Text Sentiment Analysis Research Articles

Improving sentiment analysis using text network features within different machine learning algorithms

Sentiment analysis poses a significant challenge due to the inherent subjectivity of natural language and the prevalence of unstandardized dialects in social networks. Regrettably, existing literature lacks a dedicated focus on network representation learning for sentiment classification. This paper addresses this gap by investigating ten machine learning algorithms, including support vector machine (SVM), random forest (RF), logistic regression (LR), and Naive Bayes (NB). Our approach integrates text network analysis and sentiment analysis to propose a comprehensive solution. We begin by applying text preprocessing techniques and converting a text corpus into a text network using word co-occurrence. Subsequently, we employ network analysis techniques to extract features based on network topology and node attributes. These network-derived features serve as inputs for sentiment prediction on Yelp reviews. Through the incorporation of diverse text network features and various machine learning algorithms, we achieve significant enhancements in sentiment classification performance. Our evaluation demonstrates an improved area under curve (AUC) of 83% on the Yelp reviews corpus, underscoring the efficacy of integrating network features to enhance sentiment classifiers. This research underscores the critical role of network representation and its potential impact on sentiment analysis, highlighting the prospect of harnessing network features for sentiment classification tasks.

A review of deep learning-based text sentiment analysis research

The study of textual sentiments is a growing subfield of natural language processing. Research on deep learning-based text sentiment analysis approaches has received a lot of interest as machine learning technology has advanced. There are a variety of approaches to analyzing text for sentiment, but they may be broken down into three broad categories: those that rely on neural networks, those that introduce an attention mechanism, and those that rely on pre-trained models. In this paper, the author uses a literature review approach and CNKI as the search engine to examine previous studies on deep learning-based text sentiment analysis methods and models and to categorize the evolution of this field so as to aid in the development of similar studies in the future.

Exploring Customer Review of Local Agriculture Product Acceptance in Malaysia: A Concept Paper on Sentiment Mining

Online consumer reviews in e-commerce are one technique to gather consumer opinion and sentiment about a company's products and services. However, manual analysis is impractical due to natural language text's enormous volume and complexity. Text mining and sentiment analysis methods based on machine learning provide an opportunity to analyze data for marketing objectives by increasing sales, positive electronic word-of-mouth (e-WOM), and meeting consumer demands and wants through the enhancement of market offerings. Despite the numerous benefits of analyzing e-commerce reviews to assist a company's marketing strategy, very little research has focused on sentiment and acceptance for Malaysia’s local agriculture products due to mixed language (English-Malay language) processing challenges. This concept paper highlights the use of text mining techniques to extract valuable insights from e-commerce comments related to Malaysian local agriculture products. By leveraging text mining, the study aims to better understand consumer sentiments, preferences, and feedback regarding local products, thereby facilitating improved market analysis and decision-making processes.

Complex Real-Time Monitoring and Decision-Making Assistance System Based on Hybrid Forecasting Module and Social Network Analysis

Timely short-term spatial air quality forecasting is essential for monitoring and prevention in urban agglomerations, providing a new perspective on joint air pollution prevention. However, a single model on air pollution forecasting or spatial correlation analysis is insufficient to meet the strong demand. Thus, this paper proposed a complex real-time monitoring and decision-making assistance system, using a hybrid forecasting module and social network analysis. Firstly, before an accurate forecasting module was constructed, text sentiment analysis and a strategy based on multiple feature selection methods and result fusion were introduced to data preprocessing. Subsequently, CNN-D-LSTM was proposed to improve the feature capture ability to make forecasting more accurate. Then, social network analysis was utilized to explore the spatial transporting characteristics, which could provide solutions to joint prevention and control in urban agglomerations. For experiment simulation, two comparative experiments were constructed for individual models and city cluster forecasting, in which the mean absolute error decreases to 7.8692 and the Pearson correlation coefficient is 0.9816. For overall spatial cluster forecasting, related experiments demonstrated that with appropriate cluster division, the Pearson correlation coefficient could be improved to nearly 0.99.

