GloVe Word Embeddings Research Articles

AUTOMATED SARCASM RECOGNITION USING APPLIED LINGUISTICS DRIVEN DEEP LEARNING WITH LARGE LANGUAGE MODEL

Posting sarcastic comments on social media has become popular in the modern era. Sarcasm is a linguistic expression that typically conveys the contrary meaning of what has already been said, making it challenging for machines to find the literal meaning. It depends mainly on context, making it a tedious process for computational analysis. It is well known for its modulation with spoken words and an irony undertone. In addition, sarcasm conveys negative sentiment using positive words, which easily confuses sentiment analysis (SA) models. Sarcasm detection is a natural language processing (NLP) process and is prevalent in SA, human–machine dialogue, and other NLP applications due to sarcasm’s ambiguities and complex nature. Concurrently, the advancement of machine learning (ML) techniques makes it easier to develop robust sarcasm detection methods. This paper presents an automated sarcasm recognition using applied linguistics-driven deep learning with a large language model (ASR-ALDL3M) technique. The purpose of the ASR-ALDL3M technique is to focus on recognizing the sarcastic data using the DL model. In the ASR-ALDL3M technique, the initial data preprocessing phase is utilized, and glove word embedding is applied. Next, the sarcasm recognition procedure is applied using the long short-term memory (LSTM) model. Moreover, the hyperparameter selection of the LSTM model is performed using the fractals monarch butterfly optimization (MBO) technique. At last, a large language model (LLM) is utilized to enhance the sarcastic recognition process. A comprehensive result analysis is made to validate the outcomes of the ASR-ALDL3M technique. The performance evaluation outcomes stated that the ASR-ALDL3M method gains better performance over other models.

Fake News Detection Using Optimized Convolutional Neural Network and Bidirectional Long Short-Term Memory

The spread of fake news in the digital age threatens the integrity of online information, influences public opinion, and creates confusion. This study developed and tested a fake news detection model using an enhanced CNN-BiLSTM architecture with GloVe word embedding techniques. The WELFake dataset comprising 72,000 samples was used, with training and testing data ratios of 90:10, 80:20, and 70:30. Preprocessing involved GloVe 100-dimensional word embedding, tokenization, and stopword removal. The CNN-BiLSTM model was optimized with hyperparameter tuning, achieving an accuracy of 96%. A larger training data ratio demonstrated better performance. Results indicate the effectiveness of this model in distinguishing fake news from real news. This study shows that the CNN-BiLSTM architecture with GloVe embedding can achieve high accuracy in fake news detection, with recommendations for further research to explore preprocessing techniques and alternative model architectures for further improvement.

Automatic Sarcasm Detection on Cross-Platform Social Media Datasets: A GLoVe and Bi-LSTM Based Approach 

Sarcastic remarks on social media platforms have become commonplace, with people expressing their bad feelings in a quite positive manner or in a mocking way. This contradictive nature of sarcasm makes its detection a very challenging task. Many researchers have provided their solutions to perform automatic sarcasm detection from a single domain dataset. Most of them have considered only the content of the text and has ignored the context of the text. Understanding that the context of a text is the most important factor in determining either it is sarcastic or not. This study aims to detect sarcastic remarks from multi-domain dataset by using Bi-LSTM model employed with pre-trained GloVe word embeddings because the GloVe embeddings and Bi-LSTM both are good at capturing contextual information from the provided data. The dataset is generated by the concatenation of three publicly available datasets, the gosh tweets, the news headlines dataset, and the sarcasm corpus v2 dataset. GloVe embeddings will extract contextual and semantic features from the text while the Bi-LSTM model will get trained and tested on those features. The proposed model has achieved 86.35% of accuracy with 88% of Recall, Precision, and F1-score. Different experiments have been done to test the model's reliability. This study's findings indicate that the proposed model yields state-of-the-art or comparable results. The proposed study aids in improving the performance of sentiment analysis. It will also help individuals, and different organizations to identify accurate sentiments of people about individuals or products of an organization. 

Deep learning-based method for sentiment analysis for patients' drug reviews.

