Extract Opinion Words Research Articles

A Joint Model for Target-Oriented Opinion Words Extraction and Sentiment Classification

Target-oriented opinion word extraction and aspect-level sentiment classification are two highly relevant tasks in aspect-based sentiment analysis. Previous studies tend to separate them and focus on one of the tasks, which ignore the connection between opinion word extraction and sentiment classification, and result in the waste of useful connection information. In this paper, we propose a co-extraction model, in which the two tasks are formulated as a sequence labeling problem. The model involves two stacked Bi-LSTM modules and an information interaction component to generate all opinion-polarity pairs of the input sentences simultaneously. The experimental results show that our model achieves advanced results in target opinion word-polarity co-extraction. The performance of both tasks is stronger than the baseline, and the model is of low complexity and high operational efficiency.

Gated Relational Encoder-Decoder Model for Target-Oriented Opinion Word Extraction

Target-Oriented Opinion Word Extraction (TOWE) is a challenging information extraction task that aims to find the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion words</i> corresponding to given <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion targets</i> in text. To solve TOWE, it is important to consider the surrounding words of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion words</i> as well as the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion targets</i> . Although most existing works have captured the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion target</i> using Deep Neural Networks (DNNs), they cannot effectively utilize the local context, i.e. relationship among surrounding words of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion words</i> . In this work, we propose a novel and powerful model for TOWE, Gated Relational target-aware Encoder and local context-aware Decoder (GRED), which dynamically leverages the information of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion target</i> and the local context. Intuitively, the target-aware encoder catches the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion target</i> information, and the local context-aware decoder obtains the local context information from the relationship among surrounding words. Then, GRED employs a gate mechanism to dynamically aggregate the outputs of the encoder and the decoder. In addition, we adopt a pretrained language model Bidirectional and Auto-Regressive Transformer (BART), as the structure of GRED to improve the implicit language knowledge. Extensive experiments on four benchmark datasets show that GRED surpasses all the baseline models and achieves state-of-the- art performance. Furthermore, our in-depth analysis demonstrates that GRED properly leverages the information of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion target</i> and the local context for extracting the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opinion words</i> .

Research on the Path of Network Opinion Expression in AI Environment for College Students.

Network interaction has evolved into a grouping paradigm as civilization has progressed and artificial intelligence technology has advanced. This network group model has quickly extended communication space, improved communication content, and tailored to the demands of netizens. The fast growth of the network community on campus can assist students in meeting a variety of communication needs and serve as a vital platform for their studies and daily lives. It is investigated how to extract opinion material from comment text. A strategy for extracting opinion attitude words and network opinion characteristic words from a single comment text is offered at a finer level. The development of a semiautonomous domain emotion dictionary generating technique improves the accuracy of opinion and attitude word extraction. This paper proposes a window-constrained Latent Dirichlet Allocation (LDA) topic model that improves the accuracy of extracting network opinion feature words and ensures that network opinion feature words and opinion attitude words are synchronized by using the location information of opinion attitude words. The two-stage opinion leader mining approach and the linear threshold model based on user roles are the subjects of model simulation tests in this study. It is demonstrated that the two-stage opinion leader mining method suggested in this study can greatly reduce the running time while properly finding opinion leaders with stronger leadership by comparing the results with existing models. It also shows that the linear threshold model based on user roles proposed in this paper can effectively limit the total number of active users who are activated multiple times during the information diffusion process by distinguishing the effects of different user roles on the information diffusion process.

Reasoning over multiplex heterogeneous graph for Target-oriented Opinion Words Extraction

Target-oriented Opinion Word Extraction (TOWE) is a new emerging subtask of Aspect Based Sentiment Analysis (ABSA), which aims to extract fine-grained opinion terms for a given aspect term from a sentence. In this task, the key point is how to find the correct opinion that is far away from its corresponding aspect. Ideally, reinforcement learning (RL) seems to be a promising approach due to its delayed reward mechanism. However, as aspect-opinion interaction data is likely to be complicated, it is not easy to directly apply RL techniques to improve the performance. In this paper, we propose a novel Padding-Enhanced Reinforcement learning model (PER) to address this issue. Specifically, PER first designs a multiplex heterogeneous graph to cover both sequential structure and syntactic structure in order to enrich their interactions and alleviate the long distance issue. By formulating the extraction task as a Markov Decision Process (MDP), PER then walks on the designed graph to infer corresponding opinions for each aspect. In addition, a padding module is further designed to aggregate rich information from distant nodes to guide the exploration process. Extensive experimental results on four widely used datasets illustrate that our proposed model consistently outperforms the state-of-the-art methods.

