposed models were evaluated using the SemEval-2016 annotated dataset for the Arabic hotel dataset. The experiment results of the MTL model demonstrate that the proposed models achieved comparable or better performance than state-of-the-art works (F1-scores of 80.32% for the ATE and 68.21% for the ACD). The proposed SPC-BERT model demonstrated high accuracy, reaching 89.02% and 89.36 for APC and ACPC, respectively. These improvements hold significant potential for future research in Arabic ABSA.

Optimized RMDL with Transfer Learning for Sentiment Classification in the MapReduce Framework

A core task in sentiment analysis is sentiment categorization, and it is crucial to understand user feelings based on their remarks in social media or product evaluations. Due to ambiguous phrases, refusal words, and other factors, categorizing sentiment presents several challenging issues. The objective of this research is to develop a hybrid optimization-based deep learning model and MapReduce framework-based sentiment categorization approach. The review document is taken from a dataset and used in this case with the MapReduce methodology. MapReduce is a software framework and programming model for analyzing massive volumes of data that consists of two phases, mapper and reducer. BERT tokenization and aspect term extraction are executed in the mapper phase, whereas sentiment analysis is performed in the reducer stage utilizing random multimodal deep learning (RMDL) with transfer learning and AlexNet and ResNet 50 as pre-trained models. In addition, the exponential coot political algorithm (ECPA) is offered as an optimization algorithm for weight optimization in RMDL. The ECPA is obtained by combining the exponential weighted moving average model (EWMA) with the coot algorithm, as well as a political optimizer (PO). The proposed ECPA_RMDL model has acquired 90.9% precision, 89.7% recall, and 89.9% f-measure.

Self-augmented sequentiality-aware encoding for aspect term extraction

Aspect Term Extraction (ATE) is a natural language processing task which recognizes and extracts aspect terms from sentences. The recent study in this field successfully leverages Pretrained Language Model (PLM) and data augmentation, which contributes to the construction of knowledgeable encoder for ATE. In this paper, we propose a novel method to strengthen ATE encoder, using self-augmented mechanism and sequentiality-aware network. Specifically, self augmentation expands training data with paraphrases and fuses correlated information using PLM during encoding. Back translation is used for obtaining pragmatically-diverse paraphrases. On the basis, BiGRU is utilized as a supplementary neural layer for extra-encoding, so as to involve sequence features into the output hidden states of PLM. We refer to our method as Self-augmented Sequentiality-sensitive Encoding (SSE for short). We carry out experiments on the benchmark SemEval datasets, including L-14, R-14, R-15 and R-16. Experimental results show that SSE yields substantial improvements, compared to BERT-based baselines. In particular, it is demonstrated that SSE is able to collaborate with other data augmentation approaches to produce more significant improvements, where the resultant ATE performance is up to 86.74%, 88.91%, 77.43% and 82.42% F1-scores (for L-14, R-14, R-15 and R-16 respectively).

Deep Learning-Based Aspect Term Extraction for Sentiment Analysis in Hindi

Objectives: Aspect terms play a vital role in finalizing the sentiment of a given review. This experimental study aims to improve the aspect term extraction mechanism for Hindi language reviews. Methods: We trained and evaluated a deep learning-based supervised model for aspect term extraction. All experiments are performed on a well-accepted Hindi dataset. A BiLSTM-based attention technique is employed to improve the extraction results. Findings: Our results show better F-score results than many existing supervised methods for aspect term extraction. Accuracy results are outstanding compared to other reported results. Results showed an outstanding 91.27% accuracy and an F–score of 43.16. Novelty: This proposed architecture and the achieved results are a foundational resource for future studies and endeavours in the field. Keywords: Sentiment analysis, Aspect based sentiment analysis, Aspect term extraction, Deep Learning, Bi LSTM, Indian language, Hindi