Classification Of News Articles Research Articles

Classification of Articles from Mass Media by Categories and Relevance of the Subject Area

The research is devoted to classification of news articles about P. G. Demidov Yaroslavl State University (YarSU) into 4 categories: “society”, “education”, “science and technologies”, “not relevant”.The proposed approaches are based on using the BERT neural network and methods of machine learning: SVM, Logistic Regression, K-Neighbors, Random Forest, in combination of different embedding types: Word2Vec, FastText, TF-IDF, GPT-3. Also approaches of text preprocessing are considered to achieve higher quality of the classification. The experiments showed that the SVM classifier with TF-IDF embedding and trained on full article texts with titles achieved the best result. Its micro-F-measure and macro-F-measure are 0.8214 and 0.8308 respectively. The BERT neural network trained on fragments of paragraphs with YarSU mentions, from which the first 128 words and the last 384 words were taken, showed comparable results. The resulting micro-F-measure and macro-F-measure are 0.8304 and 0.8181 respectively. Thus, using paragraphs with the target organisation mentions is enough to classify text by categories efficiently.

Fake News Detection

The art of tampering with original facts has been going on since edges. The recent act of 2016 Presidential elections proceeded by Facebook and recently COVID19 brought up the term fake news detection. In this paper, we propose to use machine learning ensemble approach for automated classification of news articles. This paper revolves around to use the different classifiers of machine learning (ML) to predict if the news is literal or hoax and evaluate their performance on 5 real world datasets. Then ruling of a classifier is done based on Model Evaluation techniques and the results are tabulated and visual- ized. Experimental evaluation confirms the superior performance of our proposed ensemble learner approach in comparison to individual learners.

An Ensemble Machine Learning Approach for Fake News Detection and Classification Using a Soft Voting Classifier

Fake news has grown in popularity and spread as a result of increased insecurity, political events, and pandemics, among other things. This study used an ensemble machine learning technique to better predict fake news on social media based on the content of news articles. The proposed model used a soft voting classifier to aggregate four machine learning algorithms, namely, Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression, for the classification of news articles as fake or real. GridSearchCV was used to fine-tune the algorithms to get the optimal results during the training process. A Kaggle dataset was used for the experiment; it was comprised of both false and true news. Performance evaluation metrics were used to measure the performance of the base learners and our proposed ensemble technique on the dataset. The results of our experiment show that the proposed ensemble approach produced the highest accuracy, precision, recall, and F1_score values of 93%, 94%, 92%, and 93%, respectively, on the dataset as compared to the individual learners. This approach may also be used in other classification techniques for spam detection, sentiment analysis, and prediction of loan eligibility, among other things.

Semantic Enrichment of Taxonomy for BI Applications using Multifaceted data sources through NLP techniques

Taxonomies are crucial for executing Business Intelligence (BI) applications by preventing users from being overwhelmed with information. The business applications require knowledge of the key concepts and their organization to perform the classification of news articles. To ensure and maintain reliable information classification quality, it is crucial to keep the same definitions and organization of these concepts. This indicates the major significance of BI taxonomies in organizations. However, their development in business information systems follows an ad hoc process in most cases. Compared to many other domains, e.g. environmental and life sciences research, no mature and updated BI taxonomies are available in the literature. Existing studies cover BI taxonomies, but these are excessively generic and domain-specific. As a result, the BI domain suffers from many immature, incorrect, and incomplete notions of concepts. New BI-related concepts emerge rapidly, making it essential to include them in existing taxonomies during the enrichment process. The contribution of our research is the exploration of the possibilities of taxonomy enrichment using existing datasets. The expansion of the existing business taxonomy using multifaceted data sources to capture new concepts comprising 1) lexical datasets, 2) pre-trained word embeddings, 3) linked open data vocabulary, and 4) corpus-based relevant thematic extraction of features from news articles using Natural Language Processing (NLP) techniques. The highest semantic enrichment rate of a taxonomy got on a combination of these 4 methods. Eventually, enriched business taxonomy will contribute to the improved classification of news articles.