Retracted: Sentiment Analysis of International and Foreign Chinese-Language Texts with Multilevel Features

Retracted: Sentiment Analysis of International and Foreign Chinese-Language Texts with Multilevel Features

A novel B&B recommendation method based on improved intuitionistic fuzzy sets

PurposeThis paper aims to propose a bed and breakfast (B&B) recommendation method that takes into account review timeliness and user preferences to help consumers choose the most satisfactory B&B.Design/methodology/approachThis paper proposes a B&B ranking method based on improved intuitionistic fuzzy sets. First, text mining and cluster analysis are combined to identify the concerns of consumers and construct an attribute set. Second, an attribute-level-based text sentiment analysis is established. The authors propose an improved intuitionistic fuzzy set, which is more in line with the actual situation of sentiment analysis of online reviews. Next, subjective-objective combinatorial assignments are applied, considering the consumers’ preferences. Finally, the vlsekriterijumska optimizacija i kompromisno resenje (VIKOR) algorithm, based on the improved score function, is advised to evaluate B&Bs.FindingsA case study is presented to illustrate the use of the proposed method. Comparative analysis with other multi-attribute decision-making (MADM) methods proves the effectiveness and superiority of the VIKOR algorithm based on the improved intuitionistic fuzzy sets proposed in this paper.Originality/valueProposing a B&B recommendation method that takes into account review timeliness and user customization is the innovation of this paper. In this approach, the authors propose improved intuitionistic fuzzy sets. Compared with the traditional intuitionistic fuzzy set, the improved intuitionistic fuzzy set increases the abstention membership, which is more in line with the actual situation of attribute-level sentiment analysis of online reviews.

Short Text Semantic Sentiment Analysis Based on Dual Channel Aspect Attention in Intelligent Systems

Traditional deep learning models for text sentiment analysis fail to fully harness the contextual semantic information of aspect nodes or use prior sentiment resources. This paper proposes a dual channel sentiment analysis model named M2BERT-BLSTM AA that is based on an enhanced Bidirectional Encoder Representations from Transformers(BERT)and Bidirectional Long short-term memory(BLSTM) model and incorporates a Dual Attention Mechanism. Firstly, an emotional resource database is constructed using existing emotional resources. Secondly, vectors are concatenated following mean and max pooling along the dimension of sentence length. These semantic features mitigate evaluation imbalance.Then the text and sentiment information are encoded separately, using distinct Attention Mechanism(Att-M) to extract contextual relationships and emotional features. The model's Aspect-Based multi-class sentiment prediction accuracies on the three Chinese datasets of Meituan ordering, restaurants, and laptops are 75.2%, 87.5%, and 75%, respectively, showing improved performance on sentiment classification.

Switch-Transformer Sentiment Analysis Model for Arabic Dialects That Utilizes a Mixture of Experts Mechanism

In recent years, models such as the transformer have demonstrated impressive capabilities in the realm of natural language processing. However, these models are known for their complexity and the substantial training they require. Furthermore, the self-attention mechanism within the transformer, designed to capture semantic relationships among words in sequences, faces challenges when dealing with short sequences. This limitation hinders its effectiveness in five-polarity Arabic sentiment analysis (SA) tasks. The switch-transformer model has surfaced as a potential substitute. Nevertheless, when employing one-task learning for their training, these models frequently face challenges in presenting exceptional performances and encounter issues when producing resilient latent feature representations, particularly in the context of small-size datasets. This challenge is particularly prominent in the case of the Arabic dialect, which is recognized as a low-resource language. In response to these constraints, this research introduces a novel method for the sentiment analysis of Arabic text. This approach leverages multi-task learning (MTL) in combination with the switch-transformer shared encoder to enhance model adaptability and refine sentence representations. By integrating a mixture of experts (MoE) technique that breaks down the problem into smaller, more manageable sub-problems, the model becomes skilled in managing extended sequences and intricate input–output relationships, thereby benefiting both five-point and three-polarity Arabic sentiment analysis tasks. The proposed model effectively identifies sentiment in Arabic dialect sentences. The empirical results underscore its exceptional performance, with accuracy rates reaching 84.02% for the HARD dataset, 67.89% for the BRAD dataset, and 83.91% for the LABR dataset, as demonstrated by the evaluations conducted on these datasets.

