Sentiment Extraction Research Articles

Fusing semantic and syntactic information for aspect sentiment triplet extraction

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

A Stacking Ensemble Based on Lexicon and Machine Learning Methods for the Sentiment Analysis of Tweets

Sentiment is employed in various fields, such as collecting web-based opinions for the formulation of governmental policies, measuring employee and customer satisfaction levels in business organizations, and measuring the sentiment of the public in political and security matters. The field has recently faced new challenges since algorithms must operate with highly unstructured sentiment data from social media. In this study, the authors present a new stacking ensemble method that combines the lexicon-based approach with machine learning algorithms to improve the sentiment analysis of tweets. Due to the complexity of the text with very ill-defined syntactic and grammatical patterns, using lexicon-based techniques to extract sentiment from the content is proposed. On the same note, the contextual and nuanced aspects of sentiment are inferred through machine learning algorithms. A sophisticated bat algorithm that uses an Elman network as a meta-classifier is then employed to classify the extracted features accurately. Substantial evidence from three datasets that are readily available for public analysis re-affirms the improvements this innovative approach brings to sentiment classification.

Graph-based stock prediction with multisource information and relational data fusion

With the application of multisource information in different fields, the combination of different types of information, such as numerical data and text information, has become a favourable choice for performing stock market analyses. Despite the rich information provided by multisource data, building structured relationships remains challenging. In addition, some market relationship-based analysis methods use a predefined graph structure as a stock relationship graph, which makes it impossible to sensitively aggregate attribute features, and these methods cannot dynamically update market relationships or relationship strengths. In this paper, we propose a novel dynamic attribute-driven graph attention network incorporating sentiment (AGATS) information, transaction data, and text data. Inspired by behavioural finance, we separately extract sentiment information as a factor of technical indicators, and further realize the early fusion of technical indicators and textual data through tensor fusion. In particular, real-time intramarket dependencies and key attribute information are captured with graph networks, enabling dynamic relationship and relationship strength updates. Experiments conducted on real datasets show that our model is capable of ourperforming previously developed methods in prediction and trading.

Understanding critical service factors in neobanks: crafting strategies through text mining

Purpose This study aims to analyse and understand customer sentiments and perceptions from neobanking mobile applications by using advanced machine learning and text mining techniques. Design/methodology/approach This study explores a substantial large data set of 330,399 user reviews available in the form of unstructured textual data from neobanking mobile applications. This study is aimed to extract meaningful patterns, topics, sentiments and themes from the data. Findings The results show that the success of neobanking mobile applications depends on user experience, security features, personalised services and technological innovation. Research limitations/implications This study is limited to textual resources available in the public domain, and hence may not present the entire range of user experiences. Further studies should incorporate a wider range of data sources and investigate the impact of regional disparities on user preferences. Practical implications This study provides actionable ideas for neobanking service providers, enabling them to improve service quality and mobile application user experience by integrating customer input and the latest trends. These results can offer important inputs to the process of user interaction design, implementation of new features and customer support services. Originality/value This study uses text mining approaches to analyse neobanking mobile applications, which further contribute to the growing literature on digital banking and FinTech. This study offers a unique view of consumer behaviour and preferences in the realm of digital banking, which will add to the literature on the quality of service concerning mobile applications.

The role of news sentiment in salmon price prediction using deep learning

This paper employs deep learning models and sentiment analysis to predict salmon spot prices. Our data includes historical price data and sentiment scores from 2018 to 2022. We extract sentiment scores from salmon-related news headlines by using FinBERT and TextBlob. We begin with price prediction using only historical price data and then introduce sentiment scores to improve the prediction accuracy of deep learning models. We find that the prediction performance of deep learning models outperforms traditional prediction methods in the salmon market. Our primary hybrid CNN-LSTM model outperforms other deep learning models and traditional models. Additionally, deep learning models incorporating sentiment scores exhibit reduced prediction errors. Our findings confirm the value of sentiment information in improving forecasting performance. These findings highlight the effectiveness and robustness of our CNN-LSTM model combined with sentiment analysis for price prediction in the salmon market.

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

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

A Sentiment Analysis Approach for Exploring Customer Reviews of Online Food Delivery Services: A Greek Case

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop.

Sentiment-semantic word vectors: A new method to estimate management sentiment

This paper introduces a novel method to extract the sentiment embedded in the Management’s Discussion and Analysis (MD &A) section of 10-K filings. The proposed method outperforms traditional approaches in terms of sentiment classification accuracy. Utilizing this method, the MD &A sentiment is found to be a strong negative predictor of future stock returns, demonstrating consistency in both in-sample and out-of-sample settings. By contrast, if traditional sentiment extraction methods are used, the MD &A sentiment exhibits no predictive ability for stock markets. Additionally, the MD &A sentiment is associated with dividend-related macroeconomic channels regarding future stock return prediction.

