Sentiment Classification Research Articles

Aspect-based sentiment analysis: A dual-task learning architecture using imbalanced maximized-area under the curve proximate support vector machine and reinforcement learning

Aspect-based sentiment analysis (ABSA) deals with understanding sentiments about specific attributes. Aspect term extraction (ATE) plays an essential role in aspect sentiment classification (ASC) by specifying the main aspects for sentiment accuracy. This paper introduces a dual-task framework for ATE and ASC models in which, the ATE model uses the imbalanced maximized-area under the curve proximate support vector machine (ImAUC-PSVM) method to mitigate the imbalance problem and the output of ATE serves as the reward in the training process of ASC supported by RL (reinforcement learning). The ImAUC-PSVM uses the conventional PSVM (proximate support vector machine) strength for sentiment tasks and the AUC (area under the curve) optimization for imbalance addressing. The ASC model employs multiple kernels for word embedding, with a transductive long short-term memory (TLSTM) for sentence representation that considers samples near the test point for better model refinement. The policy of the RL-based training strategy of the ASC model is represented by a multilayer perceptron (MLP) that categorizes sentences into positive, negative and neutral sentiments. In this RL context, aspect terms serve as rewards in the training process. The scope loss function (SLF) is also integrated within RL to rectify dataset imbalances. To optimize ATE and ASC models, an artificial bee colony (ABC) technique is incorporated for hyperparameter optimization. Experiments and evaluations conducted on English (Restaurant and Laptop) and Hindi datasets show the superiority of the proposed model over existing models of the literature. Moreover, transfer learning (TL) is applied to a Twitter dataset to assess its effect on ATE. The F-measures of the ATE model are obtained as 90.12 and 84.10 and the accuracies of the ASC model are calculated as 84.10 and 82.02 on Restaurant and Laptop datasets, respectively.

Aspect-based sentiment analysis via bidirectional variant spiking neural P systems

In recent years, aspect-based sentiment classification has predominantly relied on artificial neural networks, achieving notable success. However, effectively capturing the contextual semantic relationships between aspects and content has remained challenging. To address this issue, we propose an innovative approach for aspect-based sentiment analysis. Our method uses a Bidirectional Variant Spiking Neural P System (Bi-VSNP) as a context encoding module, integrated with a two-channel mechanism to extract context and aspect features. Furthermore, Our dual attention mechanism leverages the relationship between aspects and context, allowing the model to focus on key sentiment information. We rigorously evaluated our method on publicly available datasets, demonstrating its superior performance over most models based on artificial neural networks as context extraction. Compared to other models utilizing SNP methods, our approach achieves performance improvements of 1.72%, 1.27%, and 1.05% on the Laptop, Restaurant, and Twitter datasets, respectively. These results underscore the efficacy of our approach in aspect-based sentiment classification.

Use of prompt-based learning for code-mixed and code-switched text classification

Code-mixing and code-switching (CMCS) are prevalent phenomena observed in social media conversations and various other modes of communication. When developing applications such as sentiment analysers and hate-speech detectors that operate on this social media data, CMCS text poses challenges. Recent studies have demonstrated that prompt-based learning of pre-trained language models outperforms full fine-tuning across various tasks. Despite the growing interest in classifying CMCS text, the effectiveness of prompt-based learning for the task remains unexplored. This paper presents an extensive exploration of prompt-based learning for CMCS text classification and the first comprehensive analysis of the impact of the script on classifying CMCS text. Our study reveals that the performance in classifying CMCS text is significantly influenced by the inclusion of multiple scripts and the intensity of code-mixing. In response, we introduce a novel method, Dynamic+AdapterPrompt, which employs distinct models for each script, integrated with adapters. While DynamicPrompt captures the script-specific representation of the text, AdapterPrompt emphasizes capturing the task-oriented functionality. Our experiments on Sinhala-English, Kannada-English, and Hindi-English datasets for sentiment classification, hate-speech detection, and humour detection tasks show that our method outperforms strong fine-tuning baselines and basic prompting strategies.