ALSEE: a framework for attribute-level sentiment element extraction towards product reviews

Attribute-level sentiment element extraction aims to obtain the word pair < opinion target, opinion word > from texts, which mainly obtain fine-grained evaluation information in the attribute level. Due to the information fragmentation and semantic sparseness of product reviews, it is difficult to capture more comprehensive local information from unstructured texts, which leads to the incorrect extraction of some word pairs. Aimed at the problem, this paper proposes a framework for Attribute-Level Sentiment Element Extraction (ALSEE) towards product reviews. Firstly, a small amount of sample data is selected by random sampling, and multiple features (including part of speech, word distance, dependency relationship and semantic role) which are labelled. The labelled data are used as the training set. Then, the Condition Random Field (CRF) model is applied to extract opinion targets (OT) and opinion words (OW). The self-training strategy is used to achieve the semi-supervised learning of CRF model through iterative training. Finally, target-opinion word pairs with modifying relationship are obtained by dependency parsing. Compared with the existing methods, the proposed framework can effectively extract attribute-level sentiment elements though experimental results.

Target-oriented Opinion Words Extraction via graph convolutional network

Target-oriented opinion word extraction (TOWE) is a sequence labelling subtask of aspect-level sentiment analysis (ABSA), which aims to extract corresponding opinion words for a given sentence and opinion target. In view of the existing related work, the structural information of sentences is not fully considered. In this study, we explore the integration of neural network and dependency tree to handle the TOWE and propose a model based on graph convolution network (GCN). The model uses the long short-term memory network (LSTM) to learn the semantic features of sentences. On this basis, the model uses the GCN to model the sentence structure through dependency tree and capture the syntactic dependency relationship between the target word and the opinion word. The experimental results show that GCN can effectively improve the performance of TOWE. The F1 values of the model on the semeval-rest14 and semeval-laptop14 reached 82.60% and 74.45%.

Intelligent Aspect based Model for Efficient Sentiment Analysis of User Reviews

Mining online reviews to extract opinion targets and words are substantial tasks in fine-grained opinion mining. The main aim is to mine sensible multi-grain aspects and opinion words from unlabeled reviews. In this paper, Combined Aspect based Sentiment Model (CASM) is propounded to cooperatively mine multi-grain features and opinions. CASM deals with aspects, opinions, sentiment polarity and granularity concurrently. Support Vector Machine-Radial Basis Function kernel (SVM-RBF) classifier is applied to improve CASM by splitting aspects and opinion words. CASM-SVM-RBF deals with two different kinds of aspects and opinions: general and particular aspects, overall opinions and aspect-precise opinions. Candidates with improved confidence are mined as opinion targets or words. Index Terms:Aspects, Opinions, Sentiment, Support Vector Machine, Radial Basis Function, Support Vector Machine (SVM), Radial Basis Function (RBF)

Question-Driven Span Labeling Model for Aspect–Opinion Pair Extraction

Aspect term extraction and opinion word extraction are two fundamental subtasks of aspect-based sentiment analysis. The internal relationship between aspect terms and opinion words is typically ignored, and information for the decision-making of buyers and sellers is insufficient. In this paper, we explore an aspect–opinion pair extraction (AOPE) task and propose a Question-Driven Span Labeling (QDSL) model to extract all the aspect–opinion pairs from user-generated reviews. Specifically, we divide the AOPE task into aspect term extraction (ATE) and aspect-specified opinion extraction (ASOE) subtasks; we first extract all the candidate aspect terms and then the corresponding opinion words given the aspect term. Unlike existing approaches that use the BIO-based tagging scheme for extraction, the QDSL model adopts a span-based tagging scheme and builds a question–answer-based machine-reading comprehension task for an effective aspect–opinion pair extraction. Extensive experiments conducted on three tasks (ATE, ASOE, and AOPE) on four benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches.