Automated Disaster Monitoring From Social Media Posts Using AI-Based Location Intelligence and Sentiment Analysis

Worldwide disasters like bushfires, earthquakes, floods, cyclones, and heatwaves have affected the lives of social media users in an unprecedented manner. They are constantly posting their level of negativity over the disaster situations at their location of interest. Understanding location-oriented sentiments about disaster situation is of prime importance for political leaders, and strategic decision-makers. To this end, we present a new fully automated algorithm based on artificial intelligence (AI) and natural language processing (NLP), for extraction of location-oriented public sentiments on global disaster situation. We designed the proposed system to obtain exhaustive knowledge and insights on social media feeds related to disaster in 110 languages through AI- and NLP-based sentiment analysis, named entity recognition (NER), anomaly detection, regression, and Getis Ord Gi* algorithms. We deployed and tested this algorithm on live Twitter feeds from 28 September to 6 October 2021. Tweets with 67 515 entities in 39 different languages were processed during this period. Our novel algorithm extracted 9727 location entities with greater than 70% confidence from live Twitter feed and displayed the locations of possible disasters with disaster intelligence. The rates of average precision, recall, and F₁-Score were measured to be 0.93, 0.88, and 0.90, respectively. Overall, the fully automated disaster monitoring solution demonstrated 97% accuracy. To the best of our knowledge, this study is the first to report location intelligence with NER, sentiment analysis, regression and anomaly detection on social media messages related to disasters and has covered the largest set of languages.

Exploratory Data Analytics of Air Pollutant Data for Air Quality Management Application

Purpose: With escalating concerns over the detrimental impacts of air pollution on public health and the environment, this study embarks on a comprehensive exploration of air quality dynamics, focusing on Ogun state metropolis of Nigeria. The primary objective is to contribute to the burgeoning field of air quality management by harnessing the power of data analytics, exploratory data analysis, and advanced python programming libraries. The study seeks to address critical questions regarding the current state of air quality, major sources of pollution, government interventions, and individual contributions to better air quality. Methodology: The research employs Exploratory Data Analysis to unveil intrinsic patterns and trends within historical air quality datasets extracted from IoT devices located across Ogun state. This initial phase aims to discern key statistical parameters, including mean concentrations, variations, and correlations among various pollutants. Subsequently, the study employs Topic Modeling to extract latent themes and sentiments from qualitative data, specifically focusing on public opinions gathered through digital surveys. Resulting topics provide insights into public perceptions regarding air quality, pollution sources, and the efficacy of governmental interventions. Findings: Experimental result is revealing of the diversity of the dataset. The EDA returned a mean Particulate Matter concentration of approximately 12.65 µg/m³, while the mean Nitric Oxide concentration is approximately 13.56 µg/m³. Notable correlations include a strong positive correlation between PM2.5 and PM10 (0.69), indicating a substantial association between fine and coarse particulate matter. Additionally, there is a noteworthy positive correlation between NO and Nox (0.97), suggesting a high degree of correlation between nitric oxide and nitrogen oxide levels. However, negative correlations are observed, such as the substantial negative correlation between RH (relative humidity) and PM2.5 (-0.46), implying an inverse relationship between humidity and fine particulate matter levels. The study develops an innovative air quality management application. Unique Contribution to Theory, Practice and Policy: The application aims to empower both the public and policymakers with actionable insights, fostering informed decision-making and collaborative efforts towards improving air quality. It is highly recommended that industry experts should continue to imbibe ethical standards in data acquisition and deployment practices.

Corporate financial distress prediction using the risk-related information content of annual reports

This study presents a financial distress prediction model focusing on the linguistic analysis of risk-related sections of corporate annual reports. Here, we introduce a novel methodology that leverages BERT-based contextualized embedding models for nuanced extraction of financial sentiment and topic coherence. This stands in contrast to existing research, which predominantly relies on dictionary-based or non-contextual word embeddings and addresses their limitations in context sensitivity. Furthermore, we apply an innovative financial distress prediction model that combines the robust XGBoost algorithm with unsupervised outlier detection techniques. This hybrid model is specifically designed to tackle the issue of class imbalance, a persistent challenge in financial distress prediction. The efficacy of the proposed model is empirically validated using a comprehensive dataset of 2545 companies listed on major global stock exchanges. Our findings indicate that the introduced model not only significantly outperforms most existing state-of-the-art financial distress prediction models in terms of predictive accuracy, but also significantly outperforms the Loughran & McDonald dictionary-based approach and the Word2Vec model, underlining its potential as a superior analytical tool for financial distress prediction.

