Sentiment Consistency Research Articles

A Hybrid Deep Learning Approach for Enhanced Sentiment Classification and Consistency Analysis in Customer Reviews

Consumer reviews play a pivotal role in shaping purchasing decisions and influencing the reputation of businesses in today’s digital economy. This paper presents a novel hybrid deep learning model, WDE-CNN-LSTM, designed to enhance the sentiment classification of consumer reviews. The model leverages the strengths of Word Embeddings (WDE), Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs) to capture temporal and local text data features. Extensive experiments were conducted across binary, three-class, and five-class classification tasks, with the proposed model achieving an accuracy of 98% for binary classification, 98% for three-class classification, and 95.21% for five-class classifications. The WDE-CNN-LSTM model consistently outperformed standalone CNN, LSTM, and WDE-LSTM models regarding precision, recall, and F1-score, achieving up to 98.26% in F1-score for three-class classification. The consistency analysis also revealed a high alignment between the predicted sentiment and customer ratings, with a consistency rate of 96.00%. These results demonstrate the efficacy of this hybrid architecture in handling complex sentiment classification tasks (SCTs), offering significant improvements in accuracy, classification metrics, and sentiment consistency. The findings have important implications for improving sentiment analysis in customer review systems, contributing to more reliable and accurate sentiment classification.

Understanding the health misinformation dissemination on Twitter: The perspective of tweets-comments consistency

This study investigated users' health misinformation dissemination behaviors from the perspective of tweets-comments consistency. Specifically, we proposed a model that explores the effect of information consistency between tweets and comments, i.e., content consistency and sentiment consistency, on users' health misinformation dissemination behavior, along with the moderating effect of degree of falsehood and perceived severity. By analyzing user-generated health misinformation on Twitter, the results suggest that both content consistency and sentiment consistency positively influence individuals' health misinformation dissemination behavior. Degree of falsehood enhances the effect of content consistency but weakens the impact of sentiment consistency. While perceived severity reduces the effect of sentiment consistency, it doesn't significantly affect the connection between content consistency and sharing. By uncovering the roles of tweets-comments consistency, degree of falsehood, and perceived severity, this study enhances our understanding of health misinformation dissemination during health crises and provides guidance for addressing misinformation.

The impact of sentiment consistency on bank risk: A dual perspective from bank managers and credit rating experts

The article examines the predictive role of the consistency of tone between credit rating experts and bank managers on bank bankruptcy risk and systemic risk. Firstly, the article collected 716 reports, which are the intersection of credit rating reports and bank annual reports of all US commercial banks from 2006 to 2022. Secondly, the FINBERT model was fine-tuned to calculate the tone scores of all reports and the similarity of tones between parties. Empirical analysis revealed that the more positive the tone of credit rating reports, the lower the bankruptcy risk and systemic risk of banks. Furthermore, integrating the perspective of bank managers, the article used a moderation effect experiment to further explore the moderating effect of the tone of bank annual reports and the consistency of tone between parties on the tone of credit rating reports regarding bank risk. The empirical results indicate that the tone of bank annual reports can effectively moderate the predictive effect of credit rating reports on bank risk. Additionally, the consistency of tone index has a significant positive moderating effect on the impact of the tone of credit rating reports on bank risk. This study provides important insights into the exploration of financial text tones on bank bankruptcy risk and systemic risk, suggesting the use of multidimensional text tones for bank risk measurement. It also demonstrates for the first time the importance of consistency of financial text tones in different dimensions in bank risk warning.