Classifying news articles in multiple languages: leveraging context aware models

Despite the recent advances in text classification and the performance improvement yielded by Transformers models, the absence or inaccessibility of an adequate dataset to train a text classifier motivates the choice for alternative routes. In this study, the need to detect specific topics in the news and to discard irrelevant content encouraged the development of an article tagging pipeline which assesses the similarity between a user-defined dictionary of topic-specific keywords and news article keywords. The innovation of the paper stands in the exploitation of two BERT-based algorithms to retrieve article keywords and to embed them, which previous studies have shown to outperform state of the art solutions for keywords extraction and semantic textual similarity. In a nutshell, the pipeline computes the semantic similarity between the sentence embeddings generated from topic-specific keywords and those produced from news article keywords extracted with the KeyBERT algorithm, finally classifying each article according to a previously defined topic. The results are supported by sound coherence and diversity metrics computed, by aggregating each article by their first tag, which attests to the semantic validity of the pipeline outputs.

Hybrid Modeling to Classify and Detect Outliers on Multilabel Dataset based on Content and Context

Due to the linked various matching categories, news article categorization are a rapidly increasing field of interest in text classification. However, the low-reliability indices and ambiguities related to frequently used province classifiers restrict success in this field. Most of the existing research uses traditional machine learning algorithms. It has weaknesses in training large-scale datasets, and data sparseness often occurs from short texts. Therefore, this study proposed a hybrid model consisting of two models, namely the news article classification and the outlier detection model. The news article classification model used a combination of two deep learning algorithms (Long Short-Term Memory dan Convolutional Neural Network) and outlier classifier model, which was intended to predict the outlier news using a decision tree algorithm. The proposed model's performance was compared against two widely used datasets. The experimental results provide useful insights that open the way for a number of future initiatives.

Performance Comparison of Machine Learning Algorithms for Albanian News articles

This paper presented a methodology to classify news articles in Albanian languages with machine learning algorithms and NLP. In this proposed work Multinomial Naïve Bayes, Logistic Regression, k-nearest neighbors, Bernoulli, Centroid, SVM, SGD, Perceptron, Passive Aggressive, Decision Tree, and Random Forest machine learning Classification algorithms are trained to classify Albanian news articles and compared in term of accuracy, training time and testing time. We have used 70% of the dataset for training and 30% for tests. The execution time of training and testing algorithms is recorded and presented for different input sizes of data. For experimental we used different numbers of inputs, starting from 8000 articles, and continuing in increasing order by 8000 until the level of 80000 in 8 categories. Experimental results indicate that the Passive Aggressive algorithm shows the best performance in terms of accuracy for Albanian news articles. While the classifier with the lowest accuracy was Random Forest. Logistic Regression, SVM, and Decision Tree have a high delay in training data. SVM also has the longest testing time compared to other classifiers.

Hybrid Feature Selection Based on Principal Component Analysis and Grey Wolf Optimizer Algorithm for Arabic News Article Classification

The rapid growth of electronic documents has resulted from the expansion and development of internet technologies. Text-documents classification is a key task in natural language processing that converts unstructured data into structured form and then extract knowledge from it. This conversion generates a high dimensional data that needs further analusis using data mining techniques like feature extraction, feature selection, and classification to derive meaningful insights from the data. Feature selection is a technique used for reducing dimensionality in order to prune the feature space and, as a result, lowering the computational cost and enhancing classification accuracy. This work presents a hybrid filter-wrapper method based on Principal Component Analysis (PCA) as a filter approach to select an appropriate and informative subset of features and Grey Wolf Optimizer (GWO) as wrapper approach (PCA-GWO) to select further informative features. Logistic Regression (LR) is used as an elevator to test the classification accuracy of candidate feature subsets produced by GWO. Three Arabic datasets, namely Alkhaleej, Akhbarona, and Arabiya, are used to assess the efficiency of the proposed method. The experimental results confirm that the proposed method based on PCA-GWO outperforms the baseline classifiers with/without feature selection and other feature selection approaches in terms of classification accuracy.