This article explores the application of deep learning techniques for sentiment analysis of patients' drug reviews. The main focus is to evaluate the effectiveness of bidirectional long-short-term memory (LSTM) and a hybrid model (bidirectional LSTM-CNN) for sentiment classification based on the entire review text, medical conditions, and rating scores. This study also investigates the impact of using GloVe word embeddings on the model's performance. Two different drug review datasets were used to train and test the models. The proposed methodology involves the implementation and evaluation of both deep learning models with the GloVe word embeddings for sentiment analysis of drug reviews. The experimental results indicate that Model A (Bi-LSTM-CNN) achieved an accuracy of 96% and Model B (Bi-LSTM-CNN) performs consistently at 87% for accuracy. Notably, the incorporation of GloVe word representations improves the overall performance of the models, as supported by Cohen's Kappa coefficient, indicating a high level of agreement. These findings showed the efficacy of deep learning-based approaches, particularly bidirectional LSTM and bidirectional LSTM-CNN, for sentiment analysis of patients' drug reviews.

An Empirical Evaluation of Adapting Hybrid Parameters for CNN-based Sentiment Analysis

Sentiment analysis aims to understand human emotions and perceptions through various machine-learning pipelines. However, feature engineering and inherent semantic gap constraints often hinder conventional machine learning techniques and limit their accuracy. Newer neural network models have been proposed to automate the feature learning process and enrich learned features with word contextual embeddings to identify their semantic orientations to address these challenges. This article aims to analyze the influence of different factors on the accuracy of sentiment classification predictions by employing Feedforward and Convolutional Neural Networks. To assess the performance of these neural network models, we utilize four diverse real-world datasets, namely 50,000 movie reviews from IMDB, 10,662 sentences from LightSide Movie_Reviews, 300 public movie reviews, and 1,600,000 tweets extracted from Sentiment140. We experimentally investigate the impact of exploiting GloVe word embeddings on enriching feature vectors extracted from sentiment sentences. Findings indicate that using larger dimensions of GloVe word embeddings increases the sentiment classification accuracy. In particular, results demonstrate that the accuracy of the CNN with a larger feature map, a smaller filter window, and the ReLU activation function in the convolutional layer was 90.56% using the IMDB dataset. In comparison, it was 80.73% and 77.64% using the sentiment140 and the 300 sentiment sentences dataset, respectively. However, it is worth mentioning that, with large-size sentiment sentences (LightSide’s Movie Reviews) and using the same parameters, only a 64.44% level of accuracy was achieved.

Detecting cyberbullying using deep learning techniques: a pre-trained glove and focal loss technique.

This study investigates the effectiveness of various deep learning and classical machine learning techniques in identifying instances of cyberbullying. The study compares the performance of five classical machine learning algorithms and three deep learning models. The data undergoes pre-processing, including text cleaning, tokenization, stemming, and stop word removal. The experiment uses accuracy, precision, recall, and F1 score metrics to evaluate the performance of the algorithms on the dataset. The results show that the proposed technique achieves high accuracy, precision, and F1 score values, with the Focal Loss algorithm achieving the highest accuracy of 99% and the highest precision of 86.72%. However, the recall values were relatively low for most algorithms, indicating that they struggled to identify all relevant data. Additionally, the study proposes a technique using a convolutional neural network with a bidirectional long short-term memory layer, trained on a pre-processed dataset of tweets using GloVe word embeddings and the focal loss function. The model achieved high accuracy, precision, and F1 score values, with the GRU algorithm achieving the highest accuracy of 97.0% and the NB algorithm achieving the highest precision of 96.6%.

TOXIC COMMENT CLASSIFICATION USING BI-LSTM

In the age of internet and social media platforms, the problem of toxic remarks has become increasingly prominent. This research addresses the application of advanced deep learning technique, specifically C Bidirectional Long Short-Term Memory networks (Bi-LSTM), for the classification of toxic comments. Additionally, we employ pre-trained GloVe word embeddings to enhance the performance of the models. The project intends to increase the accuracy and efficiency of toxic comment classification, enabling platforms to automatically recognize and filter out harmful information. By utilizing Bi-LSTM architectures, which excel in capturing spatial and temporal correlations in textual data, we can effectively identify toxic language. The integration of GloVe embeddings significantly strengthens the semantic comprehension of words, contributing to more exact categorization results. Through a comprehensive analysis and evaluation of the proposed models on benchmark datasets such as the Jigsaw Multilingual Toxic Comment Classification dataset, we demonstrate the effectiveness of Bi- LSTM with GloVe embeddings in accurately identifying toxic comments. By reaching high classification accuracy, precision, recall, and F1 scores, the models highlight their potential in minimizing the harmful impact of toxic comments in online contexts. The results of this study have significant implications for online platforms, social media companies, and community moderators seeking automated solutions for content moderation. Key Words: Toxic comment classification, Bidirectional Long Short-Term Memory(BI-LSTM), GloVe embeddings, Deep learning.

