News Classification Research Articles

Long short-term memory (LSTM)-based news classification model.

In this study, we used unidirectional and bidirectional long short-term memory (LSTM) deep learning networks for Chinese news classification and characterized the effects of contextual information on text classification, achieving a high level of accuracy. A Chinese glossary was created using jieba-a word segmentation tool-stop-word removal, and word frequency analysis. Next, word2vec was used to map the processed words into word vectors, creating a convenient lookup table for word vectors that could be used as feature inputs for the LSTM model. A bidirectional LSTM (BiLSTM) network was used for feature extraction from word vectors to facilitate the transfer of information in both the backward and forward directions to the hidden layer. Subsequently, an LSTM network was used to perform feature integration on all the outputs of the BiLSTM network, with the output from the last layer of the LSTM being treated as the mapping of the text into a feature vector. The output feature vectors were then connected to a fully connected layer to construct a feature classifier using the integrated features, finally classifying the news articles. The hyperparameters of the model were optimized based on the loss between the true and predicted values using the adaptive moment estimation (Adam) optimizer. Additionally, multiple dropout layers were added to the model to reduce overfitting. As text classification models for Chinese news articles, the Bi-LSTM and unidirectional LSTM models obtained f1-scores of 94.15% and 93.16%, respectively, with the former outperforming the latter in terms of feature extraction.

Do Sentence-Level Sentiment Interactions Matter? Sentiment Mixed Heterogeneous Network for Fake News Detection

With the proliferation of fake news, the spread of misleading information can easily cause social panic and group polarization. Many existing methods for detecting fake news rely on linguistic and semantic features extracted from the content of the news. Some existing approaches focus on sentiment analysis for fake news detection, but the sentiment changes and sentence-level emotional interactions in news classification are not fully analyzed. Fortunately, we observe that in long-form news, the change and mutual influence of sentiment between sentences are different. To extract the features of sentiment interaction between sentences in the article, we propose a graph attention network-based model that combines both sentiment and external knowledge comparison to meet the needs of fake news classification. We obtain the contextual sentiment representation and entity representation of the sentence through the heterogeneous network and the emotion interaction network and obtain the change of the sentiment vector through the emotion comparison network. We compare the entity vectors in the context with those corresponding knowledge base (KB)-based, combine them with the contextual semantic representation of the sentence, and finally input them into the classifier. In experiments, our model performs well in both single and multiclass classification, achieving the state-of-the-art accuracy on existing datasets.

The Application of Random Forest to the Classification of Fake News

Fake News is one of the most widespread phenomenon with significant consequences on our daily life, particularly in the political realm. Due to the increasing use of the internet and social media, it is now much simpler to propagate false information. Therefore, the identification of elusive news is a significant issue that must be addressed, mostly due to obstacles such as the limited number of benchmark datasets and the volume of news produced per second. This study suggested using comparative data analysis based on random forest machine learning algorithm to identify bogus 4news. In this study the size of the whole dataset is 20.761 fake news record, whereas the size of it is 4.345 records. The first step in the data preparation process is to remove any unnecessary special characters, numbers, English letters, and whitespace. Before implementing the proposed classification algorithms, the most prevalent feature extraction approach (TF-IDF) is used. The data indicate that the highest level of accuracy attained was 88.24%.

Toxic Fake News Detection and Classification for Combating COVID-19 Misinformation

The emergence of COVID-19 has led to a surge in fake news on social media, with toxic fake news having adverse effects on individuals, society, and governments. Detecting toxic fake news is crucial, but little prior research has been done in this area. This study aims to address this gap and identify toxic fake news to save time spent on examining nontoxic fake news. To achieve this, multiple datasets were collected from different online social networking platforms such as Facebook and Twitter. The latest samples were obtained by collecting data based on the topmost keywords extracted from the existing datasets. The instances were then labeled as toxic/nontoxic using toxicity analysis, and traditional machine-learning (ML) techniques such as linear support vector machine (SVM), conventional random forest (RF), and transformer-based ML techniques such as bidirectional encoder representations from transformers (BERT) were employed to design a toxic-fake news detection (FND) and classification system. As per the experiments, the linear SVM method outperformed BERT SVM, RF, and BERT RF with an accuracy of 92% and -score, -score, and -score of 95%, 85%, and 87%, respectively. Upon comparison, the proposed approach has either suppressed or achieved results very close to the state-of-the-art techniques in the literature by recording the best values on performance metrics such as accuracy, F1-score, precision, and recall for linear SVM. Overall, the proposed methods have shown promising results and urge further research to restrain toxic fake news. In contrast to prior research, the presented methodology leverages toxicity-oriented attributes and BERT-based sequence representations to discern toxic counterfeit news articles from nontoxic ones across social media platforms.

