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
Veronica Maidel, Peretz Shoval, Bracha Shapira and Meirav Taieb‐Maimon
The purpose of this paper is to describe a new ontological content‐based filtering method for ranking the relevance of items for readers of news items, and its evaluation. The…
Abstract
Purpose
The purpose of this paper is to describe a new ontological content‐based filtering method for ranking the relevance of items for readers of news items, and its evaluation. The method has been implemented in ePaper, a personalised electronic newspaper prototype system. The method utilises a hierarchical ontology of news; it considers common and related concepts appearing in a user's profile on the one hand, and in a news item's profile on the other hand, and measures the “hierarchical distances” between these concepts. On that basis it computes the similarity between item and user profiles and rank‐orders the news items according to their relevance to each user.
Design/methodology/approach
The paper evaluates the performance of the filtering method in an experimental setting. Each participant read news items obtained from an electronic newspaper and rated their relevance. Independently, the filtering method is applied to the same items and generated, for each participant, a list of news items ranked according to relevance.
Findings
The results of the evaluations revealed that the filtering algorithm, which takes into consideration hierarchically related concepts, yielded significantly better results than a filtering method that takes only common concepts into consideration. The paper determined a best set of values (weights) of the hierarchical similarity parameters. It also found out that the quality of filtering improves as the number of items used for implicit updates of the profile increases, and that even with implicitly updated profiles, it is better to start with user‐defined profiles.
Originality/value
The proposed content‐based filtering method can be used for filtering not only news items but items from any domain, and not only with a three‐level hierarchical ontology but any‐level ontology, in any language.
Details
Keywords
Duen-Ren Liu, Yun-Cheng Chou and Ciao-Ting Jian
Online news websites provide diverse article topics, such as fashion news, entertainment and movie information, to attract more users and create more benefits. Recommending movie…
Abstract
Purpose
Online news websites provide diverse article topics, such as fashion news, entertainment and movie information, to attract more users and create more benefits. Recommending movie information to users reading news online can enhance the impression of diverse information and may consequently improve benefits. Accordingly, providing online movie recommendations can improve users’ satisfactions with the website, and thus is an important trend for online news websites. This study aims to propose a novel online recommendation method for recommending movie information to users when they are browsing news articles.
Design/methodology/approach
Association rule mining is applied to users’ news and movie browsing to find latent associations between news and movies. A novel online recommendation approach is proposed based on latent Dirichlet allocation (LDA), enhanced collaborative topic modeling (ECTM) and the diversity of recommendations. The performance of proposed approach is evaluated via an online evaluation on a real news website.
Findings
The online evaluation results show that the click-through rate can be improved by the proposed hybrid method integrating recommendation diversity, LDA, ECTM and users’ online interests, which are adapted to the current browsing news. The experiment results also show that considering recommendation diversity can achieve better performance.
Originality/value
Existing studies had not investigated the problem of recommending movie information to users while they are reading news online. To address this problem, a novel hybrid recommendation method is proposed for dealing with cross-type recommendation tasks and the cold-start issue. Moreover, the proposed method is implemented and evaluated online in a real world news website, while such online evaluation is rarely conducted in related research. This work contributes to deriving user’s online preferences for cross-type recommendations by integrating recommendation diversity, LDA, ECTM and adaptive online interests. The research findings also contribute to increasing the commercial value of the online news websites.
Details
Keywords
Does the same news item on three different online news platforms, namely: newspapers, blogs and video news, impact each of perceived source credibility, likeability, content…
Abstract
Purpose
Does the same news item on three different online news platforms, namely: newspapers, blogs and video news, impact each of perceived source credibility, likeability, content believability and attitude toward a message, differently? The paper aims to discuss these issues.
Design/methodology/approach
An experimental approach conducted among university students is adopted.
Findings
The psychometric properties of the instruments used are supported. Results showed that source credibility did not differ for the three platforms, indicating that respondents did not find one platform less credible than another. However, differences were observed on each of content believability, likeability and attitude toward the message. Online newspapers scored highest in all of these. Blogs came second in both content believability and likeability, while video news came second in attitude toward a message.
Research limitations/implications
A number of limitations are noted. In particular, generalisability of findings to all youths in the country and beyond must be done with extreme caution.
Practical implications
The results suggest that the medium does change the message and online newspapers as a platform retain an advantage despite the arrival of alternative new media platforms, represented by blogs and video news. The latter emerges as the least effective indicating that respondents appear to prefer reading their news.
Originality/value
The paper uses an experimental approach and robust measures to compare news platforms across a number of elements in the communication process among a strong user segment.