PESI: Personalized Explanation recommendation with Sentiment Inconsistency between ratings and reviews

Explainable recommendations aim to generate personalized explanations for suggested items, which are provided based on the historical interactions (e.g., ratings) between users and items. Review contents are often taken as a proxy of explanations. However, most review-based models presume a sentiment consistency between user ratings and review contents, ignoring their inconsistency in real applications. By analyzing three real datasets, we observe that a user may share a positive (negative) opinion to an item in terms of rating value but a negative (positive) sentiment in terms of review content, and such contradicting scenario takes over 40% of all cases in general. To resolve this issue, in this paper we propose a novel explainable recommendation model called PESI, which can generate accurate Personalized Explanations recommendation with the involvement of Sentiment Inconsistency between ratings and reviews. Specifically, PESI consists of three modules: rating prediction, explanation generation, and a novel rating-review inconsistency extraction. The inconsistency extraction module disentangles ratings and reviews, effectively distinguishing both shared and private features, and ensuring accurate disentanglement through contrastive learning objectives. Then, the extracted inconsistent features are injected into the explanation generation module to provide more personalized and higher-quality explanations. The experimental results on the three datasets show that PESI consistently outperforms other competing methods in terms of explanation quality.

Span-based dependency-enhanced graph convolutional network for aspect sentiment triplet extraction

Aspect sentiment triplet extraction task detects three elements of fine-grained sentiment analysis from given sentence, including aspect and opinion terms and their sentiment polarity. Existing methods mainly include tagging-based and span-based methods, where the former show defects on handling overlapped triplets, and the latter could theoretically handle all overlapped triplets but lack of tailored inter-word dependency so that suffer from insufficient span semantic. In this paper, we propose a span-based dependency-enhanced graph convolutional network, which leverages contextual semantic and latent dependency to enrich span representations. Specifically, we devise a latent graph convolutional network to emphasize critical inter-word dependencies and cut off redundant connections in a learnable gating manner, improving the information flow during inter-word interaction. In addition, considering the problem of multi-word term sentiment consistency, we detect effective aspect and opinion terms derived from the output of span enumeration, and introduce term-level interactions by coupling, which meanwhile enables our model to deal with various types of triplets including many-to-one and one-to-many overlapped triplets. Extensive experiments over four benchmark datasets verify that the proposed method outperforms all the baselines with an average F1 improvement of up to 6.13%, and meanwhile shows fine interpretability. The experimental results demonstrate that effectively enhancing token-level and term-level interactions can significantly improve the aspect sentiment triplet extraction performance.

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.

Sentiment analysis in social networks of health institutions

Twitter, a communication platform that creates a social impact; it conveys the messages of non-profit organizations to the masses and the emotions of the masses to non-profit organizations. This research; It aims to examine Twitter posts about health-related non-profit organizations, to determine the emotional states about these institutions on social media and to measure these feelings. 
 Sentiment analysis about WHO, ILO, IOM, UNICEF, FAO, Red Cross, UNDP and UNHCR were carried out using the R program. The tweets used in sentiment analysis were collected by approval of Twitter API. During the study, a total of 310,341 tweets were collected in three periods, November 2019, May 2020 and October 2020. Tweets are classified according to 10 different emotions. One of the main findings of the study is that “positive”, “trust” and “anticipation” feelings are at the top of the tweets shared about these institutions under normal conditions and crisis conditions. Sentiment consistency was tested with Friedman test for each institution after emotional analysis was performed in all institutions (p

Modularized Mutuality Network for Emotion-Cause Pair Extraction

Emotion-cause pair extraction (ECPE) is an emerging task born out of Emotion cause extraction (ECE), which aims to extract the emotion clause and the corresponding cause clause simultaneously. Previous methods decompose ECPE into multiple sub-tasks, namely emotion clause extraction, cause clause extraction, and emotion-cause pair extraction, and employ different modules to address them separately. However, these methods fail to effectively capture the mutuality within the three sub-tasks, which may hinder the information interaction between emotion and cause. In this paper, we revisit and analyze the mutuality between emotion and cause clauses from a linguistic perspective and further propose a novel Modularized Mutuality Network (MMN) to capture the mutuality explicitly. Specifically, the mutuality can be divided into the following categories, including position bias, sentiment consistency, and natural duality. To this end, we design three modules wrapped with various simple but effective mechanisms to address the mutuality, respectively. Extensive experiments demonstrate that MMN achieves state-of-the-art performances on the ECPE task and detailed analyzed the effect of the three modules for capturing the mutuality within sub-tasks.

