Fine-grained Opinion Research Articles

A Multi-Agent System for Fine-Grained Opinion Dynamics Analysis in Online Social Networks

The influence and dissemination of users’ opinions are the essence of the opinion dynamics in online social networks (OSNs). Understanding the process of users’ opinion formation and propagation can provide better service for public opinion monitoring and product advertising. However, most opinion dynamics research typically do not distinguish between user opinion formation and propagation, instead focusing on the process of mass opinion polarization. This article presents a multiagent system (MAS) to analyze fine-grained opinion dynamics (FOD) by agent-based modeling (ABM). At the macro level, the MAS-FOD system we designed can produce a statistical analysis of public opinion evolution based on different parameter constellations and analyze the changes in personalized agent opinions. At the micro level, the agent-based model is presented to describe the single user in OSNs as an individualized agent in MAS-FOD. Specifically, we propose two mechanisms, agent-based opinion formation (AOF) mechanism and agent-based opinion propagation (AOP) mechanism, for agents to form and disseminate opinions, respectively. Meanwhile, multidimensional social influence features mining from self, local neighbors, and global topic community are defined and used in two mechanisms to train personalized agents to self-adapt to the MAS-FOD system. We demonstrate the rationality and effectiveness of the MAS-FOD system from two types of experiments: empirical analysis and simulation analysis. The former is driven by empirical social network data to analyze the predictive performance of AOF; the latter simulates the public opinion propagation through the AOP mechanism in the MAS-FOD system. The results demonstrate that: 1) the AOF outperforms SOTA methods in the accuracy of agent opinion prediction; 2) the dissemination effect based on the AOP is more closer to the actual evolution trend of public opinion than the baseline; and 3) the MAS-FOD system can perform fine-grained analysis of opinion dynamics by adjusting different parameters.

Policy feedback and income targeting in the welfare state

Abstract In light of ongoing debates about income targeting in the welfare state, this article explores how the design and outcomes of income targeting policies are related to popular targeting preferences. Based on the unique combination of fine-grained opinion and policy indicators in a multilevel analysis, the results show that targeting preferences are indeed empirically related to targeting policies. However, whether these preferences are affected more by the de jure targeting design or the de facto targeting outcome seems to vary between two very different policy domains. In the case of unemployment benefits, the results suggest positive policy feedback: support for high-income targeting increases when unemployment benefits are designed to benefit those with previously higher incomes. For income taxation, by contrast, the results suggest negative policy feedback. In that case, it is not so much the de jure design but rather the de facto outcome that matters: the more taxes effectively work to the advantage of higher-income earners, the less support there is for a tax that levies the same amount on everyone, regardless of income.

A Novel Approach of Deep Learning Using Sentiment Analysis in Python

This paper focused on Sentiment Analysis is the task of categorize the division of a given text. For instance, a text-based tweet can be categorize into either "positive", "negative", or "neutral". Given the text and accompanying labels, a model can be trained to predict the correct sentiment. Sentiment Analysis techniques can be categorized into Deep Learning approaches, lexicon-based approaches, and even hybrid methods. Some subcategories of research in sentiment analysis include: multimodal sentiment analysis, aspect-based sentiment analysis, fine-grained opinion analysis, language specific sentiment analysis. Sentiment analysis (SA) is a process of extensive exploration of data stored on the Web to identify and categorize the views expressed in a part of the text. The intended outcome of this process is to assess the author attitude toward a particular topic, movie, product, etc. The result is positive, negative, or neutral These study illustrated different techniques in SA approach for extracting and analytics sentiments associated with the polarity of positive, negative, or neutral on the topic selected. Social networks SA can be a useful source of information and data. SA acquires important in many areas of business, politics, and thought.. The main aim of this study is to provide full concept about SA techniques and its classification and methods used it. Also, we give a brief overview of big data techniques and its relation and use in SA field. Because the recent period has witnessed a remarkable development in the use of Big Data (Hadoop) in the process collection of data and reviews from social networks for analysis.

Meta-Based Self-Training and Re-Weighting for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) means to identify fine-grained aspects, opinions, and sentiment polarities. Recent ABSA research focuses on utilizing multi-task learning (MTL) to achieve less computational costs and better performance. However, there are certain limits in MTL-based ABSA. For example, unbalanced labels and sub-task learning difficulties may result in the biases that some labels and sub-tasks are overfitting, while the others are underfitting. To address these issues, inspired by neuro-symbolic learning systems, we propose a meta-based self-training method with a meta-weighter (MSM). We believe that a generalizable model can be achieved by appropriate symbolic representation selection (in-domain knowledge) and effective learning control (regulation) in a neural system. Thus, MSM trains a teacher model to generate in-domain knowledge (e.g., unlabeled data selection and pseudo-label generation), where the generated pseudo-labels are used by a student model for supervised learning. Then, the meta-weighter of MSM is jointly trained with the student model to provide each instance with sub-task-specific weights to coordinate their convergence rates, balancing class labels, and alleviating noise impacts introduced from self-training. The following experiments indicate that MSM can utilize 50% labeled data to achieve comparable results to state-of-arts models in ABSA and outperform them with all labeled data.

