Accuracy Of Sentiment Classification Research Articles

Multi task opinion enhanced hybrid BERT model for mental health analysis

Understanding the nuanced emotions and points of view included in user-generated content remains challenging, even though text data analysis for mental health is a crucial instrument for assessing emotional well-being. Most current models neglect the significance of integrating viewpoints in comprehending mental health in favor of single-task learning. To offer a more thorough knowledge of mental health, in this study, we present an Opinion-Enhanced Hybrid BERT Model (Opinion-BERT), built to handle multi-task learning for simultaneous sentiment and status categorization. With the help of TextBlob and SciPy, we extracted opinions and dynamically constructed new opinion embeddings to complement the pre-trained BERT model. Using a hybrid architecture, these embeddings are integrated with the contextual embeddings of BERT, whereby the CNN and BiGRU layers collected local and sequential characteristics. This combination helps our model to identify and categorize user status and attitudes from the text more accurately, which leads to more accurate mental health assessments. When we compared the performance of Opinion-BERT to some baseline models, including BERT, RoBERTa, and DistilBERT, we found that it performed much better. Opinion-enhanced embeddings are crucial for improving performance, as demonstrated by our multi-task learning framework’s 96.77% sentiment classification accuracy of 94.22% status classification accuracy. This work provides a more nuanced understanding of emotions and psychological states by demonstrating the potential of combining opinion and sentiment data for mental health analysis in a multi-task learning environment.

Sentiment Classification on the 2024 Indonesian Presidential Candidate Dataset Using Deep Learning Approaches

This study aims to compare the performance of three deep learning models (LSTM, BiLSTM, and GRU) in the task of sentiment classification for the 2024 Indonesian Presidential Candidate dataset, focusing specifically on the case of Prabowo Subianto. The dataset comprises social media X posts sourced from kaggle, and the analysis investigates the effectiveness of different variants of recurrent neural network architectures in identifying public sentiment. The models were evaluated on accuracy and F1 score. The results demonstrate that BiLSTM outperformed both LSTM and GRU models in all metrics, achieving a testing accuracy of 80.70% and an F1 score of 86.86%, compared to LSTM and GRU which both achieved a testing accuracy of 72.56% and an F1 score of approximately 84%. The higher performance of BiLSTM is attributed to its ability to capture bidirectional context within the text, thereby understanding complex sentiment patterns more effectively. LSTM and GRU models displayed similar performance, therefore BiLSTM is the best model for this dataset. These results indicate that BiLSTM is especially well-suited for analyzing public sentiment towards political figures like Prabowo Subianto, offering significant insights into public discussions surrounding the 2024 Indonesian Presidential Election. This study recommends exploring transformer-based models like BERT or GPT variants to enhance sentiment classification accuracy in this domain.

AI-Driven Sentiment Classification via Combinatorial Techniques and Reasoning

This paper proposes an AI-driven approach to sentiment analysis, leveraging mathematical concepts such as permutations, along with logical reasoning techniques. The method involves splitting the text; permutations are used to extract n-grams. AI-driven logic is then applied for feature scoring. Finally, fuzzy logic integrates these scores to classify sentiments. This approach focuses on enhancing sentiment classification accuracy by blending AI-based features.

Sentiment Analysis of Product Reviews Using Machine Learning and Pre-Trained LLM

Sentiment analysis via artificial intelligence, i.e., machine learning and large language models (LLMs), is a pivotal tool that classifies sentiments within texts as positive, negative, or neutral. It enables computers to automatically detect and interpret emotions from textual data, covering a spectrum of feelings without direct human intervention. Sentiment analysis is integral to marketing research, helping to gauge consumer emotions and opinions across various sectors. Its applications span analyzing movie reviews, monitoring social media, evaluating product feedback, assessing employee sentiments, and identifying hate speech. This study explores the application of both traditional machine learning and pre-trained LLMs for automated sentiment analysis of customer product reviews. The motivation behind this work lies in the demand for more nuanced understanding of consumer sentiments that can drive data-informed business decisions. In this research, we applied machine learning-based classifiers, i.e., Random Forest, Naive Bayes, and Support Vector Machine, alongside the GPT-4 model to benchmark their effectiveness for sentiment analysis. Traditional models show better results and efficiency in processing short, concise text, with SVM in classifying sentiment of short length comments. However, GPT-4 showed better results with more detailed texts, capturing subtle sentiments with higher precision, recall, and F1 scores to uniquely identify mixed sentiments not found in the simpler models. Conclusively, this study shows that LLMs outperform traditional models in context-rich sentiment analysis by not only providing accurate sentiment classification but also insightful explanations. These results enable LLMs to provide a superior tool for customer-centric businesses, which helps actionable insights to be derived from any textual data.