Integrate syntax information for target-oriented opinion words extraction with target-specific graph convolutional network

Target-oriented Opinion Words Extraction (TOWE) aims to identify opinion words toward a specific target given the sentence. Syntax structure, which contains dependency relationships among words, is a vital clue for this task. With the help of syntax structure as a constraint, the model could remove irrelevant words and focus on tokens that are relevant to the given target. Directly adapting existing syntactic-based methods faces the problem that these models do not explicitly learn target-centric representations. Another challenge is that prior works only learn fixed order dependency relations, while context words require syntactic information in different scales. To handle these issues, we propose Target-Specific Graph Convolutional Network (TS-GCN) to explicitly integrate dependency structure. The proposed method could build high-quality syntax-aware representations by propagating target information to syntactically related words via graph convolution. Furthermore, we design a memory-based module to dynamically learn multi-granularity syntactic knowledge and infuse local features. Experimental results demonstrate the effectiveness of our method, and we achieve state-of-the-art performances on four SemEval datasets.

Enhancement of Target‐Oriented Opinion Words Extraction with Multiview‐Trained Machine Reading Comprehension Model

Target-oriented opinion words extraction (TOWE) seeks to identify opinion expressions oriented to a specific target, and it is a crucial step toward fine-grained opinion mining. Recent neural networks have achieved significant success in this task by building target-aware representations. However, there are still two limitations of these methods that hinder the progress of TOWE. Mainstream approaches typically utilize position indicators to mark the given target, which is a naive strategy and lacks task-specific semantic meaning. Meanwhile, the annotated target-opinion pairs contain rich latent structural knowledge from multiple perspectives, but existing methods only exploit the TOWE view. To tackle these issues, we formulate the TOWE task as a question answering (QA) problem and leverage a machine reading comprehension (MRC) model trained with a multiview paradigm to extract targeted opinions. Specifically, we introduce a template-based pseudo-question generation method and utilize deep attention interaction to build target-aware context representations and extract related opinion words. To take advantage of latent structural correlations, we further cast the opinion-target structure into three distinct yet correlated views and leverage meta-learning to aggregate common knowledge among them to enhance the TOWE task. We evaluate the proposed model on four benchmark datasets, and our method achieves new state-of-the-art results. Extensional experiments have shown that the pipeline method with our approach could surpass existing opinion pair extraction models, including joint methods that are usually believed to work better.

Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction

Target-oriented opinion words extraction (TOWE) is a new subtask of ABSA, which aims to extract the corresponding opinion words for a given opinion target in a sentence. Recently, neural network methods have been applied to this task and achieve promising results. However, the difficulty of annotation causes the datasets of TOWE to be insufficient, which heavily limits the performance of neural models. By contrast, abundant review sentiment classification data are easily available at online review sites. These reviews contain substantial latent opinions information and semantic patterns. In this paper, we propose a novel model to transfer these opinions knowledge from resource-rich review sentiment classification datasets to low-resource task TOWE. To address the challenges in the transfer process, we design an effective transformation method to obtain latent opinions, then integrate them into TOWE. Extensive experimental results show that our model achieves better performance compared to other state-of-the-art methods and significantly outperforms the base model without transferring opinions knowledge. Further analysis validates the effectiveness of our model.