Comparing emotion classification: machine learning algorithms and hybrid model with support vector machines

<p>Recently, the use of artificial intelligence techniques has become widespread, having been adopted in brain-computer interfaces (BCIs) with electroencephalograms (EEGs). BCIs allow direct communication between a person's brain and a computer, and have various uses ranging from assistive technology to neuroscientific study. This paper provides an introductory overview of BCIs and EEG. We adopted the use of machine learning (ML) algorithms, including K-nearest neighbors (KNN), logistic regression, decision trees, random forests, and support vector machine (SVM). Additionally, we proposed a hybrid model of deep learning (DL) and ML by combining convolutional neural networks (CNNs) and SVMs. Our achieved 98% accuracy. The goal is to classify EEG signals into three emotional states: happy, normal, and sad. The study aims to achieve a comprehensive understanding of the effectiveness of these algorithms in accurately classifying emotional states based on EEG data. By comparing the performance of traditional ML methods and the proposed hybrid model, we seek to identify the most robust and accurate approach to sentiment classification.</p>

BERT-based models for classifying multi-dialect Arabic texts

<p><a name="_Hlk133997549"></a><a name="_Hlk127607325"></a><span lang="EN-US">The area of natural language processing (NLP) is presently a rapidly developing field characterized by innovation and research. Despite this progress, several </span><a name="_Hlk148089340"></a><span lang="EN-US">dialects of Arabic</span><span><span lang="EN-US"> (DA) are classified as low-resource languages, making it challenging for NLP systems to process DA data. One approach to address this issue is to train NLP models on social media data sets containing DA texts. </span><span lang="IN">Therefore, these open-access social media datasets, as outlined in our paper, can serve as a valuable resource for developers and researchers involved in the processing of DA.</span><span lang="EN-US">To create our multilingual corpus, we gathered data from various datasets containing different versions of DA. These datasets will be used to classify texts in terms of sentiment classification, topic classification, and dialect identification. Our study contributes to the automated analysis of the classification of Arabic dialects. We aim to investigate and assess various machine learning and deep learning techniques, with a specific focus on utilizing the BERT model. </span><span lang="EN-US">The results of our experiments on our datasets show that DarijaBERT and DziriBERT trained on a similar DA outperform traditional machine learning methods and previous more general pre-trained models that were trained on multiple dialects or languages.</span></span></p>

Sentiment Analysis of Sirekap Tweets Using CNN Algorithm

Background: The research investigates the application of deep learning models for sentiment analysis on Twitter data related to Indonesia's Sirekap system. Sentiment analysis is crucial for understanding public opinion and enhancing the transparency and reliability of election result recapitulation processes. Objective: The objective of this study is to compare the performance of Convolutional Neural Networks (CNN) and CNN-LSTM models in analyzing sentiments from tweets about the Sirekap system. The study aims to identify the most effective model and preprocessing techniques to improve sentiment classification accuracy. Methods: A comprehensive data preprocessing pipeline was implemented, including cleansing, case folding, tokenizing, normalization, stopword removal, and stemming. To address class imbalance, the SMOTE technique was applied. The models were trained and evaluated using accuracy, precision, recall, and F1-score metrics. Pre-trained word embeddings were used to enhance model performance. Results: The CNN model achieved an accuracy of 85.90%, outperforming the CNN-LSTM model, which achieved 79.91% accuracy. Additionally, the CNN model demonstrated superior precision, recall, and F1-score metrics compared to the CNN-LSTM model. The thorough preprocessing and handling of class imbalance significantly contributed to the enhanced performance of the CNN model. Conclusion: The research emphasizes the effectiveness of deep learning approaches, particularly CNNs, in sentiment analysis tasks. The findings highlight the importance of comprehensive preprocessing and class imbalance handling. The use of pre-trained word embeddings and various evaluation metrics ensures robust model performance. These insights contribute to improving the accuracy and efficiency of sentiment classification, thereby enhancing the reliability and transparency of election result recapitulation processes.

