News Feature Research Articles

The Making of Good News: Discursive Construction of Good News Through News Values

ABSTRACT Good news aims to redress the balance from negative bias and contributes to a more comprehensive form of journalism. This article explores the largely ignored discursive construction of good news through news values. It first investigates the features of good news stories as against top news stories in the mainstream media, and then identifies differences in the discursive practices by the mainstream media and the good news outlets in covering the same events. The findings show that in the mainstream media, top news stories tend to highlight Eliteness and Negativity, whereas good news stories give emphasis to Personalization and Positivity. When covering the same events, reports by the good news outlets show an overemphasis on Positivity, and those by the mainstream media demonstrate a more balanced distribution of the major news values. It is proposed that good news can serve as a valuable complement to top news in the mainstream media. Reports in the mainstream media tend to be more comprehensive and informative, and the relatively shorter reports in the good news outlets pay more attention to the positive aspects of the event that are effective in uplifting the readers’ mood.

Social robot detection based on user behavioral representation

Social robots aim to facilitate our lives by mimicking our behaviors to deliver information and interact with us. Unfortunately, some social robots are bred for sinister intention, which often spread fake news, even threatening personal and national security. To effectively detect these robots, some existing works utilize basic user attributes for clustering, such as creation time and other information, but ignore the behavioral features of social robots, which are important a priori information for detection, and their absence leads to poor performance. To address this problem, we construct the Social Robot Behavior Detection model, which employs social robots' behavioral habits in disseminating content. Specifically, our method consists of three parts. First, to accurately characterize news, we analyze news features from multiple views, which facilitates representing users' habits of posting news. Second, a novel aggregation strategy is designed for aggregating user features to obtain accurate user representation. Finally, a classifier is used to detect whether user is social robots or not. We conduct analytical experiments on two public datasets, and the results show that our model has better detection performance, which demonstrates that our approach outperforms existing works on social robot detection. Our source code is available at https://github.com/NPURG/SRDB.

Exploring Public Perception of News and Citizenship and Its Relationship with News Use

ABSTRACT This survey study (N = 1065) examines Americans’ perception of news and citizenship and its relationship with consumption of news via diverse media—traditional news media, cable news channels and political satire—that include features of news yet differ from one another in their adherence to journalistic norms, such as fairness, accuracy and objectivity, to varying degrees. Findings suggest that Americans still hold high expectations for news to be fair, accurate and objective and value the role of news in our democracy and democratic citizenship, yet have negative assessments of their performance, such that news media fall short of the democratic ideal. These findings may speak to the declining public trust in media and growing perception of media bias.

Text-image multimodal fusion model for enhanced fake news detection.

In the era of rapid internet expansion and technological progress, discerning real from fake news poses a growing challenge, exposing users to potential misinformation. The existing literature primarily focuses on analyzing individual features in fake news, overlooking multimodal feature fusion recognition. Compared to single-modal approaches, multimodal fusion allows for a more comprehensive and enriched capture of information from different data modalities (such as text and images), thereby improving the performance and effectiveness of the model. This study proposes a model using multimodal fusion to identify fake news, aiming to curb misinformation. The framework integrates textual and visual information, using early fusion, joint fusion and late fusion strategies to combine them. The proposed framework processes textual and visual information through data cleaning and feature extraction before classification. Fake news classification is accomplished through a model, achieving accuracy of 85% and 90% in the Gossipcop and Fakeddit datasets, with F1-scores of 90% and 88%, showcasing its performance. The study presents outcomes across different training periods, demonstrating the effectiveness of multimodal fusion in combining text and image recognition for combating fake news. This research contributes significantly to addressing the critical issue of misinformation, emphasizing a comprehensive approach for detection accuracy enhancement.

Analyzing common lexical features of fake news using multi-head attention weights

Numerous approaches have been developed to identify fake news through machine learning; however, these methods are predominantly assessed using singular datasets specific to certain fields, leading to a scarcity of research on versatile models adaptable to a range of domains. This study evaluates the adaptability of a fake news detection model across diverse fields, employing three distinct datasets. Furthermore, the study leverages the multi-head attention feature of bidirectional encoder representations from transformers (BERT) to scrutinize the feature extraction process in the model. In our analysis, we focused on words that are commonly emphasized by machine learning in fake news detection. The dataset comprised 27,442 instances of genuine news and 28,359 instances of fabricated news, each distinctly labeled. To examine the focal words, we utilized multi-head attention, a component of BERT. This mechanism assigns greater weight to words that receive more attention. Our investigation aimed to identify which words were assigned higher weights in each article. The findings indicate that while representing a minor percentage, a common characteristic of fake news is the heightened attention to words that influence the credibility of the article. To assess the versatility of the model, we applied the model trained on one dataset to classify other datasets. The results demonstrate a notable decline in accuracy, attributable to the distinctive characteristics of the training data. These observations suggest that common features among fake news, which could be extracted using the fine-tuned BERT model, are limited.