An Efficient Aspect-based Sentiment Classification with Hybrid Word Embeddings and CNN Framework

Background: As the e-commerce product reviews and social media posts are increasing enormously, the size of the database for polarity/ sentiment detection is a challenging task, and again, predicting polarities associated with respect to aspect terms end to end in a sentence is a havoc in real-time applications. Human behavior is influenced by the various opinions generated in society. Public opinion influences our decisions most often. Businesses and establishments always need to collect the opinion of the society, which they try to obtain using customer feedback forms and questionnaires or surveys, which help them to be aware of the shortcomings if any, and to use suggestions to improve quality. It works in the same way for customers as well and the opinions of other customers about a particular product can come in handy when deciding to buy a product. Objectives: In this work, an efficient Aspect-based Sentiment Classification technique has been introduced with a hybrid, multiple-word embedding methods and implemented using the CNN framework on large databases. Methods: Most of the traditional models have a limitation on the dependency for one or more similar types of aspect words for sentiment classification problem. However, these conventional models such as TF-ID, Word 2Vec and Glove method consumes much more time for word embedding process and Aspect terms generation and further process of aspect level sentiment classification. Further, these models are facing problems of high true negative rate and misclassification rate on large aspect databases in sentiment classification. In this article, we have introduced an efficient Proposed ensemble word embedding model in the CNN network and defined Hybrid Word2 Vec method, Hybrid Glove word embedding method and Hybrid Random Forest model for sentiment classification. Results: Experiments on a widely used benchmark prove that the proposed word embedding method- based classification technique results in to higher true positive rate with minimal misclassifications and also supports better runtime and accuracy than the traditional word embedding-based aspect level classification approaches. Conclusion: In this article, a hybrid ensemble feature ranking-based classification model is proposed on the large aspect databases. In this work, advanced multiple-word embedding methods are implemented to improve the essential feature extraction problem in the aspect level sentiment process. These multiple-word embedding methods are applied to the sentiment databases in the CNN framework.

The COVID-19 Tweets Classification Based on Recurrent Neural Network

Due to its extensive use in both public and commercial contexts, sentiment analysis on Twitter has recently received much attention, particularly concerning tweets about COVID-19. Information about COVID-19 has been widely spread over social media, resulting in various views, opinions, and emotions about this pandemic, significantly impacting people's health. It is exceedingly challenging for the authorities to find these rumors on these public platforms manually. This paper proposes a framework for text classification using the RNN model and its updates, such as LSTM, BiLSTM, and GRU. This study aims to determine the best recurrent network model for handling cases of Twitter data classification. We utilized Twitter data relevant to COVID-19 and the lockdown with four classification classes (sad, joy, fear, and anger). In addition, this study aims to prove whether GloVe pre-trained word embedding can increase the accuracy of model predictions. The training and testing datasets were split into 80% and 20%, respectively. Therefore, in this experiment an early stopping technique was used with a limit of 15 epochs and a minimum delta of 0.01, meaning that training will be stopped if there is no improvement of 0.1% accuracy after 15 epochs. We used the f1-score average to measure the accuracy of the classification task results. The test results show that the BiLSTM model with GloVe word embedding yields the best f1-score compared to other models. Moreover, in all model testing, the f1-score value of the 'fear' class displays the highest accuracy compared to other classes.