Neuro or Symbolic? Fine-tuned Transformer with Unsupervised LDA Topic Clustering for Text Sentiment Analysis

For text sentiment analysis, state-of-the-art neural language models have demonstrated promising performance. However, they lack interpretability, require vast volumes of annotated data, and are typically specialized for tasks. In this paper, we explore a connection between fine-tuned Transformer models and unsupervised LDA approach to cope with text sentiment analysis tasks, inspired by the concept of Neuro-symbolic AI. The Transformer and LDA models are combined as a feature extractor to extract the hidden representations of the input text sequences. Subsequently, we employ a feedforward network to forecast various sentiment analysis tasks, such as multi-label emotion prediction, dialogue quality prediction, and nugget detection. Our proposed method obtains the best results in the NTCIR-16 dialogue evaluation (DialEval-2) task, as well as cutting-edge results in emotional intensity prediction using the Ren_CECps corpus. Extensive experiments show that our proposed method is highly explainable, cost-effective in training, and superior in terms of accuracy and robustness.

Mining the Sentiment of Online Gaming from Social-Media: A Consumer Insight

The gaming industry has changed since advanced technologies and hardware specifications were able to create the possibility of gaming with connective network or known as online gaming. Some communities are accepting positively, and others are contradicted. Thus, there is an urgency to know the insight from their sentiment. The present research extracts 10 thousand sentiments at social media with sentiment text analysis. The text is interpreted into six based emotions namely anger, disgust, fear, joy, sadness, and surprise. The mining analysis by lexicon valance aware dictionary and sentiment reasoner (VADER) projects the Joy emotions as the domination result with 94.74%. Positive joy expression on online gaming is revealed by extracting the sentiment analysis. In total, ten thousand data were collected from the corpus, which resulted in the happy sentiments that were experienced.

Guide for the application of the data augmentation approach on sets of texts in Spanish for sentiment and emotion analysis.

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features.

Construction and Application of User Check-in Spatiotemporal Knowledge Graph Based on Neo4j

With the rapid acceleration of urbanization and the widespread adoption of social networks, A vast amount of spatiotemporal check-in data from social media users has been generated. Traditional relational databases have limitations in handling massive spatiotemporal data, whereas graph databases, with their efficiency in data querying and processing, offer a novel solution for the analysis of spatiotemporal data. The paper introduces a method for constructing a user check-in spatiotemporal knowledge graph based on the Neo4j graph database, utilizing a designed graph model to create a visual knowledge graph. By incorporating temporal and spatial characteristics into entities, we realize efficient management and complex query of spatiotemporal data of social media user check-ins. By adding sentiment attributes to relationships through sentiment analysis of check-in text, the application of check-in text is realized. Ultimately, employing Cypher to achieve knowledge querying, we analyze the hot spots of urban activities and categories.

A Hybrid Neural Network Model for Sentiment Analysis of Financial Texts Using Topic Extraction, Pre-Trained Model, and Enhanced Attention Mechanism Methods

A Hybrid Neural Network Model for Sentiment Analysis of Financial Texts Using Topic Extraction, Pre-Trained Model, and Enhanced Attention Mechanism Methods

ALGORITMO DE APRENDIZAGEM PROFUNDA COMPREENSIVA PARA COMPREENDER O PAPEL DAS REDES SOCIAIS NA PERCEPÇÃO DO CONSUMIDOR EM RELAÇÃO AO CONSUMO SUSTENTÁVEL