An integrated approach to Bayesian weight regulations and multitasking learning methods for generating emotion-based content in the metaverse

This paper introduces an integrated model designed to analyze topics and sentiments in textual data simultaneously, recognizing their interdependence. By tackling challenges such as data scarcity, missing information, and biased distributions, the proposed model effectively captures the dynamic interactions between topics and sentiments within complex datasets. The method combines the use of Convolutional Neural Networks (CNN) for detecting topic-related patterns with a revised Recurrent Neural Network (RNN) to trace the emotional flow within contexts, leveraging the strengths of sequential data processing. These components are integrated within a Bayesian probability framework, modeling the conditional probabilities of sentences expressing specific sentiments and documents being associated with particular topics. The combined feature and state vectors from the CNN and revised RNN within this Bayesian setup enable precise classification and prediction of topics and sentiments. Furthermore, this paper explores innovative research avenues, including sentiment analysis in 3D virtual reality environments and the development of new algorithms that reflect content creation techniques in the metaverse, offering dynamic system construction. This integrated approach not only enhances data-driven decision-making but also unlocks new possibilities for advanced multi-text analysis.

A novel masking model for Buddhist literature understanding by using Generative Adversarial Networks

This paper is focused on ancient Chinese Buddhist literature understanding. Buddhist literature incorporates a plethora of dialects and slang, which makes it challenging to extract semantic meaning seamlessly. To address this issue, a Generative Adversarial Network Masking Model (GAN-MM) is proposed to pre-train BERT models. This method focuses on optimizing the Masked Language Model (MLM) and takes advantage of the rich semantics of Buddhist terminologies as well as the absence of functional words in Buddhist literature. Furthermore, a semi-supervised learning algorithm was developed to train the GAN-MM. The model was evaluated by assessing its performance on two private tasks related to Buddhist literature understanding: sentiment classification and text segmentation, as well as two public tasks pertaining to the ancient Chinese understanding. The experimental results demonstrated a significant enhancement in the pre-training of BERT models when utilizing GAN-MM, as compared to conventional MLM methods. A large-scale Buddhist dataset, including 20,075 utterance documents and 146 million tokens, is public released at https://data.mendeley.com/datasets/5hzs8w46jh/1.

Leveraging Large Language Models for Aspect-Based Sentiment Classification using GPT-4

Aspect-based sentiment analysis (ABSA) is an essential task in natural language processing (NLP) that aims to extract both aspects and their corresponding sentiment polarities from textual data. Despite its importance, ABSA faces challenges in accurately capturing nuanced sentiments, particularly in complex and context-dependent scenarios. This paper introduces a novel technique that employs few-shot learning with the GPT-4 model to determine the sentiment of specific aspects within the text. By using a template prompt along with few-shot examples, we enhance ChatGPT’s in-context learning capability, thereby improving the effectiveness of aspect-based sentiment classification. Our tests and evaluations demonstrate that this method achieves state-of-the-art results in ABSA. This research represents a significant advancement in sentiment analysis methodologies, especially in capturing nuanced sentiments toward specific aspects.