Graph convolution networks for social media trolls detection use deep feature extraction

This study presents a novel approach to identifying trolls and toxic content on social media using deep learning. We developed a machine-learning model capable of detecting toxic images through their embedded text content. Our approach leverages GloVe word embeddings to enhance the model's predictive accuracy. We also utilized Graph Convolutional Networks (GCNs) to effectively analyze the intricate relationships inherent in social media data. The practical implications of our work are significant, despite some limitations in the model's performance. While the model accurately identifies toxic content more than half of the time, it struggles with precision, correctly identifying positive instances less than 50% of the time. Additionally, its ability to detect all positive cases (recall) is limited, capturing only 40% of them. The F1-score, which is a measure of the model's balance between precision and recall, stands at around 0.4, indicating a need for further refinement to enhance its effectiveness. This research offers a promising step towards more effective monitoring and moderation of toxic content on social platforms.

Applied Linguistics Driven Deceptive Content Recognition using Single Valued Trapezoidal Neutrosophic Number with Natural Language Processing

Single valued neutrosophic number is a special case of single valued neutrosophic set and are of importance for neutrosophic multi-attribute decision making problem. A single valued neutrosophic number seems to define an ill-known quantity as a generalization of intuitionistic number. Applied linguistics in the context of Natural Language Processing (NLP) comprises the practical applications of linguistic approaches for addressing real time language processing issues. Social media become indispensable components in many people’s lives and have been growing rapidly. In the meantime, social networking media have become a widespread source of identity deception. Several social media identity deception cases have appeared presently. The research was performed to detect and prevent deception. Identifying deceptive content in natural language is significant to combat misrepresentation. Leveraging forward-thinking NLP methods, our model contextual cues analyze linguistic patterns, and semantic inconsistencies to flag possibly deceptive contents. By assimilating complex procedures for parameter optimization, feature extraction, and classification, the NLP focused on precisely recognizing deceptive content through different digital platforms, which contributes to the preservation of data integrity and the promotion of digital literacy. This study presents a Single Valued Trapezoidal Neutrosophic Number with Natural Language Processing for Deceptive Content Recognition (STVNNLP-DCR) technique on Social Media. The presented technique includes four important elements: preprocessing, GloVe word embedding, STVN classification, and Chicken Swarm Optimization (CSO) for parameter tuning. The preprocessing stage includes tokenization and text normalization, preparing text information for succeeding analysis. Then, GloVe word embedding represents the word in a continuous vector space, which captures contextual relationships and semantic similarities. The STVN classifier deploys the embedding to discern deceptive patterns within the text, leveraging its capability to effectively manage high-dimensional and sparse datasets. Moreover, the CSO technique enhances the hyperparameter of the STVN classifier, improving its generalization capabilities and performance. Empirical analysis implemented on varied datasets validates the efficacy of the presented technique in precisely recognizing deceptive content. Comparative studies with advanced approaches demonstrate high efficiency. The presented technique shows robustness against different forms of deceptive content, such as clickbait, misinformation, and propaganda

A Hybrid Deep Learning Architecture for Social Media Bots Detection Based on Bigru-LSTM and Glove Word Embedding

A Hybrid Deep Learning Architecture for Social Media Bots Detection Based on Bigru-LSTM and Glove Word Embedding

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model.

This study introduced a novel approach for predicting occupational injury severity by leveraging deep learning-based text classification techniques to analyze unstructured narratives. Unlike conventional methods that rely on structured data, our approach recognizes the richness of information within injury narrative descriptions with the aim of extracting valuable insights for improved occupational injury severity assessment. Natural language processing (NLP) techniques were harnessed to preprocess the occupational injury narratives obtained from the US Occupational Safety and Health Administration (OSHA) from January 2015 to June 2023. The methodology involved meticulous preprocessing of textual narratives to standardize text and eliminate noise, followed by the innovative integration of Term Frequency-Inverse Document Frequency (TF-IDF) and Global Vector (GloVe) word embeddings for effective text representation. The proposed predictive model adopts a novel Bidirectional Long Short-Term Memory (Bi-LSTM) architecture and is further refined through model optimization, including random search hyperparameters and in-depth feature importance analysis. The optimized Bi-LSTM model has been compared and validated against other machine learning classifiers which are naïve Bayes, support vector machine, random forest, decision trees, and K-nearest neighbor. The proposed optimized Bi-LSTM models' superior predictability, boasted an accuracy of 0.95 for hospitalization and 0.98 for amputation cases with faster model processing times. Interestingly, the feature importance analysis revealed predictive keywords related to the causal factors of occupational injuries thereby providing valuable insights to enhance model interpretability. Our proposed optimized Bi-LSTM model offers safety and health practitioners an effective tool to empower workplace safety proactive measures, thereby contributing to business productivity and sustainability. This study lays the foundation for further exploration of predictive analytics in the occupational safety and health domain.