Fine-grained aspect-based opinion mining on online course reviews for feedback analysis

ABSTRACT Online learning has developed rapidly and billions of learners have participated in various courses. However, the high dropout rate is universal and learning performance is not satisfactory. Fortunately, learners have posted a large number of reviews which express their feedback opinions. The fine-grained aspects and opinions existing in reviews provide valuable information for educators to improve learning performance. Thus, it is necessary to make fine-grained aspect-based opinion mining on course reviews for feedback analysis. First, the latent Dirichlet allocation is applied to generate topics and the topic related words from course reviews. Each word belongs to a topic and these words are considered as the core aspects. Second, a series of rules and an algorithm are designed based on dependency syntax analysis to extract the fine-grained aspects and opinions. The aspect-based opinion candidate set is generated. Then the corresponding opinions of the core aspects are selected from the candidate set. Third, the sentiment score of each opinion is calculated combining the dictionary-based and pointwise mutual information method to identify the polarity of the opinion. The extracted aspects and opinions with sentiment polarity provide fine-grained feedback information from several topic perspectives.

SpanMTL: a span-based multi-table labeling for aspect-oriented fine-grained opinion extraction

Aspect-oriented Fine-grained Opinion Extraction (AFOE) aims to extract the aspect terms, corresponding opinion terms and sentiment polarity in a target sentence. Most previous methods treat AFOE as word-level or span-level task, which ignore the complementarity of these two tasks. To integrate the merits of word-level and span-level information, we construct an end-to-end Span-based Multi-Table Labeling (SpanMTL) framework. SpanMTL combines word-based and span-based table labeling to tackle AFOE task. Specifically, in the proposed model, we use two separate BiLSTMs to encode the information of aspect and opinion terms into a word-based 2D representation table. Based on the table, we construct span-based table with CNN by associating the word-pair representations. At last, we integrate the table label distributions of word- and span-based table labeling to generate a multi-table labeling. The proposed method improves the performances of Opinion Pair Extraction (OPE) and Opinion Triplet Extraction (OTE) tasks by introducing span information, especially on the datasets with lots of spans. We have conducted various experiments on AFOE datasets to validate our method. The experimental results show that our method outperforms other baselines when the sentences having lots of span information.

Improving Fine-grained Opinion Mining Approach with a Deep Constituency Tree-long Short Term Memory Network and Word Embedding

Objective: One key task of fine-grained opinion mining on product review is to extract product aspects and their corresponding opinion expressed by users. Previous work has demonstrated that precise modeling of opinion targets within the surrounding context can improve performances. However, how to effectively and efficiently learn hidden word semantics and better represent targets and the context still needs to be further studied. Recent years have seen a revival of the Long Short- Term Memory (LSTM), with its effectiveness being demonstrated on a wide range of problems. However, LSTM based approaches are still limited to linear data processing since it processes the information sequentially. As a result, they may perform poorly on user-generated texts, such as product reviews, tweets, etc., whose syntactic structure is not precise. Methods: In this research paper, we propose a constituency tree long short term memory neural network- based approach. We compare our model with state-of-the-art baselines on SemEval 2014 datasets. Results: Experiment results show that our models obtain competitive performances compared to various supervised LSTM architectures. Conclusion: Our work contributes to the improvement of state-of-the-art aspect-level opinion mining methods and offers a new approach to support the human decision-making process based on opinion mining results.

Recop: fine-grained opinions and sentiments-based recommender system for industry 5.0

Recop: fine-grained opinions and sentiments-based recommender system for industry 5.0

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.

Aspect-Based Pair-Wise Opinion Generation in Chinese automotive reviews: Design of the task, dataset and model

The extraction of opinion target–word pairs from user reviews has received much attention recently, since it can provide essential information for fine-grained opinion analysis. However, according to our statistics on a large-scale dataset of Chinese reviews, about 60% reviews do not explicitly show opinion targets or words. To investigate this problem, this paper introduces a new task under fine-grained opinion analysis, named Aspect-Based Pair-wise Opinion Generation (ABPOG), which aims to generate opinion target–word pairs based on reviews and aspects. To perform this task, we develop a sequence-to-sequence model for opinion target–word pair generation by extending the pointer–generator network with two approaches: (1) an aspect-aware encoder that receives an additional aspect embedding as input to extract aspect-specific features, (2) two hierarchical decoders including a token-level GRU and a global GRU to generate opinion targets and words jointly. To empirically evaluate our task and model, we develop a multi-aspect dataset for ABPOG based on Chinese automotive reviews. Extensive experiments on our dataset show that our model outperforms several strong baselines adapted from the state-of-the-art aspect-based summarization method.