Movie Review Based Sentiment Analysis

Sentiment analysis, an automated method for detecting emotions and opinions in text, has become a versatile tool applied across various domains, from assessing online customer feedback to monitoring sentiment trends on social media. While Bag of Words (BoW) has been the traditional method, more advanced techniques like Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) have revolutionized sentiment analysis by elevating accuracy and context comprehension. This study conducts an extensive comparison between BERT, a hybrid model that combines CNN and LSTM in the realm of sentiment analysis within movie reviews. Through meticulous experimentation, the study strongly proves that both the hybrid model of CNN and LSTM models significantly outshine the techniques like BERT and BoW with noticeably higher accuracy in precisely categorizing sentiments expressed in movie reviews. These results highlight how deep learning methodologies remarkably refine the precision and effectiveness of sentiment analysis, allowing for more nuanced and context-aware sentiment classification. The study's significance goes beyond performance contrasts; it demonstrates the exceptional capacity of BERT along with the hybrid model of CNN and LSTM to comprehend the complexities of language and contextual nuances within movie reviews. This heightened contextual understanding is particularly crucial in sentiment analysis, enabling the models to discern subtle shifts in sentiment that simpler methods like BoW might overlook. By showcasing the supremacy of hybrid model that combines CNN and LSTM in movie review sentiment analysis, this research opens new avenues for the field's advancement. It emphasizes the potential of deep learning techniques in revolutionizing sentiment analysis across diverse domains, offering more accurate and contextually attuned sentiment classification for deeper insights and well-informed decision-making. This study stands as a valuable asset for researchers and practitioners aiming to leverage deep learning for sentiment analysis applications

Feasibility of big data analytics in disaster psychiatry: Impact of Seoul Itaewon tragedy on sentiment distribution on Twitter

Numerous studies have highlighted the significant impact of disasters on mental health, often leading to psychiatric disorders among affected individuals. Timely identification of disaster-related mental health problems is crucial to prevent long-term negative consequences and improve individual and community resilience. To address the limitations of prior research that has focused solely on isolated incidents, we analyzed the impact of a recurring Halloween event in Itaewon, South Korea, which culminated tragically in a crowd crush incident in 2022. We conducted sentiment analysis on big data from Korean Twitter to gauge the impact of this disaster on public sentiment. We collected tweets 2 weeks before and after the annual festival from 2020 to 2022, allowing for the consideration of variability across years and days before the disaster. Using a pre-trained RoBERTa neural network model fine-tuned with public sentiment datasets, we categorized tweets into seven pre-defined emotional categories: Anger, sadness, happiness, disgust, fear, surprise, and neutrality. These sentiments were then analyzed as daily time-series data. The overall tweet volume across all sentiment categories increased, particularly showing an increase in the number of tweets indicating “Sadness” in 2022 compared with that in previous years. Post-disaster, a substantial increase was noted in the proportion of tweets expressing “Sadness” and “Fear.” This trend was confirmed by Seasonal Autoregressive Integrated Moving Average with Exogenous Regressor models. Notably, there was an increase in the number of tweets expressing all sentiments, including “Happy.” However, significant changes in proportions were observed only in tweets categorized as expressing “Sadness” [0.046 (95% CI: 0.024–0.068, P < 0.0001)] and “Fear” [0.033 (95% CI: 0.014–0.051, P < 0.0001)]. Our study demonstrates the feasibility of using sentiment data from social media, combined with sentiment classification, to assess distinct public mental health features following disasters. This approach provides valuable insights into the emotional impact of each event.

Unmasking large language models by means of OpenAI GPT-4 and Google AI: A deep instruction-based analysis

Large Language Models (LLMs) have become a hot topic in AI due to their ability to mimic human conversation. This study compares the open artificial intelligence generative pretrained transformer-4 (GPT-4) model, based on the (GPT), and Google's artificial intelligence (AI), which is based on the Bidirectional Encoder Representations from Transformers (BERT) framework in terms of the defined capabilities and the built-in architecture. Both LLMs are prominent in AI applications. First, eight different capabilities were identified to evaluate these models, i.e. translation accuracy, text generation, factuality, creativity, intellect, deception avoidance, sentiment classification, and sarcasm detection. Next, each capability was assessed using instructions. Additionally, a categorized LLM evaluation system has been developed by means of using ten research questions per category based on this paper's main contributions from a prompt engineering perspective. It should be highlighted that GPT-4 and Google AI successfully answered 85 % and 68,7 % of the study prompts, respectively. It has been noted that GPT-4 better understands prompts than Google AI, even with verbal flaws, and tolerates grammatical errors. Moreover, the GPT-4 based approach was more precise, accurate, and succinct than Google AI, which was sometimes verbose and less realistic. While GPT-4 beats Google AI in terms of translation accuracy, text generation, factuality, intellectuality, creativity, and deception avoidance, Google AI outperforms the former when considering sarcasm detection. Both sentiment classification models did work properly. More importantly, a human panel of judges was used to assess and evaluate the model comparisons. Statistical analysis of the judges' ratings revealed more robust results based on examining the specific uses, limitations, and expectations of both GPT-4 and Google AI-based approaches. Finally, the two approaches' transformers, parameter sizes, and attention mechanisms have been examined.