ABSTRACT This research proposes a comprehensive deep-learning algorithm to understand the role of social media in consumer perception of green consumption. After the COVID-19 pandemic, society has shown increased focus on the relationship between people and nature. Achieving sustainable development goals requires promoting green consumption, which necessitates understanding and influencing public attitudes toward sustainability. While previous studies have explored green consumption using behavioral models and surveys, they often overlook the perspective of social media. This study uses deep learning techniques to analyze social media data, including text and video content, to gain insights into consumer behavior and preferences. The study entails collecting data from X (former Twitter) and YouTube, developing deep learning algorithms for text classification, and creating a visualization and reporting system. More specifically, this study aims to analyze the impact of social media information sharing on society’s green purchasing intentions and proposes advanced architectures for text mining specifically the LDA method. This study highlights the valuable insights from analyzing social media discourse on green consumption. Trends, emotional attitudes, and engagement were examined using text mining and sentiment analysis. The study reveals platform-specific differences in sentiment and identifies influential keywords and phrases. The analysis also uncovers emotional responses and key factors associated with the discourse on green consumption. The findings can inform future strategies for promoting sustainable consumption. The study concludes by emphasizing the importance of further research to explore the discrepancies between platforms and harness the implications of these findings for sustainable consumption strategies.

Research on Strategies of Digital Media in Shaping and Communicating City Image--Text Mining and Sentiment Analysis Based on Image Communication

Abstract Shaping and spreading a good city image can effectively improve the comprehensive strength of the city, promote investment attraction, promote the development of the tourism industry, and help social civilization and harmony. The research utilizes the TextRank algorithm for text mining of city images. Construct an emotional analysis model for city images, using the calculation of emotional tendencies, to make a comprehensive evaluation of the city’s image communication. For example analysis of Hangzhou city, the overlap rate of high-frequency words between city officials and tourists on Hangzhou’s city image reaches 43.3%. The two perceptions of the imagery of Hangzhou are both cross and different, and the overall satisfaction score of tourists in Hangzhou is 3.84 points. Most of the tourists in Hangzhou commented positively, and the percentage of positive, neutral, and negative sentiment comments accounted for 81.17%, 4.50%, and 14.33% of the overall, respectively.

The joint effect of online reviews and manager responses in driving company ratings

The current study extends the literature on firm-customer online relationship building by jointly assessing customers' opinions and firms' responses to understand their impact on firm ratings. This study implements text analytics and sentiment analysis on customer reviews and manager responses. Specifically, the impact of message sentiment (emotional versus rational) and textual characteristics of online reviews and manager responses is examined. Finally, the assessment focuses on the impact of hotel customer reviews and manager responses sentiment on hotel ratings. Data collection implements a web crawler to gather a consistent panel of user-level activity from TripAdvisor. The final data includes customer reviews, manager responses, and hotel ratings over a three-year period. Current contributions provide further insights into how companies can utilize online reviews and manager responses to increase online ratings of their firms. Managerial implications suggest using emotional responses with short sentences to improve online ratings.

Тональність художньої прози як вияв особливостей перекладу

The paper is devoted to the peculiarities of sentiment analysis of texts. The necessity to take into account the tone as an important component of the text’s content to achieve equivalence in literary translation and ensure the preservation of the emotional and expressive background and expressiveness of the original is substantiated. The importance of automating the processes of detecting the text’s tone to obtain better and more accurate results is determined. The paper outlines the main methods of preprocessing textual information and identifies a set of the most popular machine learning approaches that can be used for tone classification. In particular, the attention is focused on the Bag-of-Words, TF-IDF Vectorizer, and Word2Vec models used to convert textual data into numerical data. Classifier algorithms are analysed as a further step in data processing (in particular, Bayesian, maximum entropy, support vectors, etc.). The advantages of the LIWC-22 software, which has proven itself and has been successfully tested with the involvement of experts in psychology, sociology and linguistics, are described separately. Using the above-mentioned lexicon, a sentiment analysis of three versions of Y. Vynnychuk's short story («The Embroidered World») translations into English (author's translation by M. Naidan and automated translations by Google and DeepL) is carried out. The total number of words is established, and the indicators of authenticity and tone (in the binary coordinate system «positive/negative») of each translation option are determined. Prospects for further research in the field of sentiment analysis for the interpretation of original and translated texts are formulated.