Bidirectional Gated Recurrent Unit with Glove Embedding and Attention Mechanism for Movie Review Classification

During the current Internet era, enormous volume of structured and unstructured textual data is generated and exchanged online that made the text classification more crucial. With the massive amount of user-generated content on social media platforms, businesses and organizations can leverage sentiment analysis to understand customer opinions and attitudes towards the products, services, or brand. Text classification is a natural language processing task in which a machine learning model is trained to categorize the text into predefined classes or categories. Due to the advent of promising Deep Learning techniques, intelligent and accurate text classification system can be developed. In movie review classification, algorithms are used to automatically categorize movie reviews into positive, negative, or sometimes neutral sentiments based on the opinions expressed in the text. The goal is to automate the process of determining whether a review reflects a positive or negative sentiment, helping users quickly understand the overall reception of a movie. This work proposes an automated movie review classification system based on Bidirectional Gated Recurrent Unit encoder with attention module. This method encodes the words using GloVe word embedding technique. Context information is captured in an efficient manner and the encoding is more reliable. Bidirectional GRU layer captures long-term dependencies in sentences, followed by a custom Attention layer that assigns higher weights to key components. The attention mechanism allows the model to selectively focus on important parts of the input sequence, by dynamically determining attention weights based on task relevance. The model was individually trained and evaluated using popular benchmark IMDb dataset. Experimental studies have proved the better performance of proposed movie review classification system that obtained accuracy of 98%.

The Legal Effect and Application of Smart Contracts under the Administrative Law System

Abstract As an important cornerstone of future digital civilization, smart contracts are being increasingly used in blockchain finance in innovative practice, and whether smart contracts have legal effect has become a question that academia must answer. This paper discusses the legal impact and application of smart contracts under the contract layer in the blockchain architecture, with a vision of an administrative legal system. Based on the operation principle of smart contracts, a method for detecting smart contract vulnerabilities that combines Glove word embedding and the Shapelet-Transform algorithm is proposed to improve data security during the fulfillment process. Finally, the smart contract model constructed in this paper is applied to the supply chain of agricultural products, and the legal effects of the smart contract are analyzed using practical examples. The transaction volume of unqualified agricultural products decreased from 19.4545 to 13.4655, which is lower than the production volume. The credit index of the smart contract model has increased, resulting in a shortened node performance time from 0.25s to 0.2s.

Research on Text Analysis Methods in English Translation Teaching Based on Semantic Association Network Modeling

Abstract As the mainstream language of the world, English still occupies an unshakeable prime position, and English translation is one of the essential learning content for students. The semantic network association network model is introduced in this paper, and a text analysis model for English translation is proposed. The model obtains word vectors through the GloVe word embedding model, combines the relevance measure of the Jaccard index, and applies the improved RelArtNet algorithm to calculate semantic relevance in English texts. The translated data from a prominent English test is selected as a sample to analyze the relevance of each feature value of English translation scores. From the three aspects of word surface, conceptual fidelity, and semantic expression, the textual analysis of the experimental corpus by the model yields the comprehensive scoring effect of English translation by the model. The correlation between translation length and English translation scoring is the highest, and the correlation of scoring in both English to Chinese and Chinese to English is more significant than 0.58. The overall model scoring and manual scoring of English translation are closer, with a difference of 1.59 in scoring and a correlation coefficient of greater than 0.8, which verifies the practical value of the model for scoring English translations. The English translation scoring model can help teachers review translations and students practice independently, which has important practical significance.

Application of the Bidirectional Long Short-Term Memory Method with Comparison of Word2Vec, GloVe, and FastText for Emotion Classification in Song Lyrics

Along with the development of today's world, many music player software and platforms offer the flexibility of listening to music anywhere and anytime. Song lyrics can help focus listeners' attention on certain emotions, therefore it is important to classify emotions in song lyrics for recommendation systems. This study aims to test the accuracy of the Bi-LSTM deep learning method, identify and compare the effect of word embedding, and examine the impact of parameters on accuracy in the classification of emotions in song lyrics. This study compares the impact of the algorithm on two datasets, namely the Music Lyrics Kaggle dataset of 3890 data with 8 emotional categories and the MoodyLyrics dataset of 2000 data with 4 emotional categories. The main indicators used in the test consist of embedding weights, embedding dimension, learning rate, and epoch. Results of the experiments show an accuracy of 62% on the MoodyLyrics dataset, while the Music Lyrics Kaggle dataset produced an accuracy of 42%. The test results also show that the GloVe word embedding model gives the most optimal results compared to Word2Vec and FastText.