Fusion Network for Aspect-Level Sentiment Classification Based on Graph Neural Networks—Enhanced Syntactics and Semantics

Aspect-level sentiment classification (ALSC) struggles with correctly trapping the aspects and corresponding sentiment polarity of a statement. Recently, several works have combined the syntactic structure and semantic information of sentences for more efficient analysis. The combination of sentence knowledge with graph neural networks has also proven effective at ALSC. However, there are still limitations on how to effectively fuse syntactic structure and semantic information when dealing with complex sentence structures and informal expressions. To deal with these problems, we propose an ALSC fusion network that combines graph neural networks with a simultaneous consideration of syntactic structure and semantic information. Specifically, our model is composed of a syntactic attention module and a semantic enhancement module. First, the syntactic attention module builds a dependency parse tree with the aspect term being the root, so that the model focuses better on the words closely related to the aspect terms, and captures the syntactic structure through a graph attention network. In addition, the semantic enhancement module generates the adjacency matrix through self-attention, which is processed by the graph convolutional network to obtain the semantic details. Lastly, the extracted features are merged to achieve sentiment classification. As verified by experiments, the model we propose can effectively enhance ALSC’s behavior.

PUBLIC STIGMA ABOUT POLYGAMY BASED ON ISLAMIC-MUHAMMADIYAH VIEWS USING SENTIMENT ANALYSIS APPROACH

Social media is very important to control the development of issues that occur today. With social shifts and changing societal values, polygamy has become a complex issue and attracts the attention of many people around the world discussed through social media platforms. This research contributes to the field by applying a sentiment analysis approach to automatically detect and analyze public sentiment regarding polygamiy content on Twitter, particularly in the context of Islamic-Muhammadiyah views. This study used decision tree classification methods, support vector machines, and random forests with the best analysis accuracy obtained at SVM 77.4%. Furthermore, the results of the sentiment class obtained were analyzed according to the views of Muhammadiyah. The results obtained in the analysis 77% commented negatively and 23% commented positively. In addition, this research can be used as a reference for future research on sentiment analysis cases to training and testing classroom models.

Exploring electric vehicle adoption in Indonesia using zero-shot aspect-based sentiment analysis

Transportation emissions significantly contribute to greenhouse gases (GHG) and climate change. Electric vehicles (EVs) offer a promising solution to this problem. Despite the noteworthy adoption of EVs in emerging economies like China and Europe, the pace of EV rollout in Indonesia remains sluggish. Currently, the country's rate of EV adoption is below 0.3 %, leading to stagnation in the Indonesian electric vehicle market. Several factors have impeded the adoption of EVs in Indonesia. Previous studies have investigated consumer acceptance of EV adoption in specific countries using sentiment analysis. Various data analytics and machine learning techniques have been implemented in those studies. However, those studies predominantly rely on the traditional sentiment analysis method, which assigns a single sentiment classification to each document or sentence. On the other hand, this study aims to investigate consumer acceptance of electric vehicle adoption in Indonesia through Twitter conversations. It utilises the Zero-Shot Aspect-Based Sentiment Analysis (ABSA) approach, which can provide a more fine-grained analysis of the aspects discussed and their corresponding sentiments. The findings demonstrate the effectiveness of this approach in identifying discussed aspects within tweets, though its sentiment classification performance is limited. The research also uncovers crucial aspects of electric vehicle adoption and public sentiments on Twitter. These insights could provide valuable guidance to the government and other stakeholders regarding the concerns associated with EV adoption in Indonesia.