Certain Investigation of Fake News Detection from Facebook and Twitter Using Artificial Intelligence Approach

The news platform has moved from traditional newspapers to online communities in the technologically advanced area of Artificial Intelligence. Because Twitter and Facebook allow us to consume news much faster and with less restricted editing, false information continues to spread at an impressive rate and volume. Online Fake News Detection is a promising field in research and captivates the attention of researchers. The sprawl of huge chunks of misinformation in social network platforms is vulnerable to global risk. This article recommends using a Machine Learning optimization technique for automated news article classification on Facebook and Twitter. The emergence of the research is facilitated by the strategic implementation of Natural Language Processing for social forum fake news findings in order to distort news reports from non-recurrent outlets. The relent from the study is outstanding with text document frequency words, which act as extraction technique’s attribute, and the classifier is acted upon by Hybrid Support Vector Machine by achieving 91.23% accuracy.

An effective fake news detection method using WOA-xgbTree algorithm and content-based features

In recent years, with the fast development of the internet and online platforms such as social media feeds, news blogs, and online newspapers, deceptive reports have been universally spread online. This manipulated news is a matter of concern due to its potential role in shaping public opinion. Therefore, the fast spread of fake news creates an urgent need for automatic systems to detect deceitful articles. This motivates many researchers to introduce solutions for the automatic classification of news items. This paper proposed a novel system to detect fake news articles based on content-based features and the WOA-Xgbtree algorithm. The proposed system can be applied in different scenarios to classify news articles. The proposed approach consists of two main stages: first, the useful features are extracted and analyzed, and then an Extreme Gradient Boosting Tree (xgbTree) algorithm optimized by the Whale Optimization Algorithm (WOA) to classify news articles using extracted features. In our experiments, we considered the bases of the investigation on classification accuracy and the F1-measure. Then, we compared the optimized model with several benchmark classification algorithms based on a dataset that compiled over 40,000 various news articles recently. The results indicate that the proposed approach achieved good classification accuracy and F1 measure rate and successfully classified over 91 percent of articles.

Cross-Context News Corpus for Protest Event-Related Knowledge Base Construction

Abstract We describe a gold standard corpus of protest events that comprise various local and international English language sources from various countries. The corpus contains document-, sentence-, and token-level annotations. This corpus facilitates creating machine learning models that automatically classify news articles and extract protest event-related information, constructing knowledge bases that enable comparative social and political science studies. For each news source, the annotation starts with random samples of news articles and continues with samples drawn using active learning. Each batch of samples is annotated by two social and political scientists, adjudicated by an annotation supervisor, and improved by identifying annotation errors semi-automatically. We found that the corpus possesses the variety and quality that are necessary to develop and benchmark text classification and event extraction systems in a cross-context setting, contributing to the generalizability and robustness of automated text processing systems. This corpus and the reported results will establish a common foundation in automated protest event collection studies, which is currently lacking in the literature.

BIDIRECTIONAL LSTM-CNNs UNTUK EKSTRAKSI ENTITY LOKASI KEBAKARAN PADA BERITA ONLINE BERBAHASA INDONESIA


 
 
 Provinsi DKI Jakarta merupakan salah satu daerah rawan terjadi kebakaran. BPBD DKI Jakarta sebagai Lembaga penanggulangan bencana memiliki salah satu misi yaitu meningkatkan kesiagaan masyarakat kota Jakarta terhadap bencana, salah satunya bencana kebakaran. Peningkatan kesiagaan terhadap bencana kebakaran dapat dilakukan dengan penyajian informasi mengenai lokasi rawan terjadinya kebakaran. BPBD DKI Jakarta dalam hal ini dapat memanfaatkan perkembangan teknologi informasi dan komunikasi, seperti internet sebagai sumber daya informasi. Persebaran informasi melalui internet salah satunya dimuat dalam bentuk web berita online. Informasi yang terdapat pada artikel berita online dapat dijadikan sebagai sumber informasi dalam memperoleh data. Suatu rangkaian proses diperlukan untuk dapat mengekstraksi informasi yang ada didalam artikel berita online. Pada penelitian ini, Eksraksi informasi pada artikel berita online dilakukan dengan mengklasifikasi entity ke dalam kelas-kelas tertentu menggunakan Name Entity Recognition (NER) dengan pendekatan deep learning hybrid network model Bidirectional LSTM-CNNs (BLSTM-CNNs). Penelitian ini menunjukan model NER dengan BLSTM-CNNs memiliki performa yang baik berdasarkan hasil perhitungan F1-score, presisi dan recall. Kemudian, dilakukan pemetaan berdasarkan entity lokasi yang terdapat dalam artikel berita online hasil klasifikasi menggunakan model NER dengan BLSTM-CNNs.
 