The Impact of Journalistic Cultures on Social Media Discourse: US Primary Debates in Cross-Lingual Online Spaces

This cross-lingual project examines how social media posts of Spanish- and English-language media impact incivility in user comments during the 2020 primary political debates in the United States. We analyzed Facebook posts of news organizations that hosted the debates and used a state-of-the-art machine-learning model to analyze the corresponding comments. Our findings reveal distinct journalistic cultures on the post-level: English-language media are significantly more likely to use interpretation while Spanish-language media employ more audience-engagement and factual reporting strategies. We argue that in order to understand incivility in social media discourse during political debates, we need to consider journalistic cultures: While interpretative reporting explains lower levels of incivility in the English-language discourse, factual reporting explains lower levels of incivility in the Spanish-language discourse. We suggest that we need to consider how features of news reporting (textual and visual) impact discourse quality directly but also indirectly via emotional arousal in comments.

Knowledge can wait? The epistemic conversion of new beat reporters

This study shows how, during the turbulent period of their initial months on the job, new beat reporters experience a shift in their basic approach to knowledge. This new epistemic approach encompasses two interconnected shifts: From seeing self-knowledge as a necessity to reliance on sources’ knowledge, and from prioritizing content knowledge to prioritizing journalistic knowledge. Findings suggest that reporting without knowledge isn’t a bug, but rather a major feature of news reporting; that at least during reporters’ first years, the main epistemic challenge is reporting despite the lack of beat knowledge; and that the foundations of source-reporter relations are laid down when the latter are at their weakest point in terms of power and knowledge, enabling sources’ to gain a dominant position in shaping the reported realities.

When ethnic minorities hit the headlines: The longitudinal associations between news features and adolescents' ethnic prejudice.

Ethnic prejudice poses great challenges to adolescents' adjustment to multicultural societies. However, little is known about the role of the media in influencing attitudes in adolescence. Combining information environment and ecological development theories, the current study examined the longitudinal associations between the quantity, valence (i.e., neutral, positive, and negative), and target (i.e., migrant, refugee, and foreigner) of the news about ethnic minority groups and youth's affective and cognitive prejudice. In total, 962 adolescents (Mage = 15.67, 48.13% females) completed questionnaires at two time points, and news data were gathered from a national newspaper. While news quantity did not matter, positive and negative news were respectively associated with reduced and increased levels of cognitive, but not affective, prejudice. Nuanced associations emerged when accounting for the news target. Results were replicated regardless of adolescents' direct consumption of newspapers. These findings highlight the role of the information environment and suggest the need to account for it in planning interventions.

Corpus-based Multi-dimensional Analysis of the Register Features of Financial News

Nowadays, people rely heavily on financial news media to get financial updates. But as is well known, for non-native speakers of English, in order to fully understand such news, they also need to learn some register features of such financial news besides adequate English language knowledge. The purpose of this study is to explore and analyze the linguistic features of English financial news, and to help readers effectively understand financial news. Specifically, this study employes multi-feature/multi-dimensional analysis (henceforth MF/MD) method to analyze the register characteristics of English financial news based on the theory of register. Through analyzing the self-compiled corpus of financial news, it is found that that the financial news has four major register features: interactivity, persuasion, information and professionalism. These findings will shed lights on the understanding of financial news as well as the learning and teaching of financial/business English.

American Association of Neurological Surgeons/Congress of the Neurological Surgeons Section on Tumors Guidelines: Assessing Their Impact on Brain Tumor Clinical Practice.

Clinical guidelines direct healthcare professionals toward evidence-based practices. Evaluating guideline impact can elucidate information penetration, relevance, effectiveness, and alignment with evolving medical knowledge and technological advancements. As the American Association of Neurological Surgeons/Congress of Neurological Surgeons Section on Tumors marks its 40th anniversary in 2024, this article reflects on the tumor guidelines established by the Section over the past decade and explores their impact on other publications, patents, and information dissemination. Six tumor guideline categories were reviewed: low-grade glioma, newly diagnosed glioblastoma, progressive glioblastoma, metastatic brain tumors, vestibular schwannoma, and pituitary adenomas. Citation data were collected from Google Scholar and PubMed. Further online statistics, such as social media reach, and features in policy, news, and patents were sourced from Altmetric. Online engagement was assessed through website and CNS+ mobile application visits. Data were normalized to time since publication. Metastatic Tumor guidelines (2019) had the highest PubMed citation rate at 26.1 per year and webpage visits (29 100 page views 1/1/2019-9/30/2023). Notably, this guideline had two endorsement publications by partner societies, the Society of Neuro-Oncology and American Society of Clinical Oncology, concerning antiepileptic prophylaxis and steroid use, and the greatest reach on X (19.7 mentions/y). Citation rates on Google Scholar were led by Vestibular Schwannoma (2018). Non-Functioning Pituitary Adenoma led Mendeley reads. News, patent, or policy publications were led by low-grade glioma at 1.5/year. Our study shows that the American Association of Neurological Surgeons/Congress of Neurological Surgeons Section on Tumors guidelines go beyond citations in peer-reviewed publications to include patents, online engagement, and information dissemination to the public.