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)

A Research Agenda for Financial Opinion Mining

Opinion mining is a prevalent research issue in many domains. In the financial domain, however, it is still in the early stages. Most of the researches on this topic only focus on the coarse-grained market sentiment analysis, i.e., 2-way classification for bullish/bearish. Thanks to the recent financial technology (FinTech) development, some interdisciplinary researchers start to involve in the in-depth analysis of investors' opinions. In this position paper, we first define the financial opinions from both coarse-grained and fine-grained points of views, and then provide an overview of the issues already tackled. In addition to listing research issues of the existing topics, we further propose a road map of fine-grained financial opinion mining for future researches, and point out several challenges yet to explore. Moreover, we provide possible directions to deal with the proposed research issues.

Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction

Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining. Since ASTE consists of multiple subtasks, including opinion entity extraction, relation detection, and sentiment classification, it is critical and challenging to appropriately capture and utilize the associations among them. In this paper, we transform ASTE task into a multi-turn machine reading comprehension (MTMRC) task and propose a bidirectional MRC (BMRC) framework to address this challenge. Specifically, we devise three types of queries, including non-restrictive extraction queries, restrictive extraction queries and sentiment classification queries, to build the associations among different subtasks. Furthermore, considering that an aspect sentiment triplet can derive from either an aspect or an opinion expression, we design a bidirectional MRC structure. One direction sequentially recognizes aspects, opinion expressions, and sentiments to obtain triplets, while the other direction identifies opinion expressions first, then aspects, and at last sentiments. By making the two directions complement each other, our framework can identify triplets more comprehensively. To verify the effectiveness of our approach, we conduct extensive experiments on four benchmark datasets. The experimental results demonstrate that BMRC achieves state-of-the-art performances.

MTVRep: A movie and TV show reputation system based on fine-grained sentiment and semantic analysis

Customer reviews are a valuable source of information from which we can extract very useful data about different online shopping experiences. For trendy items (products, movies, TV shows, hotels, services . . . ), the number of available users and customers’ opinions could easily surpass thousands. Therefore, online reputation systems could aid potential customers in making the right decision (buying, renting, booking . . . ) by automatically mining textual reviews and their ratings. This paper presents MTVRep, a movie and TV show reputation system that incorporates fine-grained opinion mining and semantic analysis to generate and visualize reputation toward movies and TV shows. Differently from previous studies on reputation generation that treat the task of sentiment analysis as a binary classification problem (positive, negative), the proposed system identifies the sentiment strength during the phase of sentiment classification by using fine-grained sentiment analysis to separate movie and TV show reviews into five discrete classes: strongly negative, weakly negative, neutral, weakly positive and strongly positive. Besides, it employs embeddings from language models (ELMo) representations to extract semantic relations between reviews. The contribution of this paper is threefold. First, movie and TV show reviews are separated into five groups based on their sentiment orientation. Second, a custom score is computed for each opinion group. Finally, a numerical reputation value is produced toward the target movie or TV show. The efficacy of the proposed system is illustrated by conducting several experiments on a real-world movie and TV show dataset.

Opinion subset selection via submodular maximization

Current research on subset selection for opinion analysis assumes that their methods can retrieve the opinions expressed in documents from general text features. However, such relaxed conditions can hardly maintain the performance of the analysis in opinion mining, especially when given strict limitations on the subset size. In this paper, we propose a framework for opinion subset selection. This framework can select a small set of instances from original data to convey a subjective representation for opinion classification and regression. Compared with our framework, the conventional submodular based subset selection approach cannot capture the fine-grained opinion features expressed in the corpus. Specifically, we propose a monotone non-decreasing score function and a framework based on topic modeling and submodular maximization for filtering irrelevant information and selecting the subsets. Our work further introduces an opinion-sensitive algorithm for optimizing the proposed function for opinion subset construction. We perform extensive experiments and comparative analysis of different subset selection methods in this work. The experimental result shows that the proposed opinion subset selection framework can compress the original text training set and preserve the test set’s classification and regression metric performance at the same time.