Comparative Analysis of Machine Learning and Deep Learning Models for Aspect-based Sentiment Analysis in Education

Aspect-Based Sentiment Analysis (ABSA) has emerged as a powerful technique for analyzing student feedback in educational settings, providing a deeper understanding of sentiments linked to specific aspects such as course content, instructor performance, assessment quality and technology support. Unlike traditional sentiment analysis, ABSA enables granular insights by extracting multiple aspects from a single review and assigning sentiments to each aspect independently. This study evaluates the performance of traditional Machine Learning (ML) models, including Logistic Regression (LR), Support Vector Machines (SVM), Naïve Bayes (NB), Random Forest (RF) and Gradient Boosting (GB), alongside advanced Deep Learning (DL) models such as Multi-Layer Perceptron (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers (BERT). The focus is on addressing the challenge of handling multiple aspects per review and performing aspect-specific sentiment classification. Experimental results demonstrate that BERT significantly outperforms other models in both tasks, offering superior precision, recall and F1-scores. Notably, BERT excels in handling complex, multi-aspect feedback, providing more accurate sentiment classification for each aspect. These findings highlight the importance of leveraging advanced models to analyze educational feedback effectively, enabling institutions to implement targeted improvements in key areas of learning and teaching.

Sentiment Analysis of Online Reviews: A Machine Learning Based Approach with TF-IDF Vectorization

Nowadays, online reviews wield considerable influence over consumer decision-making processes. Surveys show 84% of people compare their trustworthiness to recommendations from personal connections in these online reviews. Online reviews of services or destinations can significantly benefit the tourism industry. Therefore, our primary intent of this study is to leverage Machine Learning (ML) and Natural Language Processing (NLP) for sentiment analysis of hotel reviews in Jordan in order to assist both hotel owners and tourists. In this study, we proposed a ML-based approach using Support Vector Machine (SVM) and TF-IDF to perform sentiment analysis of hotel reviews into positive or negative. In addition, our experiments were performed using our real dataset, “JOHotelRating”, which was gathered in the Jordanian context. In the feature extraction stage, we utilized the Term Frequency-Inverse Document Frequency (TF-IDF) method. In the machine learning (ML) classification phase, we utilized various algorithms such as Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), Bernoulli’s Naïve Bayes (BNB), Decision Tree (DT), and Random Forest (RF). SVM with TF-IDF for feature extraction, emerged as the standout performer, achieving an impressive 97% accuracy in sentiment classification. Our proposed approach offers the hotel owners a time-saving method to identify positive and negative reviews, allow them to understand trends, and enhance the overall customer experience. On the tourist side, the study attempts to tackle the challenge of comprehending numerous reviews by providing sentiment analysis, ultimately aiding them in making better-informed decisions when selecting a hotel in Jordan.

The Classification Method is Used for Sentiment Analysis in My Telkomsel

User reviews significantly impact how mobile apps are perceived and provide developers with valuable insights into improving the functionality and quality of their products. Sentiment analysis of these evaluations helps identify the main issues faced by consumers, such as technical difficulties, costs, and service levels. The main objective of this study is to classify user sentiment into positive and negative categories, focusing on the MyTelkomsel app. With the use of Google Play Scraper, 39,493 reviews on various app versions and user experiences were collected. This data was analyzed using multiple machine learning models, including Support Vector Machines (SVM), Naive Bayes, Random Forest, and Gradient Boosting, alongside the Natural Language Processing (NLP) approach. The results show that 39.2% of the reviews are positive, while 60.8% reflect negative sentiment. Among the models, SVM showed the highest accuracy in sentiment classification with a value of (0.854792), while Naive Bayes (0.775541), Random Forest (0.829725), and Gradient Boosting (0.819344) also performed well in sentiment classification. These findings suggest that developers can leverage the insights gained from this analysis to proactively improve the performance and user experience of the MyTelkomsel app, by addressing technical and service-related issues identified in user reviews.

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.