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

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

Longitudinal Sentiment Analysis with Conversation Textual Data

AbstractThe inherent qualitative nature of textual data poses significant challenges for direct integration into statistical models. This paper presents a two-stage process for analyzing longitudinal textual data, offering a solution to this inherent challenge. The proposed model comprises (1) initial data preprocessing and sentiment extraction, followed by (2) applying a growth curve model to analyze the extracted sentiments directly. The paper also explores four distinct approaches for extracting sentiment scores in the dialogue, providing versatility to the proposed framework. The practical application of the proposed model is demonstrated through the analysis of an empirical longitudinal textual dataset. This framework offers a valuable contribution to the field by addressing the challenges associated with modeling qualitative textual data, providing a robust methodology for extracting and analyzing sentiments longitudinally.

The social media sentiment analysis framework: deep learning for sentiment analysis on social media

Researching public opinion can help us learn important facts. People may quickly and easily express their thoughts and feelings on any subject using social media, which creates a deluge of unorganized data. Sentiment analysis on social media platforms like Twitter and Facebook has developed into a potent tool for gathering insights into users' perspectives. However, difficulties in interpreting natural language limit the effectiveness and precision of sentiment analysis. This research focuses on developing a social media sentiment analysis (SMSA) framework, incorporating a custom-built emotion thesaurus to enhance the precision of sentiment analysis. It delves into the efficacy of various deep learning algorithms, under different parameter calibrations, for sentiment extraction from social media. The study distinguishes itself by its unique approach towards sentiment dictionary creation and its application to deep learning models. It contributes new insights into sentiment analysis, particularly in social media contexts, showcasing notable advancements over previous methodologies. The results demonstrate improved accuracy and deeper understanding of social media sentiment, opening avenues for future research and applications in diverse fields.

We care: A User-Focused Sentiment Analysis Framework for Social Media Interactions

This paper addresses the sentiment analysis of WhatsApp chats, focusing on the challenges and opportunities presented by conversational data. The introduction outlines the prevalence of sentiment analysis in social media platforms and the significance of accurate sentiment categorization. The literature review highlights previous work in sentiment analysis, emphasizing methods for categorizing sentiment polarity and feature selection. The proposed system introduces a comprehensive approach to sentiment analysis tailored to WhatsApp chats, considering the unique characteristics of conversational data. Key features include user-centric inclusion, nuanced extraction of sentiment, context-aware analysis, and effective handling of conversational nuances. The method section details the proposed system's emphasis on real-time sentiment tracking, user-specific sentiment scores, and integration with WhatsApp's API for broader applications. The results section summarizes the positive outcomes of the proposed method, including user-centric inclusion, nuanced extraction, context-aware illustration, and effective content handling. The future scope section discusses potential enhancements such as real-time sentiment alerts, multilingual support, detailed sentiment analysis, improved user feedback systems, personalized sentiment metrics, and collaboration capabilities. The conclusion highlights the significance of the "WeCare" sentiment analysis project in improving our understanding of digital conversations, particularly within the context of WhatsApp chats. The project's commitment to user-centric design, adaptability, and ethical considerations positions it as a dynamic tool for enhancing digital interactions and well-being. Finally, acknowledgments recognize the contributions of the development team and academic mentor.

Discovering Untapped Potential in Finance Markets Using NLP-Driven Sentiment Analysis

Objectives: The main objective in Sentiment Analysis, and financial data is to decode sentiments through the use of Natural Language Processing (NLP) and Machine Learning (ML). This provides insights into market trends that are essential for risk management and well-informed financial decisions. By removing emotion from financial writing, gives stakeholders practical advice for wise investments in dynamic markets. The main objective is to increase the accuracy of Multinomial Naïve Bayes (Multinomial NB). In this work, we used purely ML models to get the accuracy more than the previous works, which got 74%, and in this work, we can see the accuracy increased to approximately 82%. Methods: This specific Research Work employs Machine Learning approaches to extract sentiment polarity (positive, negative, and neutral) from financial text data. The used ML models are- Multinomial Naïve Bayes (Multinomial NB), Logistic Regression (LR), KNeighbors, Decision Tree, and Random Forest algorithms are used for Sentiment Analysis. Findings: Studies conducted in the financial sector have shown that sentiment and informational substance in stock news have a big impact on market factors such as trading volume, volatility, stock prices, and corporate earnings. This study involves approximately 6000 newspaper articles to extract the polarity from financial text data. The incorporation of Multinomial NB of Natural Language Processing techniques results in a marginal improvement in the sentiment classification model performance among all the models used, where the previous works got the lowest accuracy of 74%. Novelty: This research introduces advanced ML models for extracting financial sentiment from text, including Random Forest, LR, KNeighbors, Decision Tree, and Multinomial NB previously unexplored in similar studies. Notably, the Multinomial NB model accuracy rose significantly from 65% to 82%. The study also presents sentiment segregation (positive, negative, neutral) visualized in a donut chart. Keywords: Sentiment Analysis, Machine Learning, Natural Language Processing, Financial data, Stock market prediction