Detecting singleton spams in reviews via learning deep anomalous temporal aspect-sentiment patterns

Customer reviews are an essential source of information to consumers. Meanwhile, opinion spams spread widely and the detection of spam reviews becomes critically important for ensuring the integrity of the echo system of online reviews. Singleton spam reviews—one-time reviews—have spread widely of late as spammers can create multiple accounts to purposefully cheat the system. Most available techniques fail to detect this cunning form of malicious reviews, mainly due to the scarcity of behaviour trails left behind by singleton spammers. Available approaches also require extensive feature engineering, expensive manual annotation and are less generalizable. Based on our thorough study of spam reviews, it was found that genuine opinions are usually directed uniformly towards important aspects of entities. In contrast, spammers attempt to counter the consensus towards these aspects while covering their malicious intent by adding more text but on less important aspects. Additionally, spammers usually target specific time periods along products’ lifespan to cause maximum bias to the public opinion. Based on these observations, we present an unsupervised singleton spam review detection model that runs in two steps. Unsupervised deep aspect-level sentiment model employing deep Boltzmann machines first learns fine-grained opinion representations from review texts. Then, an LSTM network is trained on opinion learned representation to track the evolution of opinions through the fluctuation of sentiments in a temporal context, followed by the application of a Robust Variational Autoencoder to identify spam instances. Experiments on three benchmark datasets widely used in the literature showed that our approach outperforms strong state-of-the-art baselines.

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.

Techniques and Trends for Fine-Grained Opinion Mining and Sentiment Analysis: Recent Survey

Background: Nowadays, with the appearance of web 2.0, more users express their opinions, judgments, and thoughts towards certain objects, services, organizations, and their attributes via social networking, forum entries, websites, and blogs and so on. In this way, the volume of raw content generated by these users will increase rapidly with enormous size, where people often find difficulties in identifying and summarizing fine-grained sentiments buried in the opinion-rich resources. The traditional opinion mining techniques, which focused on the overall sentiment of the review, fails to uncover the sentiments expressed on the aspects of the reviewed entity. For that, researchers in Aspect-based opinion mining community try to solve and handle this problem. Objective: Our proposed study aims to present, survey and compare in the first place the important recent Aspect-based opinion mining approaches relevant to important languages such English, Arabic and Chinese and commonly datasets used in literature so that future researchers could improve their results. The cited approaches used the last techniques in the area on Opinion mining field, relevant to the Deep Learning models. In the second place, we try to highlight and give special attention to the Arabic language by introducing a dashboard of deep learning methods dedicated to the Arabic language. Finally, we emphasize the research gaps and future challenges in both English and Arabic languages that provide some new potential research fields. Methods: We have carefully summarized 48 models according to their algorithm into three categories: supervised, semi-supervised and unsupervised. Due to a large number of approaches with diverse datasets and techniques, we propose some statistical graphics to compare different experimentation results namely precision, Recall, and F-measure. Also, the study has conferred a comparative analysis and a comprehensive discussion of different approaches and techniques dedicated to the aspect extraction sub-task using the new tendency that of deep learning on both Arabic, English and Chinese language. We have introduced some future challenges, research gaps, and new trends in the opinion mining task, which need more efforts and investigations to present new solutions that make the opinion mining field more pervasive and give more ideas about the different researches done in the field of OM. Methods: We have compared the different approaches and techniques dedicated to the extraction of aspects using the new tendency that of deep learning. Our contribution illustrates the add values given by deep learning models in the treatment of user reviews expressed in the Arabic language. At the same time, this work is mainly based on the use of the evaluation performance metrics (precision, recall, and f-measure).

Fine-Grained Opinion Mining on Chinese Car Reviews with Conditional Random Field

Nowadays, the Internet has penetrated into all aspects of people’s lives. A large number of online customer reviews have been accumulated in several product forums, which are valuable resources to be analyzed. However, these customer reviews are unstructured textual data, in which a lot of ambiguities exist, so analyzing them is a challenging task. At present, the effective deep semantic or fine-grained analysis of customer reviews is rare in the existing literature, and the analysis quality of most studies is also low. Therefore, in this paper a fine-grained opinion mining method is introduced to extract the detailed semantic information of opinions from multiple perspectives and aspects from Chinese automobile reviews. The conditional random field (CRF) model is used in this method, in which semantic roles are divided into two groups. One group relates to the objects being reviewed, which includes the roles of manufacturer, the brand, the type, and the aspects of cars. The other group of semantic roles is about the opinions of the objects, which includes the sentiment description, the aspect value, the conditions of opinions and the sentiment tendency. The overall framework of the method includes three major steps. The first step distinguishes the relevant sentences with the irrelevant sentences in the reviews. At the second step the relevant sentences are further classified into different aspects. At the third step fine-grained semantic roles are extracted from sentences of each aspect. The data used in the training process is manually annotated in fine granularity of semantic roles. The features used in this CRF model include basic word features, part-of-speech (POS) features, position features and dependency syntactic features. Different combinations of these features are investigated. Experimental results are analyzed and future directions are discussed.

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.