Spider Monkey Optimization with Deep Learning-based Hindi Short Text Sentiment Analysis

Sentiment analysis (SA) intends to categorize a text respective to sentimental polarity of individual opinions, like neutral, positive, or negative. The study of Hindi is limited because of the grammatical and morphological complexities of the Hindi language while many research work concentrates on drawing features from English text. The hindi languages make the sentiment classification procedure for Hindi short text a tedious process. The Hindi language has complicated morphology and variation based on phonetics, spelling, and vocabulary; the common usage of numerous dialects between Hindi in India produces a massive volume of glossaries. In this study, we introduce a Spider Monkey Optimization with stacked recurrent neural network (SMO-SRNN) for short text SA on Hindi Corpus. The proposed SMO-SRNN technique mainly aims to identify and categorize the Hindi short text into three distinct classes, namely negative, positive, and neutral. In the presented SMO-SRNN method, the SRNN approach is exploited for the investigation and classification of sentiment. Moreover, the SMO model is employed to finetune the hyperparameter related to the SRNN model. A detailed set of experiments is applied to ensure the high efficiency of the SMO-SRNN algorithm. The comparative outcome highlighted the enhancement of the SMO-SRNN technique over other methods.

Enhancing collaborative learning in psychoeducation through social network analysis

Abstract Social network opens up a practical new path for psychoeducation and, with the help of a multimedia mobile terminal’s network, text sentiment analysis for students’ mental health problem revelation and constructing corresponding psychoeducation model. Based on the above viewpoint, this paper proposes a semi-supervised learning method for sentiment analysis using graphs. Specifically, a graph-based semi-supervised learning classifier is constructed using the “Weibo-Weibo” relationship graph. At the same time, social network and text similarity relationships are combined. A link between annotated and unannotated texts was established, and an optimization algorithm was used to solve the model, revealing the psychological problems of students under the emotional texts of social networks, thus constructing a corresponding “four-in-one” mental health education model, which enhances the collaborative learning of students and the four major organizations in psychoeducation. The accuracy, accuracy, recall, and F1 value are outperformed by the model in this paper by 2.44%, 2.11%, 1.45%, and 2.34%, respectively. The eight questions designed around the three dimensions of collaborative learning situation, learning effectiveness, and four-in-one teaching model were highly rated by students. The four-in-one teaching model that utilizes social network sentiment analysis effectively enhances students’ collaborative learning and improves their ability to solve psychoeducation’s difficulties.

Fine-Grained Emotional Calculation of Emotional Expression in Modern Visual Communication Designs

Abstract In the context of the information age, mining for emotions has become a popular topic today, and deep learning plays an important role in the task of sentiment analysis. In this study, we propose a LE-CNN-MBiLSTM fine-grained sentiment analysis model for the task of fine-grained sentiment computation for emotional expression in visual communication design. The model combines the ERNIE model and introduces a parallel CNN and dual-channel BiLSTM structure, which first mines multiple local key features in the text with CNN, then extracts the contextual semantics with BiLSTM, and extracts the fusion features by CNN-BiLSTM. Fine-grained sentiment analysis tasks are well-served by the model in this paper, with an accuracy of 93.58% and a loss function value of 0.18, respectively. Using the model to analyze the corpus of comments on visual communication design works, positive and negative emotions dominated the samples, each accounting for 50%, and the expression of sadness was particularly prominent. The model in this paper can be applied in fine-grained sentiment computation for visual communication design and can be migrated to other natural language processing domains, thus providing a new idea for the construction of network models for text sentiment analysis.