Towards explainable fake news detection and automated content credibility assessment: Polish internet and digital media use-case

Detecting fake news and disinformation is a challenging and complex task. With the proliferation of the transformer architectures, researchers and practitioners have started actively using them to combat this phenomenon. In that regard, different approaches have been proposed by the community. Unfortunately, a significant number of solutions have started to treat misinformation in a similar way as other natural language processing challenges (e.g., sentiment classification). However, the reality is more complex, and the fake news detection problem often require additional context that may be essential to provide a complete assessment. Another pitfall in combating fake news is treating it as a binary classification challenge (e.g., fake vs. legitimate news). Combining such a simplified response with a deep black-box neural system effectively impacts the interpretability and eventual trustworthiness of the detection system. In this paper, the phenomenon of fake news is approached from a multi-factor perspective. Therefore, the proposed innovative approach does not limit news content rating to a one-dimensional binary response. In particular, the authors utilize a vast spectrum of processing techniques, including text embedding, machine translation, and various users’ preferences to provide content assessment. The results are presented using a Polish digital media use-case.

Aspect-Level Sentiment Analysis on GoPay App Reviews Using Multilayer Perceptron and Word Embeddings

The increase of smartphone usage in Indonesia has encouraged the development of digital wallet applications, one of which is GoPay. Nowadays, GoPay has gained significant popularity among the public in Indonesia. Therefore, this research conducts aspect-level sentiment analysis to analyze user reviews of the GoPay application in more detail and depth. The sentiment analysis process in this study utilizes the Multilayer Perceptron (MLP) with fastText and word2vec as word embeddings. The dataset used is GoPay application reviews, which consist of 15,000 reviews collected from Google Play Store. The dataset is categorized into three main aspects: Feature and functionality, App Interface, and User Satisfaction. The stages of the research include data preparation, data preprocessing, word embeddings, model training, and model testing and evaluation. This research explores the effect of fastText and word2vec as word embeddings on model performance. Furthermore, this research examines the application of oversampling techniques, such as SMOTE and Random Oversampling. Based on the experiments conducted, utilizing fastText as word embeddings in MLP with a balanced dataset resulted the best model performance, with an F1-Score of 97%, Recall of 96%, and Precision of 95% for aspect category classification. Then, for sentiment classification, using fastText on MLP with a balanced dataset resulted in a value of 98% for each of the F1-score, Recall, and Precision metrics. This research validates that MLP is effective for aspect-level sentiment analysis, delivering strong evaluation results.

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.

Exploring transformer models for sentiment classification: A comparison of BERT, RoBERTa, ALBERT, DistilBERT, and XLNet

AbstractTransfer learning models have proven superior to classical machine learning approaches in various text classification tasks, such as sentiment analysis, question answering, news categorization, and natural language inference. Recently, these models have shown exceptional results in natural language understanding (NLU). Advanced attention‐based language models like BERT and XLNet excel at handling complex tasks across diverse contexts. However, they encounter difficulties when applied to specific domains. Platforms like Facebook, characterized by continually evolving casual and sophisticated language, demand meticulous context analysis even from human users. The literature has proposed numerous solutions using statistical and machine learning techniques to predict the sentiment (positive or negative) of online customer reviews, but most of them rely on various business, review, and reviewer features, which leads to generalizability issues. Furthermore, there have been very few studies investigating the effectiveness of state‐of‐the‐art pre‐trained language models for sentiment classification in reviews. Therefore, this study aims to assess the effectiveness of BERT, RoBERTa, ALBERT, DistilBERT, and XLNet in sentiment classification using the Yelp reviews dataset. The models were fine‐tuned, and the results obtained with the same hyperparameters are as follows: 98.30 for RoBERTa, 98.20 for XLNet, 97.40 for BERT, 97.20 for ALBERT, and 96.00 for DistilBERT.

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.