scholarly journals Pitch Proposal: Recommenders with a Mission - Assessing Diversity in News Recommendations

2020 ◽  
pp. 554-561
Author(s):  
Sanne Vrijenhoek ◽  
Natali Helberger
Keyword(s):  
Social Science ◽  
Recommender Systems ◽  
Recommender System ◽  
Crucial Role ◽  
Selective Exposure ◽  
Fake News ◽  
Quantitative Metrics ◽  
Digital News ◽  
Filter Bubbles ◽  
Ongoing Project

AbstractBy helping the user find relevant and important online content, news recommenders have the potential to fulfill a crucial role in a democratic society. Simultaneously, recent concerns about filter bubbles, fake news and selective exposure are symptomatic of the disruptive potential of these digital news recommenders. Recommender systems can make or break filter bubbles, and as such can be instrumental in creating either a more closed or a more open internet. This document details a pitch for an ongoing project that aims to bridge the gap between normative notions of diversity, rooted in democratic theory, and quantitative metrics necessary for evaluating the recommender system. Our aim is to get feedback on a set of proposed metrics grounded in social science interpretations of diversity.

scholarly journals Credibility of Digital Political News in Spain: Comparison between Traditional Media and Social Media

2021 ◽  
Vol 10 (5) ◽  
pp. 170
Author(s):  
Reinald Besalú ◽  
Carles Pont-Sorribes
Keyword(s):  
Social Media ◽  
News Item ◽  
Digital Television ◽  
Fake News ◽  
Traditional Media ◽  
Political News ◽  
Digital News ◽  
Key Factor ◽  
The Mean ◽  
Digital Formats

In the context of the dissemination of fake news and the traditional media outlets’ loss of centrality, the credibility of digital news emerges as a key factor for today’s democracies. The main goal of this paper was to identify the levels of credibility that Spanish citizens assign to political news in the online environment. A national survey (n = 1669) was designed to assess how the news format affected credibility and likelihood of sharing. Four different news formats were assessed, two of them linked to traditional media (digital newspapers and digital television) and two to social media (Facebook and WhatsApp). Four experimental groups assigned a credibility score and a likelihood of sharing score to four different political news items presented in the aforementioned digital formats. The comparison between the mean credibility scores assigned to the same news item presented in different formats showed significant differences among groups, as did the likelihood of sharing the news. News items shown in a traditional media format, especially digital television, were assigned more credibility than news presented in a social media format, and participants were also more likely to share the former, revealing a more cautious attitude towards social media as a source of news.

scholarly journals A Systematic Review of Recommender Systems and Their Applications in Cybersecurity

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5248
Author(s):  
Aleksandra Pawlicka ◽  
Marek Pawlicki ◽  
Rafał Kozik ◽  
Ryszard S. Choraś
Keyword(s):  
Systematic Review ◽  
Recommender Systems ◽  
Recommender System ◽  
State Of The Art ◽  
The State ◽  
Advantages And Disadvantages ◽  
Comprehensive Survey ◽  
Security Concerns ◽  
Valuable Role

This paper discusses the valuable role recommender systems may play in cybersecurity. First, a comprehensive presentation of recommender system types is presented, as well as their advantages and disadvantages, possible applications and security concerns. Then, the paper collects and presents the state of the art concerning the use of recommender systems in cybersecurity; both the existing solutions and future ideas are presented. The contribution of this paper is two-fold: to date, to the best of our knowledge, there has been no work collecting the applications of recommenders for cybersecurity. Moreover, this paper attempts to complete a comprehensive survey of recommender types, after noticing that other works usually mention two–three types at once and neglect the others.

Modelling trust networks using resistive circuits for trust-aware recommender systems

2016 ◽  
Vol 43 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Mehdi Hosseinzadeh Aghdam ◽  
Morteza Analoui ◽  
Peyman Kabiri
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Item Selection ◽  
Trust Networks ◽  
Trust Inference ◽  
Trust Information

Recommender systems have been widely used for predicting unknown ratings. Collaborative filtering as a recommendation technique uses known ratings for predicting user preferences in the item selection. However, current collaborative filtering methods cannot distinguish malicious users from unknown users. Also, they have serious drawbacks in generating ratings for cold-start users. Trust networks among recommender systems have been proved beneficial to improve the quality and number of predictions. This paper proposes an improved trust-aware recommender system that uses resistive circuits for trust inference. This method uses trust information to produce personalized recommendations. The result of evaluating the proposed method on Epinions dataset shows that this method can significantly improve the accuracy of recommender systems while not reducing the coverage of recommender systems.

The paradox of pluralism: A key to interpreting the online public sphere in the time of ‘encastellation’

2021 ◽  
Vol 13 (1) ◽  
pp. 141-148 ◽  
Author(s):  
Gabriele Giacomini
Keyword(s):  
Public Sphere ◽  
Political System ◽  
Selective Exposure ◽  
The Internet ◽  
New Concepts ◽  
Echo Chambers ◽  
Filter Bubbles

This viewpoint makes a theoretical effort to label the organization of the virtual sphere under new concepts: ‘encastellation’ and the ‘paradox of pluralism’. The former is a metaphorical synthesis of already-known concepts (selective exposure, polarization, homophily, echo chambers and filter bubbles). In the second case, we emphasize the existence of a ‘paradox of online pluralism’: the internet has increased the possibility for everyone to make their voice heard (in quantitative terms), but at the same time it appears to also be increasing the distance between voices, putting in jeopardy the achievement of the aims of the pluralist political system (in qualitative terms). In conclusion, we express doubts about the feasibility of the deliberative vision of democracy in the current virtual sphere.