Stance-Based Fake News Identification on Social Media with Hybrid CNN and RNN-LSTM Models

Today, fake news can be readily generated and disseminated via social media platforms. Misinformation and hoaxes propagated via online social media or traditional news media are commonly referred to as fake news. Stance-based fake news is based on the opinions of an audience rather than providing correct facts. This study presents a hybrid model focusing on the CNN model and RNN-LSTM model to identify fake news. A balanced dataset of 216k news items called ‘SherLock-FakeNewsNet’ is explored throughout the study resulting in the proposed hybrid model. The NLTK toolkit is utilized to perform some noise reduction. After that, the Keras tokenizer and pre-processor are used for the tokenization and pre-processing steps. Next, the text data is fitted and represented using pre-trained GloVe word embeddings. CNN model is applied with Conv1D layers and MaxPooling layers to extract higher-level features of the text. Following this, to detect the longer context of the given text and to capture interdependencies among word sequences LSTM units are employed in the RNN model. Dropout layers are carefully chosen to reduce overfitting in the final hybrid model. The proposed hybrid model achieves the highest accuracy rate of 92% by outperforming most of the conventional models today with an average Precision of 91%, Recall of 91%, and F1-Score of 91% using an Adam optimizer and a Binary Cross-Entropy loss function. Based on the five experiments performed in the study, we have presented the results by comparing our proposed hybrid model with five related datasets.

Hate speech detection on Indonesian text using word embedding method-global vector

<p>Hate speech is defined as communication directed toward a specific individual or group that involves hatred or anger and a language with solid arguments leading to someone's opinion can cause social conflict. It has a lot of potential for individuals to communicate their thoughts on an online platform because the number of Internet users globally, including in Indonesia, is continually rising. This study aims to observe the impact of pre-trained global vector (GloVe) word embedding on accuracy in the classification of hate speech and non-hate speech. The use of pre-trained GloVe (Indonesian text) and single and multi-layer long short-term memory (LSTM) classifiers has performance that is resistant to overfitting compared to pre-trainable embedding for hatespeech detection. The accuracy value is 81.5% on a single layer and 80.9% on a double-layer LSTM. The following job is to provide pre-trained with formal and non-formal language corpus; pre-processing to overcome non-formal words is very challenging.</p>

Measuring trust: a text analysis approach to compare, contrast, and select trust questionnaires.

Trust has emerged as a prevalent construct to describe relationships between people and between people and technology in myriad domains. Across disciplines, researchers have relied on many different questionnaires to measure trust. The degree to which these questionnaires differ has not been systematically explored. In this paper, we use a word-embedding text analysis technique to identify the differences and common themes across the most used trust questionnaires and provide guidelines for questionnaire selection. A review was conducted to identify the existing trust questionnaires. In total, we included 46 trust questionnaires from three main domains (i.e., Automation, Humans, and E-commerce) with a total of 626 items measuring different trust layers (i.e., Dispositional, Learned, and Situational). Next, we encoded the words within each questionnaire using GloVe word embeddings and computed the embedding for each questionnaire item, and for each questionnaire. We reduced the dimensionality of the resulting dataset using UMAP to visualize these embeddings in scatterplots and implemented the visualization in a web app for interactive exploration of the questionnaires (https://areen.shinyapps.io/Trust_explorer/). At the word level, the semantic space serves to produce a lexicon of trust-related words. At the item and questionnaire level, the analysis provided recommendation on questionnaire selection based on the dispersion of questionnaires' items and at the domain and layer composition of each questionnaire. Along with the web app, the results help explore the semantic space of trust questionnaires and guide the questionnaire selection process. The results provide a novel means to compare and select trust questionnaires and to glean insights about trust from spoken dialog or written comments.