MR-FNC: A Fake News Classification Model to Mitigate Racism

MR-FNC: A Fake News Classification Model to Mitigate Racism

Novel Multichannel Deep Learning Model for Arabic News Classification

Novel Multichannel Deep Learning Model for Arabic News Classification

Overview of Multimodal Data and its Application to Fake News Detection

In the context of the growing popularity of social media over the past ten years, an urgent problem of fake news spreading has arisen, which underscores the research’s relevance. The research aims to analyse current studies, focused on identifying and classifying fake news. To achieve this goal, a multimodal approach was chosen that combines deep learning frameworks and pre-trained models. This approach provides a comprehensive analysis of textual, visual, and audio information, allowing for more accurate identification of disinformation sources. The use of various knowledge transfer methods made it possible to process information efficiently, improving the quality of classification. The study conducted a thorough analysis of various data collection strategies, as well as a comparative analysis of available multimodal approaches to fake news detection and the datasets used. The results of this study included a detailed analysis of current research work in the field of fake news detection and the development of a multimodal approach to this problem. Pre-trained models and deep learning were used to process textual, visual, and audio information, which allowed for high accuracy in fake news detection. The results of the study showed that the multimodal approach allows for more accurate identification of sources of disinformation and increases the efficiency of fake news classification compared to other methods. A comparative analysis of different data collection strategies and datasets was also conducted, which helped to confirm the high efficiency of our approach in different conditions. The practical significance of the study is that it provides practical recommendations for the development and implementation of fake news detection systems based on multimodal approaches. Thus, this study not only reveals the actual problem of fake news but also provides practical tools for combating it, which is of significant importance for modern science and society. The study proposes a multimodal approach to accurately identify and classify fake news.

Ensembling Deep Learning Models for Fake News Classification

Fake news remains one of the most pressing concerns of the current era for any citizen caring about political independence and the state of politics. In an implementation of NLP’s classic problems, we have set out to develop a stacked ensemble of deep learning models to classify and hence separate fake news from true articles. We have considered three well known deep learning architecture as baseline models, such as CNN, BiLSTM, and Multi Layer Perceptron (MLP). We also employed word embeddings like GloVe and Transformer BERT to boost our models’ performances, which brings our number of standalone models to six. We have further taken the individual model’s predictions to build a deep learning ensemble. We compared four such ensembles, namely models using hard weighted voting, soft voting, soft weighted voting, and logistic regression. After analysing the results, we conclude that our proposed logistic regression-based stacked ensemble is the best performing model, achieving significant f1-score of 96.03% and 74.24% using publicly available datasets.

Multimodal Chinese Agricultural News Classification Method Based on Interactive Attention

Multimodal Chinese Agricultural News Classification Method Based on Interactive Attention

Fake News Classification Methodology With Enhanced BERT

Fake News Classification Methodology With Enhanced BERT

MorphBungee: A 65-nm 7.2-mm2 27-μJ/image Digital Edge Neuromorphic Chip with On-Chip 802-frame/s Multi-Layer Spiking Neural Network Learning.

This paper presents a digital edge neuromorphic spiking neural network (SNN) processor chip for a variety of edge intelligent cognitive applications. This processor allows high-speed, high-accuracy and fully on-chip spike-timing-based multi-layer SNN learning. It is characteristic of hierarchical multi-core architecture, event-driven processing paradigm, meta-crossbar for efficient spike communication, and hybrid and reconfigurable parallelism. A prototype chip occupying an active silicon area of 7.2 mm2 was fabricated using a 65-nm 1P9M CMOS process. when running a 256-256-256-256-200 4-layer fully-connected SNN on downscaled 16 × 16 MNIST images. it typically achieved a high-speed throughput of 802 and 2270 frames/s for on-chip learning and inference, respectively, with a relatively low power dissipation of around 61 mW at a 100 MHz clock rate under a 1.0V core power supply, Our on-chip learning results in comparably high visual recognition accuracies of 96.06%, 83.38%, 84.53%, 99.22% and 100% on the MNIST, Fashion-MNIST, ETH-80, Yale-10 and ORL-10 datasets, respectively. In addition, we have successfully applied our neuromorphic chip to demonstrate high-resolution satellite cloud image segmentation and non-visual tasks including olfactory classification and textural news categorization. These results indicate that our neuromorphic chip is suitable for various intelligent edge systems under restricted cost, energy and latency budgets while requiring in-situ self-adaptative learning capability.