Details
Keywords
This paper aims to take, as a starting point, the contribution of audiovisual documentation to TV news programs, the impact of digitalisation in the organisation and design of…
Abstract
Purpose
This paper aims to take, as a starting point, the contribution of audiovisual documentation to TV news programs, the impact of digitalisation in the organisation and design of audiovisual documentation's services is analysed.
Design/methodology/approach
Data, collected by a quantitative and qualitative research on: the use of audiovisual documentation in the news, documentation requests processed by journalists, and the study of the operation of documentation services of six TV stations, serve as a basis to analyse the factors that must be taken into account when it comes to designing query systems of digital audiovisual documentation, so that these systems meet the needs of journalists and can be used with satisfactory results by the users.
Findings
Audio‐visual documentation is one of the constituent elements of TV information on current events, as much for its quantitative presence (40 percent of the news) as for its qualitative contribution to news messages, as well as for its general use in all the news sections. Audiovisual documentation has a greater presence in important news, and can carry out informative, completive or illustrative functions. News programs use the audiovisual documentation that these same programs have generated, using it mainly as a purely visual documentation. In documentation services, the journalist asks mainly for people's images and, to a lesser extent, formal groups and the news. A second group of categories collects around 10 percent of requests: places, animal‐thing, natural phenomena, informal group; while the remaining categories (concept and work) have a marginal incidence. The analysis of documentation use in the news, as well as of the content of requests made by the journalists, offers important clues when it come to designing documentary information systems, specially regarding the analysis of audiovisual douments and databases' query, used directly by the end user.
Research limitations/implications
Collected data regarding analogue TV are used to make forecasts about what should be documentation in digital TV.
Originality/value
The detailed analysis of the use of audiovisual documentation in the news, as well as of the requests made by the journalists to documentation services, constitutes an important guide when it comes to successfully designing the new digital systems of audiovisual documentation.
Details
Keywords
Dimitris Trimithiotis, Iacovos Ioannou, Vasos Vassiliou, Panicos Christou, Stelios Chrysostomou, Erotokritos Erotokritou and Demetris Kaizer
This article explores the synergy between journalism studies and computer science in the context of observing online news. By establishing web applications of online media…
Abstract
Purpose
This article explores the synergy between journalism studies and computer science in the context of observing online news. By establishing web applications of online media observatories as research tools, researchers can employ various analytical approaches to gain valuable insights into online news discourse and production.
Design/methodology/approach
Drawing eight months of data (01.08.2022–30.04.2023) from the Labservatory’s web application, i.e. over 250,000 news items, the article demonstrates how some of this web application’s main functionalities may be useful in implementing (1) news flow analysis, (2) news topic distribution analysis and (3) media discourse analysis.
Findings
The capabilities provided by this web application, (1) to simultaneously analyse the daily news production of ten media outlets with varying features, (2) to rapidly collect a large volume of news items, (3) to identify the news categories as classified by the media themselves, (4) to present the results of the search in relevance order and (5) to automatically generate a search report, highlight the significance of this interdisciplinary collaboration for implementing comprehensive analyses of online news.
Originality/value
The article concludes by emphasising the importance of continuing this joint effort, as it opens new avenues for further research and provides a deeper grasp of the intricate relationship between journalism, technology and society in the digital era. The Labservatory also contributes to society since it may be used by the broader public for immediate access to more pluralistic information and thus for promoting both news media literacy and news media accountability.
Details
Keywords
Venancio Tauringana and Gin Chong
This paper reports the results of an investigation into the neutrality of the narrative discussion of financial performance and position, as evidenced in 179 annual reports of UK…
Abstract
This paper reports the results of an investigation into the neutrality of the narrative discussion of financial performance and position, as evidenced in 179 annual reports of UK listed companies. Neutrality of narrative discussion was determined by comparing the average proportions of good and bad news contained in the narrative and statutory accounts sections of the annual reports. The results of a comparison of the proportion of good news in the two sections of the annual reports suggest that the narrative sections contained a significantly higher proportion of good news than the statutory accounts sections. Comparison of proportions of bad news, however, indicates that the narrative sections contained a significantly lower proportion of bad news compared to the statutory accounts sections. Finally, the results also suggest that the proportion of good news as compared to bad news in the narrative sections is significantly higher than the proportion of good news compared to bad news in the statutory accounts section. The results are consistent with the suggestion that company management highlights good news in narrative discussions. The implications of the findings for company management, users, auditors and regulators are discussed.