ALS-MRS: Incorporating aspect-level sentiment for abstractive multi-review summarization

Multi-review summarization, the process of automatically generating a summary for a set of reviews, is of value to customers when they are making informed decisions. Incorporating sentiments can improve the performance of abstractive review summarization, as shown in some prior studies. However, these studies assume that each review contains a single sentiment, which does not reflect reality in many real conditions. In practice, a review always contains many aspects with conflicting sentiments. In this paper, we present ALS-MRS, a novel abstractive multi-review summarization model that combines multi-review representations and aspect-level sentiment. We propose an aspect-level sentiment consistency function to keep the sentiments of the various aspects in the generated summaries the same as those in the reference summaries. Specifically, ALS-MRS constructs aspect-sentiment tuples via an aspect extractor and a sentiment analysis model. In the aspect extractor, the aspects are identified according to the aspect terms obtained by an unsupervised neural attention model, and the sentiment polarity of a sentence about the aspect is detected in the sentiment analysis model. The experimental results, evaluated by automatic and human metrics on two public datasets, show that ALS-MRS performs favorably when compared against many state-of-the-art approaches.

How does social media sentiment impact mass media sentiment? A study of news in the financial markets

AbstractMass media sentiment of financial news significantly influences investment decisions of investors. Hence, studying how this sentiment emerges is important. In years past, this was straightforward, often dictated by journalists who cover financial news, but this has become more complex now. In this paper, we focus on how social media sentiment affects mass media sentiment. Using data from Sina Weibo and Sina Finance (around 60 million weibos and 6.2 million news articles), we show that social media does influence mass media sentiment emergence for financial news. The sentiment consistency between social media reaction and prior news articles amplifies the persistence of mass media sentiment over time. By contrast, we found limited evidence of social media reducing the persistence of mass media sentiment over time. The results have significant implications for understanding how 2 types of media, treated separately in the literature, may be connected.

Microblog sentiment analysis via embedding social contexts into an attentive LSTM

With the rise of microblogging services like Twitter and Sina Weibo, users are able to post various contents on breaking news, public events, or products conveniently and swiftly. These massive contents carry users’ mass sentiment and opinions on various topics, which are a kind of useful and timely source. Traditional microblog sentiment analysis methods often assume that microblogs are independent and identically distributed, they ignore the fact that the microblogs are networked data. Although some methods take the relations between microblogs into consideration, they only use shallow network features which are not sufficient, such as neighbors. Besides, these methods are content-based methods because they cannot use social context information in the prediction stage. To solve this problem, in this paper we use a deep learning method to fully capture the features of microblog relations including both the implicit and explicit ones and use these features to promote microblog sentiment analysis results. Specifically, we first construct a graph which models the relations between microblogs inspired by sentiment consistency and emotional contagion theories. Then we embed the microblog graph and get a continuous vector representation for social contexts of each microblog. After that, we propose a novel neural network to integrate social context knowledge with text information. To handle the problem that different words have different contributions to the classification result, we introduce the attention mechanism into our model. We conduct experiments on three publicly released datasets. The experimental results show that our proposed model can outperform state-of-the-art methods consistently and significantly.

Does the review deserve more helpfulness when its title resembles the content? Locating helpful reviews by text mining

Online review helpfulness has always sparked a heated discussion among academics and practitioners. Despite the fact that research has extensively examined the impacts of review title and content on perceptions of online review helpfulness, the underlying mechanism of how the similarities between a review' title and content may affect review helpfulness has been rarely explored. Based on mere exposure theory, a research model reflecting the influences of title-content similarity and sentiment consistency on review helpfulness was developed and empirically examined by using data collected from 127,547 product reviews on Amazon.com. The TF-IDF and the cosine of similarity were used for measuring the text similarity between review title and review content, and the Tobit model was used for regression analysis. The results showed that the title-content similarity positively affected review helpfulness. In addition, the positive effect of title-content similarity on review helpfulness is increased when the title-content sentiment consistency is high. The title sentiment also negatively moderates the impact of the title-content similarity on review helpfulness. The present research can help online retailers identify the most helpful reviews and, thus, reduce consumers' search costs as well as assist reviewers in contributing more valuable online reviews.