A Comparative Analysis of Word Embeddings Techniques for Italian News Categorization

A Comparative Analysis of Word Embeddings Techniques for Italian News Categorization

News Categories in Mainstream and Social Media: A Comparative Analysis of Daily Dawn and Twitter

News Categories in Mainstream and Social Media: A Comparative Analysis of Daily Dawn and Twitter

Advancements in News Article Classification: Approaches in Machine Learning and Deep Learning across Sports, Entertainment, Politics, Business, and Weather Domains

The classification of news articles is a crucial technology for processing news information, aiding in the organization of information. It is challenging to classify news due to the continuous emergence of news that requires processing. The modern technological era has reshaped traditional lifestyles in various domains. Similarly, the medium of publishing news and events has experienced rapid growth with the advancement of Information Technology. In this research, news article classification is organized into five selected domains: sports, entertainment, politics, business, and weather news. The classification involves both common and uncommon approaches, along with datasets based on Machine Learning and Deep Learning techniques. Furthermore, the evaluation incorporates various metrics such as precision, recall, and accuracy to compare approaches across the selected five news domains with datasets. To narrow the focus, we limited the news categorization to a few domains (sports, entertainment, politics, business, and weather) to facilitate a better understanding of a large amount of data through concise content. We recommend our work to individuals interested in extending and building upon my research over time.

STID-Prompt: Prompt learning for sentiment-topic-importance detection in financial news

With the development of the Internet and the financial industry, the analysis and judgement of financial news has become increasingly important. Common tasks in this area include sentiment analysis, topic classification, and importance judgement. Existing approaches use fine-tuning paradigms to address these tasks. However, the lack of labeled data in the field of financial news poses a small sample learning problem. The new paradigm represented by prompt learning provides a new way and means to improve the performance of small-sample classification. In addition, existing methods do not focus on research on sentiment, topic, and importance simultaneously, which is also an important factor in evaluating financial news. In practical applications, joint judgment of sentiment, topic, and importance is more effective. Finally, these methods require different tuning for each specific task. They do not consider relationships between individual tasks and cannot utilize information across tasks. This limits their application in complex situations. In this work, we propose a prompt-based financial news classification model (STID-Prompt) to address these issues. For the first two problems, we solve the sentiment analysis task, the topic classification task, the importance judgment task, and the 〈sentiment, topic, importance〉 classification task by designing complex prompt templates. For the third problem, we propose a unique prompt-based joint multi-task learning approach. It learns knowledge from multiple tasks and integrates it into the target task, and the multi-task learning approach further improves the performance of the model. Experimental results show the effectiveness of our approach even with less training data.

Implementasi Metode LSTM Untuk Mengklasifikasi Berita Palsu Pada PolitiFact

Fake news is an increasingly worrying issue in the digital age, as its spread has the potential to impact public perception and the democratic process. The information classified in this study consists of political claims assessed by Politifact, along with Politifact's evaluation of their accuracy. The purpose of this research is to create a fake news classification system concentrated on data from Politifact using Long Short-Term Memory (LSTM). The methods to be used include data collection from the PolitiFact.com website that provides fake news and fact news, followed by data labeling, Exploratory Data Analysis (EDA), data preprocessing, use of wordcloud visualization, data separation, LSTM model formation, evaluation, testing with new data to be classified. The data used amounted to 1500 news with the number of fact news as many as 34 and fake news as many as 1466. The results showed that the LSTM model was very good at classifying fake news in Politifact by being able to produce a very high accuracy rate of 97%. The ability of this model can be one of the right choices for classifying fake news and can be an invaluable tool in combating the spread of false information and supporting reliable media in disseminating accurate news to the public.