Opinion Relation Co-Extraction Based on Partially-Supervised Topical Relations Word Alignment Model

The most critical tools for fine-grained opinion extraction are opinion goals and opinion terms extracted from on-line comments. The key part of this process is to identify the connection between terms. To do this, the Word Alignment Model (WAM) was introduced in which the associated variable can be identified by word alignment by an opinion goal. Nevertheless, its ability to extract opinion words was less successful. In order to determine opinion connections as a process of alignment, the partially supervised Word Alienation Model (PSWAM) has therefore been created. Then a visual co-ranking algorithm was implemented together with the Opinion Relationship Map, to model all the candidates and to measure the confidence of each voter by defining their opinion. In addition, higher-confidence candidates were extracted as opinions or opinions. This method, though, involves an added kind of interaction with terms such as topical connections in graphic thought. Therefore the current relationship is assumed in this report in order to model the applicants and derive the feelings, views and opinions. The efficiency of co-extracting thoughts, viewpoints and issues is enhanced effectively by using this method. The experimental results further indicate that compared to the existing paradigm, the efficiency of the proposed model.

LISA: Language-Independent Method for Aspect-Based Sentiment Analysis

Understanding “what others think” is one of the most eminent pieces of knowledge in the decision-making process required in a wide spectrum of applications. The procedure of obtaining knowledge from each aspect (property) of users' opinions is called aspect-based sentiment analysis which consists of three core sub-tasks: aspect extraction, aspect and opinion-words separation, and aspect-level polarity classification. Most successful approaches proposed in this area require a set of primary training or extensive linguistic resources, which makes them relatively costly and time consuming in different languages. To overcome the aforementioned challenges, we propose an unsupervised paradigm for aspect-based sentiment analysis, which is not only simple to use in different languages, but also holistically performs the subtasks for aspect-based sentiment analysis. Our methodology relies on three coarse-grained phases which are partitioned to manifold fine-grained operations. The first phase extracts the prior domain knowledge from dataset through selecting the preliminary polarity lexicon and aspect word sets, as representative of aspects. These two resources, as primitive knowledge, are assigned to an expectation-maximization algorithm to identify the probability of any word based on the aspect and sentiment. To determine the polarity of any aspect in the final phase, the document is firstly broken down to its constituting aspects and the probability of each aspect/polarity based on the document is calculated. To evaluate this method, two datasets in the English and Persian languages are used and the results are compared with various baselines. The experimental results show that the proposed method outperforms the baselines in terms of aspect, opinion-word extraction and aspect-level polarity classification.

Effective Opinion Words Extraction for Food Reviews Classification

Opinion mining (known as sentiment analysis or emotion Artificial Intelligence) holds important roles for e-commerce and benefits to numerous business and organizations. It studies the use of natural language processing, text analysis, computational linguistics, and biometrics to provide us business valuable insights into how people feel about our product brand or service. In this study, we investigate reviews from Amazon Fine Food Reviews dataset including about 500,000 reviews and propose a method to transform reviews into features including Opinion Words which then can be used for reviews classification tasks by machine learning algorithms. From the obtained results, we evaluate useful Opinion Words which can be informative to identify whether the review is positive or negative.

Product Quality Assessment Based on Online Reviews

Reviews can reflect the degree of consumers' satisfaction and views on product quality, and consumers tend to read product reviews and then get helpful information about product quality before placing an order in e-commerce platforms. However, the existing research mainly focus on the assessment of review quality, fake review detection, opinion mining, and there is little research to assess product quality from the perspectives of product features based on reviews objectively and quantifialy. Therefore, the authors propose a method to assess product quality based on reviews in a granularity of product feature. The authors define the related quality dimensions and develop the corresponding assessment models, assess the review quality crawled from an e-commerce platform, then extract product features and opinion words from the quality reviews, and finally assess product quality on the extracted and consumer-concerned features. Experiment results demonstrate the methodology can achieve the assessment of product quality on any feature objectively and quantificationally.

Opinion Extraction on Online Malay Text

Growing of social media usage present a new set of opportunities and challenges in the way of information is retrieved and searched. Opinions on social media has become an important factor in influencing people choices on purchasing a product and service. Hence, sentiment analysis has become the most crucial tool in tracking people feedbacks on products and services. For Malay language there is limited sources available for this language. Thus, in this paper we present the method of extracting opinion on online Malay text. The traditional method using POS extraction is not adequate. Thus, rule based method is integrated with POS extraction method to improve opinion words extraction. Most of the existing tools are able to retrieve opinion at sentence and document level. More detail analysis is acquired to have detail information and summarization of a product. This is where feature level sentiment analysis is needed. The process of identifying opinion of a particular feature in a sentence, can be quite tedious and troublesome. This is because opinion of the feature can be hidden and scattered in the sentence. Therefore, opinion mapping is employed for opinion extraction at feature level in this paper. A set of tweets from telecommunication domain is used to evaluate the proposed framework. From the experiment, the accuracy of the extraction performed is 88%. The detail description of the feature level opinion extraction steps is discussed in this paper.