scholarly journals Fake news: emotion, belief and reason in selective sharing in contexts of proximity

2019 ◽  
Vol 15 (3) ◽  
pp. 590-613 ◽  
Author(s):  
João Carlos Correia ◽  
Pedro Jerónimo ◽  
Anabela Gradim
Keyword(s):  
New Media ◽  
Selective Exposure ◽  
Geographical Proximity ◽  
Fake News ◽  
Online Groups ◽  
The Usa ◽  
Media Ecosystem ◽  
The Uk ◽  
Los Grupos ◽  
Traditional Communities

This text addresses the phenomenon of so-called fake news in the new media ecosystem, namely in contexts of increasing influence of populist discourse and action, such as Brazil, the UK, the USA, Italy, among others. It does so by way of some characteristics already implicit in the limited effects theory: a) fake news involves, in a specific way, the participation of its receivers in disseminating and sharing it; b) producers/consumers (prosumers) are involved in contexts of proximity that facilitate selective exposure, perception, and memorization; c) these phenomena are joined by another (selective sharing): the stakeholders share ideas they agree with more intensely. Information bubbles reinforce existing beliefs and predispositions; d) the phenomenon is increased in contexts of proximity, be it geographical proximity provided by regional media or thematic and ideological proximity shared in online groups. Despite this, there is a difference between contexts of proximity in traditional communities and mechanisms of propaganda that have a significant level of organization and ideological polarization.Este texto aborda o fenômeno das chamadas fake news no novo ecossistema midiático, nomeadamente em contextos de aumento da influência do discurso e das ações populistas, como Brasil, Reino Unido, EUA, Itália entre outros, através de algumas características, já implícitas na teoria dos efeitos limitados: a) as fake news implicam, de um modo especial, a participação dos seus receptores na sua divulgação e dispersão; b) os produtores/consumidores (prosumers) estão envolvidos em contextos de proximidade que facilitam a exposição, percepção, memorização seletivas; c) a estes fenômenos acrescenta-se outro (partilha seletiva): os stakeholders compartilham com mais intensidade as ideias com que estão de acordo. As bolhas de informação reforçam crenças e predisposições já existentes; d) o fenômeno agrava-se em contextos de proximidade, seja esta a proximidade geográfica e temática proporcionada nos media regionais, seja a proximidade temática e ideológica partilhadas nos grupos online. Apesar disso, há uma diferença liminar entre os contextos de proximidade em comunidades tradicionais e os mecanismos de propaganda com forte índice de organização e mobilização ideológica.Este texto aborda el fenómeno de las llamadas fake news en el nuevo ecosistema mediático, a saber, en contextos de creciente influencia del discurso y la acción populistas como Brasil, EE.UU., U.K., Italia, entre otros, mediante algunas características implícitas en la teoria de los efectos limitados: a) las fake news implican, de modo especial, la participación de sus receptores en su divulgación y dispersión; b) los productores / consumidores (prosumers) participan en contextos de proximidad que facilitan la exposición, la percepción y la memorización selectiva; c) a estos fenómenos se añade otro (compartición selectiva): los stakeholders, quienes comparten con más intensidad las ideas con que están de acuerdo. Las burbujas de información refuerzan creencias y predisposiciones ya existentes; d) el fenómeno se agrava en contextos de proximidad, es decir, la proximidad geográfica y temática proporcionada en los medios regionales, sea la proximidad temática y ideológica compartida en los grupos online. Apesar de ello, hay una diferencia entre los contextos de proximidad en comunidades tradicionales y los mecanismos de propaganda con fuerte índice de organización y movilización ideológica.

scholarly journals A New Similarity Measure for User-based Collaborative Filtering in Recommender Systems

2015 ◽  
Vol 14 (9) ◽  
pp. 6118-6128 ◽  
Author(s):  
T. Srikanth ◽  
M. Shashi
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Similarity Measure ◽  
Recommender System ◽  
Distance Measure ◽  
Current User ◽  
Challenging Problem ◽  
Popular Approach ◽  
Similarity Calculation

Collaborative filtering is a popular approach in recommender Systems that helps users in identifying the items they may like in a wagon of items. Finding similarity among users with the available item ratings so as to predict rating(s) for unseen item(s) based on the preferences of likeminded users for the current user is a challenging problem. Traditional measures like Cosine similarity and Pearson correlation’s correlation exhibit some drawbacks in similarity calculation. This paper presents a new similarity measure which improves the performance of Recommender System. Experimental results on MovieLens dataset show that our proposed distance measure improves the quality of prediction. We present clustering results as an extension to validate the effectiveness of our proposed method.

scholarly journals Syn Rec: A Prediction Technique using Collaborative Filtering and Synergy Score

2019 ◽  
Vol 8 (5S3) ◽  
pp. 457-463
Keyword(s):  
Social Interactions ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Effective Technique ◽  
Novel Technique ◽  
Trust Relation ◽  
Prediction Technique ◽  
User Trust

Recommender systems are techniques designed to produce personalized recommendations. Data sparsity, scalability cold start and quality of prediction are some of the problems faced by a recommender system. Traditional recommender systems consider that all the users are independent and identical, its an assumption which leads to a total ignorance of social interactions and trust among user. Trust relation among users ease the work of recommender systems to produce better quality of recommendations. In this paper, an effective technique is proposed using trust factor extracted with help of ratings given so that quality can be improved and better predictions can be done. A novel-technique has been proposed for recommender system using film-trust dataset and its effectiveness has been justified with the help of experiments.

Sign in / Sign up

Export Citation Format

Share Document