Sentiment Analysis and Rating Predicting for Hotel Review

This paper provides a comprehensive system for sentiment analysis and rate prediction of hotel reviews, combining modern natural language processing techniques with machine learning algorithms. The major purpose is to automatically assess consumer input and forecast related scores based on textual reviews. The system employs regression models to predict star ratings from the textual data and sentiment analysis to categorise reviews into good, negative, or neutral categories. The dataset consists of a large corpus of hotel reviews collected from various online platforms. Experimental results demonstrate the effectiveness of the proposed approach, with high accuracy in sentiment classification and rating prediction. The findings indicate that automated sentiment analysis and rating prediction can provide valuable insights for hotel management, helping to enhance customer satisfaction and improve sequence.

The Use of Naïve Bayes Algorithm in Sentiment Analysis of Grab Application Reviews

This study aims to analyze the sentiment of Grab application user reviews using the Naïve Bayes algorithm. In conducting the analysis, how well the Naïve Bayes algorithm can analyze Grab application user review data. Thus, this process refers to the elements that affect the accuracy of the Naïve Bayes analysis. to analyze the sentiment of Grab application user reviews using the Naïve Bayes algorithm. Thus, it not only evaluates the accuracy of the Naïve Bayes method, but also considers the problem of imbalanced class, because in reality not all datasets can be accessed perfectly. To consider the problem of data imbalance, this study requires the Adaptive Synthetic Sampling or ADASYN technique which is used in machine learning to overcome the problem of class imbalance in the dataset. The tools used in processing the algorithm in the method and conducting the analysis use Google Colab. This study focuses on the classification of positive and negative sentiments from user reviews taken by the scraping process from the Google Play Store platform. The analysis process involves data preprocessing, including tokenization, stemming, and word weighting, to improve the accuracy of sentiment classification. Based on the results of this study, the Naïve Bayes model sought an accuracy result of 85.33%, the precision result obtained was 80.55% and the recall result in this research test was 79.09%, from these results by implementing calculations using a confusion matrix and dividing the data into testing data and training data

Web Semantic-Enhanced Multimodal Sentiment Analysis Using Multilayer Cross-Attention Fusion

Aiming at the existing multimodal sentiment analysis approaches, which include inadequate extraction of unimodal features, redundancy of independent modal features, insufficient analysis of semantic correlation between data and insufficient fusion, a Web-Semantic Enhanced Multimodal Sentiment Analysis Using Multilayer Cross-Attention Fusion is proposed. The model utilizes deep learning (including XLNet, ResNeSt, and convolutional neural networks) to extract high-level features from text, audio, and visual modes through self-attention mechanisms, and improves the accuracy of emotion classification through multimodal fusion. The results of experiments demonstrate that the suggested MCFMSA can achieve Acc-2, Acc-3, F1, and MAE values of 89.7%, 85.2%, 89.3%, and 0.466 on the CMU-MOSI dataset, respectively; and on the CMU-MOSEI dataset, Acc-2, Acc-3, F1, and MAE values of 88.7%, 82.5%, 86.5%, and 0.475. All of them are significantly improved compared to several other advanced multimodal sentiment analysis methods, which can enhance the accuracy of sentiment classification.

Design of news sentiment classification and recommendation system based on multi-model fusion and text similarity

To improve the performance of the news recommendation system, the study employs a multi-model fusion strategy in conjunction with three classification methods to improve the accuracy of sentiment classification. In addition, a text similarity-based recommendation algorithm is proposed to provide personalized recommendations to users. This is achieved by analyzing their interest features and key text features. In addition, a comprehensive recommendation system including news sentiment classification, recommendation algorithms, and a user interface is developed. The study showed that the sentiment classification method based on multi-model fusion had an accuracy rate of 0.95, which was an improvement of 0.10 compared to the support vector machine. Furthermore, the recommendation algorithm based on text similarity calculation demonstrated an accuracy, recall, and F1 value of 0.806, 0.804, and 0.806, respectively, which outperformed the collaborative filtering algorithm and the matrix decomposition recommendation algorithm. The average satisfaction rating for the news recommendation content was above 90 points, indicating that it met user needs. The findings indicate that consumers perceive the personalized news suggestion system to be well-received and that it functions effectively in terms of reaction time and resource consumption. This research offers an effective solution for news recommendation in the era of information overload, which holds significant theoretical and practical value.