Analysis on Opinion Words Extraction in Electronic Product Reviews

Online user reviews are increasingly becoming important for measuring the quality of different products and services. Sentiment classification or opinion mining involves studying and building a system that collects data from online and examines the opinions. Sentiment classification is also defined as opinion extraction as the computational research area of subjective information towards different products. Opinion mining or sentiment classification has attracted in many research areas because of its usefulness in natural language processing and other area of applications. Extracting opinion words and product features are also important tasks in opinion mining. In this work an unsupervised approach was proposed to extract opinions and product features without training examples. To obtain the dependency relation between the product aspects and opinions, this work used StanfordCoreNLP dependency parser. From these relations, rules are predified to extract product and opinions. The main advantage of this approach is that there is no need for training data and it has domain independence. Acoording to the experimental results, the modified algorithm gets better results than the double propagation algorithm.

Sentence Level Domain Independent Opinion and Targets Identification in Unstructured Reviews

User reviews, blogs, and social media data are widely used for various types of decision-making. In this connection, Machine Learning and Natural Language Processing techniques are employed to automate the process of opinion extraction and summarization. We have studied different techniques of opinion mining and found that the extraction of opinion target and opinion words and the relation identification between them are the main tasks of state-of-the-art techniques. Furthermore, domain-independent features extraction is still a challenging task, since it is costly to manually create an extensive list of features for every domain. In this study, we tested different syntactic patterns and semantic rules for the identification of evaluative expressions containing relevant target features and opinion. We have proposed a domain-independent framework that consists of two phases. First, we extract Best Fit Examples (BFE) consisting of short sentences and candidate phrases and in the second phase, pruning is employed to filter the candidate opinion targets and opinion words. The results of the proposed model are significant.

A comprehensive survey of research based on extraction of opinion words and opinion targets from customer reviews

This survey paper categorizes, compares, and summarizes the algorithms, data sets and performance measurement in the published articles related to extraction of opinion targets and words from customer reviews. The systems reviewed either deploy a supervised or completely unsupervised algorithm for the process. Most of the systems rely on K-nearest neighbor algorithm or a bootstrapping approach. Most of the methods have produced a list comprising of opinion targets from the customer reviews of a product. As a result, opinion targets usually are product features or attributes. The approaches mentioned in the papers reviewed suffer either from error propagation or from lack of automation for parsing long span relations. Certain approaches have taken an initial bag of seed words and proceeded to exploit the syntactical relationship between opinion words and targets. Mainly online product reviews have been used. It is generally believed that the co- occurrence of certain target and opinion words in close proximity makes them more relevant to each other and to the product as well. Owing to the nature of online review data sets most literature have not include assessment of opinion targets and words across multiple domains.

Feature-opinion pair identification method in two-stage based on dependency constraints

Feature-opinion pair identification includes opinion words, opinion targets extraction and their relations identification, is important for analysis online reviews. In this paper, we propose a feature-opinion pair identification method in two-stage based on dependency constraints according to the relationship between the identification of feature-opinion pair and dependency constraints. In the first stage, we construct dependency constraints based on the dependency information of words. Then, dependency constraints and seed words are employed to extract opinion words and opinion targets. In the second stage, we use opinion words and opinion targets extracted in the first stage to construct candidate feature-opinion pairs. Thereafter, integrate dependency constraints, location features and part-of-speech features into support vector machine to identify feature-opinion pair. Our experimental result using online reviews demonstrates that the proposed method is effective in the identification of feature-opinion pairs, and the F-score has reached 83.85%.