Details
Keywords
Alberto Díaz, Pablo Gervás, Antonio García and Inmaculada Chacón
Through an evaluation of system performance and user satisfaction for the Mercurio system, considers the general applicability and usefulness of different methods of specifying…
Abstract
Through an evaluation of system performance and user satisfaction for the Mercurio system, considers the general applicability and usefulness of different methods of specifying user interest for the general case of digital news services. Outlines the specific characteristics distinguishing such systems from more general information systems and discusses their effect. Proposes an evaluation blueprint for them starting from information retrieval procedures, existing work on search engine evaluation, and a close study of the working principles and the required evaluation according to the particular properties and conditions of the services under consideration. Presents and discusses actual evaluation results for system tests based both on real users and customised test cases. Conclusions cover the nature of the information handling tasks that digital news services are faced with, the relative merits of sections, categories and keywords with respect to this particular set of tasks, and the risks of careless application of recall and precision measures in systems such as these.
Details
Keywords
The present article seeks to further the analysis by examining the epitext employed by the press seeing as the epitext in the digital spaces might have given Animal Farm and its…
Abstract
Purpose
The present article seeks to further the analysis by examining the epitext employed by the press seeing as the epitext in the digital spaces might have given Animal Farm and its Thai re-translations a new lease on life.
Design/methodology/approach
The interest in the study of translation and paratext has primarily been in analysing peritextual material of translated texts, not on the epitext, the distanced elements located outside the book. To add to a limited amount of research into epitext, this study focusses on the element that is external to the published re-translations: the news items published by the media in the Thai and English languages from May–June 2019, immediately after the Thai PM’s book recommendation.
Findings
These news items, as an epitextual element, primed, explained, contextualised, justified and tempted readers. The “Afterlife” of Animal Farm in Thailand is sustained by political upheavals and re-translations. Rather than through their textual qualities, the re-translations of Animal Farm compete with each other through epitext.
Originality/value
In discussing literary re-translation of Animal Farm in the digital age, Genette’s categories of paratextual field are not without their merits. The materials examined in this article are posted by web administrators with collective identity or institutional affiliation. In some of these news items or articles, materials created by different paratextual creators are selectively coalesced within a singular textual space. The site users or news readers encounter various elements in the texts that had been curated by journalists. In other words, these elements had been consciously crafted.
Details
Keywords
Rahul Rajan Lexman, Gopinath Krishnan, Rupashree Baral and Shameem Cina Thomas
This paper aims to explore and unravel the contents portrayed in online news discourses on massive open online courses (MOOCs). Considering sociological dimensions and…
Abstract
Purpose
This paper aims to explore and unravel the contents portrayed in online news discourses on massive open online courses (MOOCs). Considering sociological dimensions and journalistic strategies, this study examines how online news media reflects, shapes and informs narratives about the social acceptance and use of the MOOC model of learning.
Design/methodology/approach
Using the Gioia methodology as the overarching framework, this study adopted a two-staged qualitative content analysis of 1,162 online news items from the websites of the top seven online English newspapers of India, published between May 2012 and September 2023. In subsequent semi-structured interviews with subject matter experts, broad themes were identified. In addition, this study integrated Van Dijk’s ideological square model with media content theories to comprehensively analyze the intricate complexities in media depictions of MOOCs.
Findings
While manifest content analysis revealed the emergence of 25 categories, latent content analysis unveiled six broad themes: “announcements, user stages, characteristics, benefits, changing facets, and educational inequalities,” which are associated with the MOOC model. Application of Van Dijk’s model evidenced the usage of a positive self-representation strategy by Indian online news media until mid-2020. The application of media content theories underscored the predominant usage of reframing as a journalistic strategy to maintain reader interest in MOOC-related content in online news items, emphasizing the dynamic nature of media portrayals of social phenomena such as MOOCs.
Practical implications
The depth of MOOC-related coverage and the increasing number of news articles discussing MOOCs in Indian online media signify a growing acceptance of this educational innovation in society. Insights from emergent themes can aid administrators and platforms to effectively design and deliver future courses. In addition, understanding these themes can guide the development of media strategies to address contextual issues such as educational inequalities arising from MOOCs. This study also focuses on the necessity of upholding journalistic ethics in content dissemination.
Originality/value
This study provides a comprehensive synthesis of various themes and journalistic strategies adopted by online news media over the last decade in MOOC-based narratives in India. Given the distinctive Indian context, wherein MOOCs are growing rapidly amid widening digital inequalities, this research addresses calls within information systems literature to explore this phenomenon. It pioneers the integration of communication and mass media theories to analyze the complex sociological dynamics in news discourses on MOOCs, offering a novel perspective on the intersection of media representation and educational innovation.