Exploring the Impact of Word2Vec Embeddings Across Neural Network Architectures for Sentiment Analysis

Abstract. Sentiment analysis is crucial for understanding public opinion, gauging customer satisfaction, and making informed business decisions based on the emotional tone of textual data. This study investigates the performance of different Word2Vec-based embedding strategies static, non-static, and multichannel for sentiment analysis across various neural network architectures, including Convolution Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Despite the rise of advanced contextual embedding methods such as Bidirectional Encoder Representations from Transformers (BERT), Word to Vector (Word2Vec) retains its importance due to its simplicity and lower computational demands, making it ideal for use in settings with limited resources. The goal is to evaluate the impact of fine-tuning Word2Vec embeddings on the accuracy of sentiment classification. Using the Internet Movie Database (IMDb), this work finds that multichannel embeddings, which combine static and non-static representations, provide the best performance across most architectures, while static embeddings continue to deliver strong results in specific sequential models. These findings highlight the balance between efficiency and accuracy in traditional word embeddings, particularly when advanced models are not feasible.

Exploring the Impact of Word2Vec Embeddings Across Neural Network Architectures for Sentiment Analysis

Abstract. Sentiment analysis is crucial for understanding public opinion, gauging customer satisfaction, and making informed business decisions based on the emotional tone of textual data. This study investigates the performance of different Word2Vec-based embedding strategies static, non-static, and multichannel for sentiment analysis across various neural network architectures, including Convolution Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Despite the rise of advanced contextual embedding methods such as Bidirectional Encoder Representations from Transformers (BERT), Word to Vector (Word2Vec) retains its importance due to its simplicity and lower computational demands, making it ideal for use in settings with limited resources. The goal is to evaluate the impact of fine-tuning Word2Vec embeddings on the accuracy of sentiment classification. Using the Internet Movie Database (IMDb), this work finds that multichannel embeddings, which combine static and non-static representations, provide the best performance across most architectures, while static embeddings continue to deliver strong results in specific sequential models. These findings highlight the balance between efficiency and accuracy in traditional word embeddings, particularly when advanced models are not feasible.

Dynamic Lexicon-Based Sentiment Analysis Architecture Using Nonlinear Feature Optimization

Dynamic Lexicon-Based Sentiment Analysis (DLSA) improves sentiment detection by using adaptive, nonlinear feature optimization techniques. The model targets gaps in traditional methods, which often miss complex and subtle sentiment patterns. DLSA integrates modules for text preprocessing, lexicon and phrase extraction, and feature optimization with genetic algorithms. The system refines feature sets by selecting, combining, and adjusting features based on real-time performance data. Key findings show DLSA outperforms traditional models like SLPCF in accuracy, precision, and recall, especially in analyzing nuanced text data. This approach provides a flexible and efficient solution, enhancing the accuracy of sentiment classification in varied applications.

Discovering User Sentiment Patterns in Libraries with a Hybrid Machine Learning and Lexicon-Based Approach

The need to enhance library services is the focus of this study, which relies on user feedback for data-driven decision-making. Text data from library user surveys conducted at Politeknik Caltex Riau (PCR) is analyzed to categorize sentiment and identify areas for improvement. The biannual student and lecturer feedback collected from 2018 to 2023 through the institution's official survey system (survey.pcr.ac.id) is utilized, providing a comprehensive and robust picture of user needs across five years. Sentiment analysis is employed using the VADER method to classify user comments into positive or negative categories. Text preprocessing techniques, such as stemming, tokenizing, and filtering, are performed to ensure robust classification. Machine learning algorithms – Naïve Bayes, Support Vector Machine (SVM), and Random Forest – are then utilized to evaluate sentiment classification accuracy. The study offers significant findings. Both SVM and Random Forest achieve an outstanding accuracy of 99%, indicating highly reliable sentiment categorization. Notably, these algorithms also achieve 100% precision, recall, and F1-score, demonstrating their effectiveness in accurately identifying positive and negative user sentiment. While Naïve Bayes shows slightly lower accuracy at 98%, it maintains a high recall rate (100%), ensuring all negative feedback is captured. This research presents a novel approach combining user sentiment analysis with a comprehensive five-year dataset. This enables a deeper understanding of evolving user needs and priorities. The high accuracy and effectiveness of the employed algorithms highlight the potential of this methodology for libraries. Libraries can leverage user feedback for evidence-based service improvement and increased user satisfaction.