Automatic Classification of Arabic News and Column Articles using Machine Learning and Deep Learning Approaches

Automatic Classification of Arabic News and Column Articles using Machine Learning and Deep Learning Approaches

Buzzing before the Storms: Infodemic Pattern of COVID-19 in Indonesia

Amid the COVID-19 pandemic that Indonesia has been facing as a country with diversity and a high population, hoaxes and misinformation have become an acute problem. The Ministry of Communication and Informatics recorded 1,600 hoaxes related to COVID-19 from January 2020 to June 2021. By using the concept of infodemic and the theory of uses and gratification, this research attempt to describe and analyze categories of fake news, the types of media used, the description of the issues raised in the fake news, and the frequency of hoaxes spread during the COVID-19 pandemic in Indonesia; and examine the relationship between the number of new COVID-19 cases and the frequency of hoaxes in the early days of the pandemic. This study used quantitative methods, with trend analysis in data processing of 1970 hoax issues released by the Ministry of Communication and Informatics to the number of new cases of COVID-19 patients during the same time frame. The results show no relationship between total COVID-19 cases and real issues. The frequency pattern of hoax issue distribution during the COVID-19 pandemic follows infodemic conditions, with the peak of hoax circulation equal to the start of COVID-19 cases in Indonesia. Although the Indonesia government has made various efforts to address the problem of hoaxes and misinformation during the COVID-19 pandemic in Indonesia, this research shows that further action is still required to reduce the negative impact of hoaxes and misinformation on Indonesian society. Keywords: COVID-19, hoax, infodemic, pattern, social media.

Cross-lingual Sentiment Analysis of Tamil Language Using a Multi-stage Deep Learning Architecture

In recent years, sentiment analysis has become a focal point in natural language processing. Cross-lingual sentiment analysis is a particularly demanding yet essential task that seeks to construct models capable of effectively analyzing sentiments across a variety of languages. The primary motivation behind this research is to bridge the gap in current techniques that often struggle to perform well with low-resource languages, due to the scarcity of large, annotated datasets, and their unique linguistic characteristics. In light of these challenges, we propose a novel Multi-Stage Deep Learning Architecture (MSDLA) for cross-lingual sentiment analysis of the Tamil language, a low-resource language. Our approach utilizes transfer learning from a source language with abundant resources to overcome data limitations. Our proposed model significantly outperforms existing methods on the Tamil Movie Review dataset, achieving an accuracy, precision, recall, and F1-score of 0.8772, 0.8614, 0.8825, and 0.8718, respectively. ANOVA statistical comparison demonstrates that the MSDLA’s improvements over other models, including mT5, XLM, mBERT, ULMFiT, BiLSTM, LSTM with Attention, and ALBERT with Hugging Face English Embedding are significant, with p-values all less than 0.005. Ablation studies confirm the importance of both cross-lingual semantic attention and domain adaptation in our architecture. Without these components, the model’s performance drops to 0.8342 and 0.8043 in accuracy, respectively. Furthermore, MSDLA demonstrates robust cross-domain performance on the Tamil News Classification and Thirukkural datasets, achieving an accuracy of 0.8551 and 0.8624, respectively, significantly outperforming the baseline models. These findings illustrate the robustness and efficacy of our approach, making a significant contribution to cross-lingual sentiment analysis techniques, especially for low-resource languages.

Ensemble machine learning approaches for fake news classification

In today’s interconnected digital landscape, the proliferation of fake news has become a significant challenge, with far-reaching implications for individuals, institutions, and societies. The rapid spread of misleading information undermines the credibility of genuine news outlets and threatens informed decision-making, public trust, and democratic processes. Recognizing the profound relevance and urgency of addressing this issue, this research embarked on a mission to harness the power of machine learning to combat fake news menace. This study develops an ensemble machine learning model for fake news classification. The research is targeted at spreading fake news. The research subjects are machine learning methods for misinformation classification. Methods: we employed three state-of-the-art algorithms: LightGBM, XGBoost, and Balanced Random Forest (BRF). Each model was meticulously trained on a comprehensive dataset curated to encompass a diverse range of news articles, ensuring a broad representation of linguistic patterns and styles. A distinctive feature of the proposed approach is the emphasis on token importance. By leveraging specific tokens that exhibited a high degree of influence on classification outcomes, we enhanced the precision and reliability of the developed models. The empirical results were both promising and illuminating. The LightGBM model emerged as the top performer among the three, registering an impressive F1-score of 97.74% and an accuracy rate of 97.64%. Notably, all three of the proposed models consistently outperformed several existing models previously documented in academic literature. This comparative analysis underscores the efficacy and superiority of the proposed ensemble approach. In conclusion, this study contributes a robust, innovative, and scalable solution to the pressing challenge of fake news detection. By harnessing the capabilities of advanced machine learning techniques, the research findings pave the way for enhancing the integrity and veracity of information in an increasingly digitalized world, thereby safeguarding public trust and promoting informed discourse.