Search results
1 – 10 of over 51000Krishnadas Nanath, Supriya Kaitheri, Sonia Malik and Shahid Mustafa
The purpose of this paper is to examine the factors that significantly affect the prediction of fake news from the virality theory perspective. The paper looks at a mix of…
Abstract
Purpose
The purpose of this paper is to examine the factors that significantly affect the prediction of fake news from the virality theory perspective. The paper looks at a mix of emotion-driven content, sentimental resonance, topic modeling and linguistic features of news articles to predict the probability of fake news.
Design/methodology/approach
A data set of over 12,000 articles was chosen to develop a model for fake news detection. Machine learning algorithms and natural language processing techniques were used to handle big data with efficiency. Lexicon-based emotion analysis provided eight kinds of emotions used in the article text. The cluster of topics was extracted using topic modeling (five topics), while sentiment analysis provided the resonance between the title and the text. Linguistic features were added to the coding outcomes to develop a logistic regression predictive model for testing the significant variables. Other machine learning algorithms were also executed and compared.
Findings
The results revealed that positive emotions in a text lower the probability of news being fake. It was also found that sensational content like illegal activities and crime-related content were associated with fake news. The news title and the text exhibiting similar sentiments were found to be having lower chances of being fake. News titles with more words and content with fewer words were found to impact fake news detection significantly.
Practical implications
Several systems and social media platforms today are trying to implement fake news detection methods to filter the content. This research provides exciting parameters from a viral theory perspective that could help develop automated fake news detectors.
Originality/value
While several studies have explored fake news detection, this study uses a new perspective on viral theory. It also introduces new parameters like sentimental resonance that could help predict fake news. This study deals with an extensive data set and uses advanced natural language processing to automate the coding techniques in developing the prediction model.
Details
Keywords
Paula M.C. Swatman, Cornelia Krueger and Kornelia van der Beek
To provide an empirically based analysis and evaluation of the existing and possible future evolution of Internet business models within the digital content market, focusing…
Abstract
Purpose
To provide an empirically based analysis and evaluation of the existing and possible future evolution of Internet business models within the digital content market, focusing particularly on the possibilities for cooperation and coopetition within this market‐space.
Design/methodology/approach
The paper is based on a three‐year study of the European online news and online music sectors, comprising a set of preliminary, scene‐setting case studies of a number of major players within the European online news and music sectors; a detailed, two‐stage survey made up of online questionnaires and face‐to‐face interviews; and a small number of in‐depth case studies.
Findings
Provides a discussion of the changes taking place in the online news and music sectors, the evolution of the business models within them, the driving forces we have identified, and finally some predictions about what the future may hold for both these sectors.
Research limitations/implications
The research is indicative, rather than general – being centred on European participants in two sectors of the digital content market‐space in the period between May 2003 and August 2004.
Practical implications
A rich evaluation of these two fast‐moving digital content sectors, providing empirically based insights into the ways in which they are evolving and changing and into parallels with other, similar sectors of the digital content market.
Originality/value
This paper is the first major empirical evaluation of the digital content market‐space and offers practical assistance, as well as new theoretical insights on e‐business model evolution in this area.
Details
Keywords
Louisa Ha, Debipreeta Rahut, Michael Ofori, Shudipta Sharma, Michael Harmon, Amonia Tolofari, Bernadette Bowen, Yanqin Lu and Amir Khan
To provide human judgment input for computer algorithm development, this study examines the relative importance of source, content, and style cues in predicting the truthfulness…
Abstract
Purpose
To provide human judgment input for computer algorithm development, this study examines the relative importance of source, content, and style cues in predicting the truthfulness ratings of two common types of online health information: news stories and institutional news releases.
Design/methodology/approach
This study employed a multi-method approach using (1) a manual content analysis of 400 randomly selected online health news stories and news releases from HealthNewsReview.org and (2) an online experiment comparing truthfulness ratings between news stories and news releases.
Findings
Using content analysis, the authors found significant differences in the importance of source, content, and style cues in predicting truthfulness ratings of news stories and news releases: source and style cues predicted truthfulness ratings better than content cues. In the experiment, source credibility was the most important predictor of truthfulness ratings, controlling for individual differences. Experts have higher ratings for news media stories than news releases and lay people have no differences in rating the two news formats.
Practical implications
It is important for health educators to curb consumer trust in misinformation and increase health information literacy. Rather than solely reporting scientific evidence, educators should focus on addressing cues people use to judge the truthfulness of health information.