 

Classification of News Articles using Supervised Machine Learning Approach

Today the big challenge for NEWS organization to well organize the news and well categorize the news in automatically no need the data entry people to enter and select the category and then based on the category and its sub-category they will be manually selected and enter the details and then after this the analysis will later on used for different aspects. The news is almost every second used in different sources of media in soft and hard. We use the both sources of the Pakistan News in dual languages English and Urdu both and process them and prepare them for machine learning and based on the Machine learning trained data we build a very effective and efficient model that can predict the title category of the news and category of description of the news. We use different machine learning algorithms and different features extraction finally we build the model using the machine learning algorithm with 89% accuracy with logistic regression.

A multi-layer approach to disinformation detection in US and Italian news spreading on Twitter

We tackle the problem of classifying news articles pertaining to disinformation vs mainstream news by solely inspecting their diffusion mechanisms on Twitter. This approach is inherently simple compared to existing text-based approaches, as it allows to by-pass the multiple levels of complexity which are found in news content (e.g. grammar, syntax, style). As we employ a multi-layer representation of Twitter diffusion networks where each layer describes one single type of interaction (tweet, retweet, mention, etc.), we quantify the advantage of separating the layers with respect to an aggregated approach and assess the impact of each layer on the classification. Experimental results with two large-scale datasets, corresponding to diffusion cascades of news shared respectively in the United States and Italy, show that a simple Logistic Regression model is able to classify disinformation vs mainstream networks with high accuracy (AUROC up to 94%). We also highlight differences in the sharing patterns of the two news domains which appear to be common in the two countries. We believe that our network-based approach provides useful insights which pave the way to the future development of a system to detect misleading and harmful information spreading on social media.

Fake News Detection Using Machine Learning Ensemble Methods

The advent of the World Wide Web and the rapid adoption of social media platforms (such as Facebook and Twitter) paved the way for information dissemination that has never been witnessed in the human history before. With the current usage of social media platforms, consumers are creating and sharing more information than ever before, some of which are misleading with no relevance to reality. Automated classification of a text article as misinformation or disinformation is a challenging task. Even an expert in a particular domain has to explore multiple aspects before giving a verdict on the truthfulness of an article. In this work, we propose to use machine learning ensemble approach for automated classification of news articles. Our study explores different textual properties that can be used to distinguish fake contents from real. By using those properties, we train a combination of different machine learning algorithms using various ensemble methods and evaluate their performance on 4 real world datasets. Experimental evaluation confirms the superior performance of our proposed ensemble learner approach in comparison to individual learners.

A Multi-label Classification System to Distinguish among Fake, Satirical, Objective and Legitimate News in Brazilian Portuguese

Currently, there has been a significant increase in the diffusion of fake news worldwide, especially the political class, where the possible misinformation that can be propagated, appearing at the elections debates around the world. However, news with a recreational purpose, such as satirical news, is often confused with objective fake news. In this work, we decided to address the differences between objectivity and legitimacy of news documents, where each article is treated as belonging to two conceptual classes: objective/satirical and legitimate/fake. Therefore, we propose a DSS (Decision Support System) based on a Text Mining (TM) pipeline with a set of novel textual features using multi-label methods for classifying news articles on these two domains. For this, a set of multi-label methods was evaluated with a combination of different base classifiers and then compared with a multi-class approach. Also, a set of real-life news data was collected from several Brazilian news portals for these experiments. Results obtained reported our DSS as adequate (0.80 f1-score) when addressing the scenario of misleading news, challenging the multi-label perspective, where the multi-class methods (0.01 f1-score) overcome by the proposed method. Moreover, it was analyzed how each stylometric features group used in the experiments influences the result aiming to discover if a particular group is more relevant than others. As a result, it was noted that the complexity group of features could be more relevant than others.