Emergent Sentiment in Financial Markets: Sentiment Flow from Social Media to Mass Media

Mass media sentiment of financial news significantly influences investment decisions of investors. Hence, studying how this sentiment emerges is important. In years past this was straightforward, often dictated by journalists who cover financial news, but this has become more complex now. In this paper we focus on how social media sentiment affects mass media sentiment. Using data from Sina Weibo and Sina Finance (around 60 million weibos and 6.2 million news articles) we show that social media does influence mass media sentiment emergence for financial news. The sentiment consistency between social media reaction and prior news articles amplifies the persistence of mass media sentiment over time. By contrast, we found limited evidence of social media reducing the persistence of mass media sentiment over time. The results have significant implications for understanding how two types of media, treated separately in the literature, may be connected.

A Unified Model for Opinion Target Extraction and Target Sentiment Prediction

Target-based sentiment analysis involves opinion target extraction and target sentiment classification. However, most of the existing works usually studied one of these two sub-tasks alone, which hinders their practical use. This paper aims to solve the complete task of target-based sentiment analysis in an end-to-end fashion, and presents a novel unified model which applies a unified tagging scheme. Our framework involves two stacked recurrent neural networks: The upper one predicts the unified tags to produce the final output results of the primary target-based sentiment analysis; The lower one performs an auxiliary target boundary prediction aiming at guiding the upper network to improve the performance of the primary task. To explore the inter-task dependency, we propose to explicitly model the constrained transitions from target boundaries to target sentiment polarities. We also propose to maintain the sentiment consistency within an opinion target via a gate mechanism which models the relation between the features for the current word and the previous word. We conduct extensive experiments on three benchmark datasets and our framework achieves consistently superior results.

Microblog sentiment analysis with weak dependency connections

With the rise of microblogging services like Twitter and Sina Weibo, users are able to post their real-time mood and opinions conveniently and swiftly. At the same time, the ubiquitous social media results in abundant social relations such as following and follower relations. Social relations create a new source for microblog sentiment analysis, which attracts a great amount of attention in recent years. There are two theories that support the use of social relations for sentiment analysis - sentiment consistency and emotional contagion. However, most existing microblog sentiment analysis methods only employ direct connections which cannot fully use the heterogeneous connections in social media. As online social networks consist of communities and nodes in the same community which form weak dependency connections usually share similarities, we investigate how to exploit weak dependency connections as an aspect of social contexts for microblog sentiment analysis in this paper. In particular, we employ community detection methods to capture weak dependency connections and propose a new model for microblog sentiment analysis which incorporates weak dependency connections, sentiment consistency, and emotional contagion together with text information. Experimental results on two real Twitter datasets demonstrate that our proposed model can outperform baseline methods consistently and significantly.

Learning patterns for discovering domain-oriented opinion words

Sentiment analysis is a challenging task that attracted increasing interest during the last years. The availability of online data along with the business interest to keep up with consumer feedback generates a constant demand for online analysis of user-generated content. A key role to this task plays the utilization of domain-specific lexicons of opinion words that enables algorithms to classify short snippets of text into sentiment classes (positive, negative). This process is known as dictionary-based sentiment analysis. The related work tends to solve this lexicon identification problem by either exploiting a corpus and a thesaurus or by manually defining a set of patterns that will extract opinion words. In this work, we propose an unsupervised approach for discovering patterns that will extract domain-specific dictionary. Our approach (DidaxTo) utilizes opinion modifiers, sentiment consistency theories, polarity assignment graphs and pattern similarity metrics. The outcome is compared against lexicons extracted by the state-of-the-art approaches on a sentiment analysis task. Experiments on user reviews coming from a diverse set of products demonstrate the utility of the proposed method. An implementation of the proposed approach in an easy to use application for extracting opinion words from any domain and evaluate their quality is also presented.