Design of a news recommendation model based on collaborative filtering and LSTM

This paper aims to design a news recommendation model based on user preferences to address the issues in recommendation systems under large datasets. Initially, four datasetsclick_history, news, news_embedding, and user_predictwere integrated into a single table, followed by data cleaning and feature engineering. Due to the large volume of data, this paper proposes necessary data filtering for the training and testing sets, utilizing temporal data to construct user feature vectors and news feature vectors. One challenge is how to effectively integrate user preferences and news features into the model to avoid overfitting or underfitting. In the model design and building phase, different methods were attempted to merge the information of users and news. Ultimately, the user preference features were processed using a fully connected layer, and the news embedding vectors were handled using an LSTM model. These two data parts were then combined into another fully connected layer, using ReLU as the activation function and CELoss as the loss function. Subsequently, the model's hyperparameters were adjusted and evaluated, achieving favorable model performance. The prediction accuracy for recommending news to users in user_predict was calculated as an evaluation criterion. Finally, this paper proposes directions for generalization and optimization in three aspects: data processing, model design, and experimental design. This includes data processing methods, potential improvements or mechanisms that could be incorporated into the model, and hyperparameter tuning. The paper primarily proposes data filtering to solve the problem of excessive data scale, which may aid in addressing recommendation system issues under large-scale datasets.

What Chinese Internet Users “Like” to Read: Selective Exposure in a Restricted Information Environment

Abstract We study the phenomenon of selective exposure in China's restricted online information environment. Through an experimental survey study, we measure to what extent features of online news, such as popularity (i.e. number of “likes”), influence information selection among Chinese internet users (“netizens”). We find evidence of preferences for news information according to news topic and the nationalist sentiments of individuals. Generally, for news about domestic affairs, Chinese netizens prefer articles that take the opposite position of the government; for foreign affairs, they prefer articles aligned with the government's position. However, nationalistic individuals are more likely to select domestic affairs articles congruent with the Chinese government's issue framing. We also find social endorsements to be highly influential on news selection behaviour. Popular posts with many “likes” attract Chinese netizens to the point where they select content they may not otherwise read, even though the internet environment is easily manipulated.

Finding common features in multilingual fake news: a quantitative clustering approach

Abstract Since the Internet is a breeding ground for unconfirmed fake news, its automatic detection and clustering studies have become crucial. Most current studies focus on English texts, and the common features of multilingual fake news are not sufficiently studied. Therefore, this article uses English, Russian, and Chinese as examples and focuses on identifying the common quantitative features of fake news in different languages at the word, sentence, readability, and sentiment levels. These features are then utilized in principal component analysis, K-means clustering, hierarchical clustering, and two-step clustering experiments, which achieved satisfactory results. The common features we proposed play a greater role in achieving automatic cross-lingual clustering than the features proposed in previous studies. Simultaneously, we discovered a trend toward linguistic simplification and economy in fake news. Furthermore, fake news is easier to understand and uses negative emotional expressions in ways that real news does not. Our research provides new reference features for fake news detection tasks and facilitates research into their linguistic characteristics.

NRMG: News Recommendation With Multiview Graph Convolutional Networks

The emergence of a news recommendation system can effectively improve the news reading experience of users. The most important task of the system is how to learn news and user representations accurately. In the process of learning news representations, most of the current research works do not fully utilize the news features, which makes it difficult to learn more comprehensive news representations. Most research work only learns user representations from a single perspective, which may not be sufficient to learn diverse and dynamic user representations. Therefore, we propose a news recommendation system with a multiview graph convolutional network (NRMG). It contains two parts: news representation and user representation. The knowledge–content collaboration network is adapted to learn news representations from news content and entities, while the multiview graph convolutional network (GCN) is utilized to learn user representations from the user’s click history. The advantage of the NRMG system is that we not only expand the available features by constructing a subclass knowledge graph (KG), but also effectively improve the ability of the news recommendation system to accurately learn news and user representations. Experimental results on the real dataset MIcrosoft News Dataset (MIND) show that the NRMG achieves a 2.25% improvement in area under the receiver operating characteristic (ROC) curve (AUC) value compared with state-of-the-art methods.