Originality/value
This is the first study that directly compares human judgments of health news stories and news releases. Using both the breadth of content analysis and experimental causality testing, the authors evaluate the relative importance of source, content, and style cues in predicting truthfulness ratings.
Details
Keywords
Srishti Sharma, Mala Saraswat and Anil Kumar Dubey
Owing to the increased accessibility of internet and related technologies, more and more individuals across the globe now turn to social media for their daily dose of news rather…
Abstract
Purpose
Owing to the increased accessibility of internet and related technologies, more and more individuals across the globe now turn to social media for their daily dose of news rather than traditional news outlets. With the global nature of social media and hardly any checks in place on posting of content, exponential increase in spread of fake news is easy. Businesses propagate fake news to improve their economic standing and influencing consumers and demand, and individuals spread fake news for personal gains like popularity and life goals. The content of fake news is diverse in terms of topics, styles and media platforms, and fake news attempts to distort truth with diverse linguistic styles while simultaneously mocking true news. All these factors together make fake news detection an arduous task. This work tried to check the spread of disinformation on Twitter.
Design/methodology/approach
This study carries out fake news detection using user characteristics and tweet textual content as features. For categorizing user characteristics, this study uses the XGBoost algorithm. To classify the tweet text, this study uses various natural language processing techniques to pre-process the tweets and then apply a hybrid convolutional neural network–recurrent neural network (CNN-RNN) and state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) transformer.
Findings
This study uses a combination of machine learning and deep learning approaches for fake news detection, namely, XGBoost, hybrid CNN-RNN and BERT. The models have also been evaluated and compared with various baseline models to show that this approach effectively tackles this problem.
Originality/value
This study proposes a novel framework that exploits news content and social contexts to learn useful representations for predicting fake news. This model is based on a transformer architecture, which facilitates representation learning from fake news data and helps detect fake news easily. This study also carries out an investigative study on the relative importance of content and social context features for the task of detecting false news and whether absence of one of these categories of features hampers the effectiveness of the resultant system. This investigation can go a long way in aiding further research on the subject and for fake news detection in the presence of extremely noisy or unusable data.
Details
Keywords
Rob Angell, Matthew Gorton, Paul Bottomley, Ben Marder, Shikhar Bhaskar and John White
Newsjacking (real-time deployment of news stories in communications) is now ubiquitous for brands using social media. Despite its pervasiveness, little analysis of its…
Abstract
Purpose
Newsjacking (real-time deployment of news stories in communications) is now ubiquitous for brands using social media. Despite its pervasiveness, little analysis of its effectiveness exists. The purpose of this paper is to test if newsjacking positively influences various consumer responses (attitude toward content, brand attitude and purchase intent). Taking an audience perspective supported by the elaboration likelihood model, the research also establishes if a higher level of news involvement, as well as an ability to recognize the story behind the content, enhances the effectiveness of newsjacking content.
Design/methodology/approach
An experimental design using taglines (newsjacking vs non-topical content) from a real BMW campaign was tested on a sample of 252 consumers. Three research questions pertaining to the effectiveness of newsjacking were specified and analyzed within a structural equation modeling framework.
Findings
The findings support the conclusion that newsjacking is an effective communication tool. More favorable consumer responses were elicited in the newsjacking condition, as compared to content deploying a non-topical tagline. In addition, recipients reporting a higher level of news involvement rated the content more favorably in the newsjacking (vs the non-topical) condition. Deploying news stories that are more recognizable increases the chances of successful newsjacking. Messages received by those with higher product involvement (category level: cars) were more effective regardless of the type of the appeal.
Originality/value
The authors contribute to the communications and social media literatures by investigating the effectiveness of an emerging but popular tactic leveraged by content creators. The work builds upon the limited research that has tested consumer responses to newsjacking. From a practical perspective, the research provides insight into the type of audience and situations most likely to yield a favorable outcome from newsjacking.
Details
Keywords
The creation and dissemination of fake news can have severe consequences for a company’s brand. Researchers, policymakers and practitioners are eagerly searching for solutions to…
Abstract
Purpose
The creation and dissemination of fake news can have severe consequences for a company’s brand. Researchers, policymakers and practitioners are eagerly searching for solutions to get us out of the “fake news crisis”. Here, one approach is to use automated tools, such as artificial intelligence (AI) algorithms, to support managers in identifying fake news. The study in this paper demonstrates how AI with its ability to analyze vast amounts of unstructured data, can help us tell apart fake and real news content. Using an AI application, this study examines if and how the emotional appeal, i.e., sentiment valence and strength of specific emotions, in fake news content differs from that in real news content. This is important to understand, as messages with a strong emotional appeal can influence how content is consumed, processed and shared by consumers.