CRAS: cross-domain recommendation via aspect-level sentiment extraction

CRAS: cross-domain recommendation via aspect-level sentiment extraction

Hierarchical denoising representation disentanglement and dual-channel cross-modal-context interaction for multimodal sentiment analysis

Multimodal sentiment analysis aims to extract sentiment cues from various modalities, such as textual, acoustic, and visual data, and manipulate them to determine the inherent sentiment polarity in the data. Despite significant achievements in multimodal sentiment analysis, challenges persist in addressing noise features in modal representations, eliminating substantial gaps in sentiment information among modal representations, and exploring contextual information that expresses different sentiments between modalities. To tackle these challenges, our paper proposes a new Multimodal Sentiment Analysis (MSA) framework. Firstly, we introduce the Hierarchical Denoising Representation Disentanglement module (HDRD), which employs hierarchical disentanglement techniques. This ensures the extraction of both common and private sentiment information while eliminating interference noise from modal representations. Furthermore, to address the uneven distribution of sentiment information among modalities, our Inter-Modal Representation Enhancement module (IMRE) enhances non-textual representations by extracting sentiment information related to non-textual representations from textual representations. Next, we introduce a new interaction mechanism, the Dual-Channel Cross-Modal Context Interaction module (DCCMCI). This module not only mines correlated contextual sentiment information within modalities but also explores positive and negative correlation contextual sentiment information between modalities. We conducted extensive experiments on two benchmark datasets, MOSI and MOSEI, and the results indicate that our proposed method offers state-of-the-art approaches.

An Online Hotel Selection Method With Three-Dimensional Analysis of Reviews' Helpfulness

The multi-attribute decision-making method based on online reviews has been widely used in addressing the hotel selection problem. However, due to information overload and the presence of fake reviews, traditional hotel selection methods that rely solely on unverified review analysis can affect the outcome of hotel selections. In this study, a novel three-dimensional helpful review analysis model based multi-attribute decision-making approach for hotel selection is established. Firstly, a new three-dimensional helpful review analysis model that effectively filters out sentiment inconsistency reviews, topic inconsistency reviews, and reviews from invalid sources is proposed. Secondly, this study employs TF-IDF and LDA to extract attributes for hotel selection. We further utilize BERT to extract sentiment level for each attribute. Then, a ranking result for alternative hotels is obtained using a combination compromise solution method (CoCoSo). Finally, we demonstrate its effectiveness and feasibility through a case study of selecting the optimal hotel from TripAdvisor.com.

A Multimodal Sentiment Analysis Approach Based on a Joint Chained Interactive Attention Mechanism

The objective of multimodal sentiment analysis is to extract and integrate feature information from text, image, and audio data accurately, in order to identify the emotional state of the speaker. While multimodal fusion schemes have made some progress in this research field, previous studies still lack adequate approaches for handling inter-modal information consistency and the fusion of different categorical features within a single modality. This study aims to effectively extract sentiment coherence information among video, audio, and text and consequently proposes a multimodal sentiment analysis method named joint chain interactive attention (VAE-JCIA, Video Audio Essay–Joint Chain Interactive Attention). In this approach, a 3D CNN is employed for extracting facial features from video, a Conformer is employed for extracting audio features, and a Funnel-Transformer is employed for extracting text features. Furthermore, the joint attention mechanism is utilized to identify key regions where sentiment information remains consistent across video, audio, and text. This process acquires reinforcing features that encapsulate information regarding consistency among the other two modalities. Inter-modal feature interactions are addressed through chained interactive attention, and multimodal feature fusion is employed to efficiently perform emotion classification. The method is experimentally validated on the CMU-MOSEI dataset and the IEMOCAP dataset. The experimental results demonstrate that the proposed method significantly enhances the performance of the multimodal sentiment analysis model.