People News - Spring 2024

Spring 2024 People News features member accomplishments as well as remembrances of Joan B. Berkowitz, Yasuhiko Ito, and David A. Vermilyea, among others

A Hotspot-Aware Personalized News Recommendation Mechanism Based on DistilBERT-TC-MA

Aiming at the problems of existing news recommendation methods, such as inadequate exploration of the semantic information of news, neglecting potential hotspot features of news, and challenging the balance between user preferences and hotspot features, a hotspot-aware personalized news recommendation model (DistilBERT-TC-MA) is suggested, which integrates the distilled version of BERT (DistilBERT), text convolutional neural network (TextCNN), and multilayer attention (MA). First, it takes full advantage of DistilBERT, TextCNN, and self-attention mechanism to achieve news encoding. Following this, representations of trending news are dynamically aggregated using the attention mechanism, while user preferences are mined utilizing user click history. Finally, in order to successfully accomplish the click prediction of candidate news, the hotspot features, user preferences, and candidate news are ultimately combined using a click predictor. The experimental results of the suggested DistilBERT-TC-MA model on MIND dataset are better than several other advanced methods.

GBCA: Graph Convolution Network and BERT combined with Co-Attention for fake news detection

Social media has evolved into a widely influential information source in contemporary society. However, the widespread use of social media also enables the rapid spread of fake news, which can pose a significant threat to national and social stability. Current fake news detection methods primarily rely on graph neural network, which analyze the dissemination patterns of news articles. Nevertheless, these approaches frequently overlook the semantic characteristics of the news content itself. To address this problem, we propose a novel Graph Convolution Network and BERT combined with Co-Attention (GBCA) model. Initially, we conduct training for a graph classification task on the propagation structure of fake news. Subsequently, we employ the BERT model to extract semantic features in fake news. Finally, we utilize co-attention mechanism to integrate the two dimensions of propagation structure and semantic features, which enhances the effectiveness of fake news detection. Our model outperforms baseline methods in terms of accuracy and training time, as demonstrated by experiments on three public benchmark datasets.

The Scary World Syndrome: News Orientations, Negativity Bias, and the Cultivation of Anxiety

ABSTRACT Negativity bias is one of the most salient features of news reporting. According to cultivation theory, this bias can foster anxiety about societal issues among news audiences. The relationship is, however, likely to depend on the audience’s news orientations and the issue under consideration. Drawing on a content analysis of mainstream and alternative news media and a three-wave panel survey, both conducted in Sweden, we examine how general and alternative news orientations relate to egotropic anxiety (worry about being personally affected or harmed) about violent crimes and climate change. The results show that while alternative news media portray violent crimes more negatively than mainstream news media, the opposite is true for climate change, which mainstream news media portray more negatively than alternative news media. Consistent with this finding, alternative news orientation is related to higher levels of anxiety about violent crimes, while general news orientation is related to higher levels of anxiety about climate change, illustrating how people seek information that concur with and thereby maintain or reinforce their beliefs. These results have consequences both for cultivation theory and for our understanding of the role played by mainstream and alternative news media in society.

A Corpus-based Comparison of Lexical Features in English News: China Daily and CNNs Reports about Russia-Ukraine Conflict as Examples

The news plays a crucial role in disseminating information to the public. The use and preferences of vocabulary in news articles reflect the language proficiency, attitudes, and positions of news writers. Therefore, this study examines the differences in vocabulary characteristics between China Daily, a Chinese news organization, and CNN, a US news organization, in their news writing on the Russia-Ukraine conflict. Through corpus-based research methods, the study aims to explore the differences in lexical features and provide insights for journalists and English writing learners in terms of vocabulary selection and comprehension when writing and reading English news about the Russia-Ukraine conflict and related war and conflict events.

Multimodal integration for fake news detection on social media platforms

The widespread dissemination of fake news on social media platforms can cause serious social impact, making the detection of fake news on social media platforms an urgent problem to be solved. Up to now, scholars have proposed various methods ranging from traditional manual feature extraction to deep learning algorithms for detecting fake news. However, these methods still have some limitations and two difficult problems: (1) How to learn informative news feature representations without losing information as much as possible? (2) How to effectively fuse multi-modal information to obtain high-order complementary information about news and enhance fake news detection? To overcome these two difficulties, this article proposes a multi-modal fusion fake news detection model. Firstly, the model uses BERT and VGG-19 to obtain the text and image feature representations of news content, respectively, and then further fuses multi-modal information through a multi-modal attention mechanism module to obtain high-order complementary information between different modalities, thereby obtaining informative news feature representations for fake news detection. Experimental results on two real-world public datasets demonstrate the effectiveness of our model compared to mainstream detection methods.