Design/methodology/approach
The study analyzes a data set of 150 real and fake news articles using an AI application, to test for differences in the emotional appeal in the titles and the text body between fake news and real news content.
Findings
The results suggest that titles are a strong differentiator on emotions between fake and real news and that fake news titles are substantially more negative than real news titles. In addition, the results reveal that the text body of fake news is substantially higher in displaying specific negative emotions, such as disgust and anger, and lower in displaying positive emotions, such as joy.
Originality/value
This is the first empirical study that examines the emotional appeal of fake and real news content with respect to the prevalence and strength of specific emotion dimensions, thus adding to the literature on fake news identification and marketing communications. In addition, this paper provides marketing communications professionals with a practical approach to identify fake news using AI.
Details
Keywords
Berna Haktanirlar Ulutas and A. Attila Islier
A layout problem may deal with the assignment and arrangement of buildings in a green field, location and/or relocation of machines/departments in manufacturing facilities, and so…
Abstract
Purpose
A layout problem may deal with the assignment and arrangement of buildings in a green field, location and/or relocation of machines/departments in manufacturing facilities, and so on. If multi‐periods are considered, the problem is called a dynamic layout problem in manufacturing environments. Designing web pages, especially internet newspaper layouts, might also be considered dynamic layout problems. This study aims to introduce a layout procedure for the front page of internet newspapers.
Design/methodology/approach
The news contents are ranked and selected based on their characteristic attributes. Then they are assigned to locations on dynamic content area of the front page. Layout optimization is made by use of Clonal Selection Algorithm (CSA). Finally, an illustrative example is provided and concepts for real life applications are discussed. The proposed method is based on CSA, which is a nature‐inspired technique. The novel heuristic is applied to a simulated system to depict how the news content layouts can be optimized in dynamic environments.
Findings
The capacity for addition of new news contents and removal of the old turns the internet newspaper environment into a dynamic structure. A systematic layout method for internet newspapers is developed to fill the gap.
Practical implications
The results are encouraging for real life applications of internet newspapers. The study has also introduced a new site for the manufacturing area. In the classic dynamic layout model, the machine locations and the number of available machines are assumed to be fixed. But the concept of introducing/removing news contents can be adapted to the machines at the manufacturing facilities.
Originality/value
The paper's value lies in showing that the front page layout is not considered to optimize the locations of the articles. Also, the proposed algorithm is applied to solve these kinds of problems.
Details
Keywords
Duen-Ren Liu, Yang Huang, Jhen-Jie Jhao and Shin-Jye Lee
Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on…
Abstract
Purpose
Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.
Design/methodology/approach
The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.
Findings
This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.
Originality/value
As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.
Details
Keywords
Scottie Kapel and Krista D. Schmidt
The purpose of this paper is to describe the challenges associated with identifying newspapers of record for local, regional and national newspapers, specifically as those…
Abstract
Purpose
The purpose of this paper is to describe the challenges associated with identifying newspapers of record for local, regional and national newspapers, specifically as those challenges pertain to students’ news media literacy. Visual literacy and information literacy intersections are explored.
Design/methodology/approach
Newspapers of record for province/territory and state areas of Canada and the United States of America were identified for student project purposes. Criteria for newspaper of record qualification were investigated, refined, and applied to all newspapers reviewed.
Findings
Distinguishing newspapers of record based on traditional criteria is inadequate in an online environment. Criteria must be more flexible and address both the visual as well as the content aspects of newspapers. Neither database access nor native website access alone is sufficient for identifying these newspapers. Straightforward and definitive identification of these newspapers will no longer be possible.
Practical implications
Librarians will be faced with focusing on content or visual literacy, addressing both in a meaningful way during a single instruction session will be difficult. More strategic instruction within and across disciplines is necessary to produce news media-literate and savvy students.
Originality/value
News media literacy for students in all disciplines is an urgent need and must incorporate both visual and content literacies. In a time of proliferation of news sources, understanding the challenges associated with identifying newspapers of record for both librarians and students is a necessary step in this area of information literacy.
Details