Supervised Sentiment Analysis of COVID-19 Tweets: Insights into Public Reactions and Trends

In the modern digital era, social media platforms have experienced exponential growth, serving as a medium for individuals to share their emotions and opinions. Twitter, a prominent social media platform, hosts a substantial number of users who regularly express their thoughts through tweets. This research paper focuses on conducting sentiment analysis on tweets pertaining to the COVID-19 situation in India. By utilizing a lexicon-based approach using TextBlob, we determine sentiment scores for each tweet. These scores are then used to categorize the tweets into Positive, Negative, or Neutral sentiment categories. To further enhance the accuracy of sentiment classification, we employ the Naïve Bayes machine learning model, achieving an impressive accuracy rate of 87.65%. The sentiment analysis results obtained through this study provide valuable insights for governmental bodies and other organizations, enabling them to formulate effective policies in order to address similar issues in the future.

Enhanced UrduAspectNet: Leveraging Biaffine Attention for superior Aspect-Based Sentiment Analysis

Urdu, with its rich linguistic complexity, poses significant challenges for computational sentiment analysis. This study presents an enhanced version of UrduAspectNet, specifically designed for Aspect-Based Sentiment Analysis (ABSA) in Urdu. We introduce key innovations including the incorporation of Biaffine Attention into the model architecture, which synergizes XLM-R embeddings, a bidirectional LSTM (BiLSTM), and dual Graph Convolutional Networks (GCNs). Additionally, we utilize dependency parsing to create the adjacency matrix for the GCNs, capturing syntactic dependencies to enhance relational representation. The improved model, termed Enhanced UrduAspectNet, integrates POS and lemma embeddings, processed through BiLSTM and GCN layers, with Biaffine Attention enhancing the extraction of intricate aspect and sentiment relationships. We also introduce the use of BIO tags for aspect term identification, improving the granularity of aspect extraction. Experimental results demonstrate significant improvements in both aspect extraction and sentiment classification accuracy. This research advances Urdu sentiment analysis and sets a precedent for leveraging sophisticated NLP techniques in underrepresented languages.

Tree hierarchical deep convolutional neural network optimized with sheep flock optimization algorithm for sentiment classification of Twitter data

ABSTRACT The increasing volume of online reviews and tweets poses significant challenges for sentiment classification because of the difficulty in obtaining annotated training data. This paper aims to enhance sentiment classification of Twitter data by developing a robust model that improves classification accuracy and computational efficiency. The proposed method named Tree Hierarchical Deep Convolutional Neural Network optimized with Sheep Flock Optimization Algorithm for Sentiment Classification of Twitter Data (SCTD-THDCNN-SFOA) utilizes the Stanford Sentiment Treebank dataset. The process begins with pre-processing steps including Tokenization, Stop words Elimination, Filtering, Hashtag Removal, and Multiword Grouping. The Gray Level Co-occurrence Matrix Window Adaptive Algorithm is employed to extract features, such as emoticon counts, punctuation counts, gazetteer word existence, n-grams, and part of speech tags. These features are selected using Entropy–Kurtosis-based Feature Selection approach. Finally, the Tree Hierarchical Deep Convolutional Neural Network enhanced by the Sheep Flock Optimization Algorithm is used to categorize the Twitter data as positive, negative, and neutral sentiments. The proposed SCTD-THDCNN-SFOA method demonstrates superior performance, achieving higher accuracy and lesser computation time than the existing models, respectively. The SCTD-THDCNN-SFOA framework significantly improves the accuracy and efficiency of sentiment classification for Twitter data.

Sentiment analysis using graph-based Quickprop method for product quality enhancement

ABSTRACT The degree to which customers express satisfaction with a product on Twitter and other social media platforms is increasingly used to evaluate product quality. However, the volume and variety of textual data make traditional sentiment analysis methods challenging. The nuanced and context-dependent nature of product-related opinions presents a challenge for existing tools. This research addresses this gap by utilizing complex graph-based modelling strategies to capture the intricacies of real-world data. The Graph-based Quickprop Method constructs a graph model using the Sentiment140 dataset with 1.6 million tweets, where individuals are nodes and interactions are edges. Experimental results show a significant increase in sentiment classification accuracy, demonstrating the method’s efficacy. This contribution underscores the importance of relational structures in sentiment analysis and provides a robust framework for extracting actionable insights from user-generated content, leading to improved product quality evaluations. The GQP-PQE method advances sentiment analysis and offers practical implications for businesses seeking to enhance product quality through a better understanding of consumer feedback on social media.