Named Entity Recognition of South China Sea Conflicts

Online news articles not only provide us with useful and reliable information and reports, it also eases information extraction and gathering for research purposes especially in Natural Language Processing (NLP) and machine learning (ML). The topics regarding the South China Sea have been popular lately due to the rise of conflicts between several countries claim on the islands in the sea. Gathering data through Internet and online sources proves to be easy, but to process a huge amount of data and to identify only useful information is no longer possible. Because of that, relevant information and the classification of news articles in relation to the conflicts need to be done. In this paper, a model is proposed to use NER that search for and classifies important information regarding to the conflicts. In order to do that, a combination of POS and NER are needed to extract meaningful information from the news. This study also aims to classify conflict related news by using Conditional Random Field (CRF) algorithm as classification method by training and testing the data.

South China Sea Conflicts Classification Using Named Entity Recognition (NER) and Part-of-Speech (POS) Tagging

Internet connects everyone to everything globally. The existence of Internet eases people in completing daily tasks. Thanks to Internet, information is being digitalized and spread openly to the public. Online news articles not only provide us with useful and reliable information and reports, it also eases information extraction and gathering for research purposes especially in Natural Language Processing (NLP) and Machine Learning (ML). The topics regarding the South China Sea have been popular lately due to the rise of conflicts between several countries claim on the islands in the sea. Gathering data through Internet and online sources proves to be easy, but to process a huge amount data and to identify only useful information manually takes a longer time to complete. Extracting important features from a text document can be done by using one or a combination of feature extraction methods. Relevant information and the classification of news articles in relation to the conflicts in South China Sea need to be done. In this paper, a model is proposed to use Named Entity Recognition (NER) that search for and classifies important information regarding to the conflicts. In order to do that, a combination of Part-of-Speech (POS) and NER are needed to extract type of conflicts from the news. This study also claims to classify news by using Conditional Random Field (CRF) algorithm and Multinomial Naïve Bayes (MNB) as classification methods by training and testing the data.

3bij3 – Developing a framework for researching recommender systems and their effects

Abstract Today’s online news environment is increasingly characterized by personalized news selections, relying on algorithmic solutions for extracting relevant articles and composing an individual’s news diet. Yet, the impact of such recommendation algorithms on how we consume and perceive news is still understudied. We therefore developed one of the first software solutions to conduct studies on effects of news recommender systems in a realistic setting. The web app of our framework (called 3bij3) displays real-time news articles selected by different mechanisms. 3bij3 can be used to conduct large-scale field experiments, in which participants’ use of the site can be tracked over extended periods of time. Compared to previous work, 3bij3 gives researchers control over the recommendation system under study and creates a realistic environment for the participants. It integrates web scraping, different methods to compare and classify news articles, different recommender systems, a web interface for participants, gamification elements, and a user survey to enrich the behavioural measures obtained.

Topology comparison of Twitter diffusion networks effectively reveals misleading information

In recent years, malicious information had an explosive growth in social media, with serious social and political backlashes. Recent important studies, featuring large-scale analyses, have produced deeper knowledge about this phenomenon, showing that misleading information spreads faster, deeper and more broadly than factual information on social media, where echo chambers, algorithmic and human biases play an important role in diffusion networks. Following these directions, we explore the possibility of classifying news articles circulating on social media based exclusively on a topological analysis of their diffusion networks. To this aim we collected a large dataset of diffusion networks on Twitter pertaining to news articles published on two distinct classes of sources, namely outlets that convey mainstream, reliable and objective information and those that fabricate and disseminate various kinds of misleading articles, including false news intended to harm, satire intended to make people laugh, click-bait news that may be entirely factual or rumors that are unproven. We carried out an extensive comparison of these networks using several alignment-free approaches including basic network properties, centrality measures distributions, and network distances. We accordingly evaluated to what extent these techniques allow to discriminate between the networks associated to the aforementioned news domains. Our results highlight that the communities of users spreading mainstream news, compared to those sharing misleading news, tend to shape diffusion networks with subtle yet systematic differences which might be effectively employed to identify misleading and harmful information.