Search results

The purpose of this paper is to explore the effects of online recommender systems (RS) on three types of diversity: algorithmic recommendation diversity, perceived recommendation diversity and sales diversity. The analysis distinguishes different recommendation algorithms and shows whether user perceptions match the actual effects of RS on sales.

An online experiment was conducted using a realistic shop design, various recommendation algorithms and a representative consumer sample to ensure the generalizability of the findings.

Recommendation algorithms show a differential impact on sales diversity, but only collaborative filtering can lead to higher sales diversity. However, some of these effects are subject to how much information firms have about users’ preferences. The level of recommendation diversity perceived by users does not always reflect the factual diversity effects.

Recommendation and consumption patterns might differ for other types of products; future studies should replicate the study with search or credence goods. The authors also recommend that future research should move from taking a unidimensional measure for the assessment of diversity and employ multidimensional measures instead.

Online shops need to conduct a more comprehensive assessment of their RS’ effect on diversity, taking into account not only the effects on their sales distribution, but also on users’ perceptions and faith in the recommendation algorithm.

This study offers a framework for assessing different forms of diversity in online RS. It employs various recommendation algorithms and compares their impact using not just one but three different types of diversity measures. This helps explaining some of the contradictious findings from the previous literature.

This paper aims to shed light on the impact of personalized news media on the shared issue agenda that provides democracies with a set of topics that structure the public debate. The advent of personalized news media that use smart algorithms to tailor the news offer to the user challenges the established way of setting the agenda of such a common core of issues.

This paper tests the effects of personalized news use on perceived importance of these issues in the common core. In particular, the authors study whether personalized news use leads to a concentration at the top of the issue agenda or to a more diverse issue agenda with a long tail of topics.

Based on a cross-sectional survey of a representative population sample (n = 1,556), we find that personalized news use does not lead to a small common core in which few topics are discussed extensively, yet there is a relationship between personalized news use and a preference for less discussed topics. This is a result of a specific user profile of personalized news users: younger, more educated news users are more interested in topics at the fringes of the common core and also make more use of personalized news offers.

The results are discussed in the light of media diversity and recent advances in public sphere research.

This paper contributes to the ongoing debate about algorithmic news dissemination. While, currently, much attention is reserved for the role of platforms as information gatekeepers in relationship to the news media, maybe their ability to enable or hinder the audience in discovering and distributing news content is part of what really characterizes their influence on the market place of ideas.

The purpose of this paper is to apply cultivation theory to social network sites by investigating how Facebook uses cultivates users' ethnic diversity perceptions and attitudes.

The authors’ investigations include an online and offline survey study with 476 Facebook users and a follow-up experiment with 75 individuals.

The authors provide empirical support that Facebook use cultivates ethnic diversity perceptions and ethnic diversity-related attitudes. They show that Facebook use relates to perceptions of ethnic minorities that resemble the world on Facebook that is characterized by high ethnic diversity. The authors further demonstrate that the cultivation of ethnic diversity-related attitudes is mediated by diversity perceptions related to users' close social environment.

Future research should consider culturally and educationally diverse samples as well as longitudinal research designs to address external validity and causality issues.

Algorithms determining the content users are exposed should be thoughtfully curated to avoid attitudinal and ideological polarization.

Facebook can play an important role in positively shaping intergroup relations, thereby countering negative outgroup attitudes, social anxieties and radical right-wing parties.

The authors’ studies extend the scope of cultivation research by identifying a new media vehicle as a source of cultivation influences and shed light on the cultivation-based process of attitude change on social network sites.

The purpose of this paper is to present an up-to-date survey on the non-orthogonal multiple access (NOMA) technique with co-operative strategy, a fast-evolving fifth-generation (5 G) technology. NOMA is used for serving many mobile users, both in power and code domains. This paper considers the power-domain NOMA, which is now discussed as NOMA.

The first part of the paper discusses NOMA-based cooperative relay systems using different relay strategies over different channel models. In various research works, the analytical expressions of many performance metrics were derived, measured and simulated for better performance of the NOMA systems. In the second part, a brief introduction to diversity techniques is discussed. The multiple input and multiple output system merged with cooperative NOMA technology, and its future challenges were also presented in this part. In the third part, the paper surveys some new conceptions such as cognitive radio, index modulation multiple access, space-shift keying and reconfigurable intelligent surface that can be combined with NOMA systems for better performance.

The paper presents a brief survey of diverse research projects being carried out in the field of NOMA. The paper also surveyed two different relaying strategies that were implemented in cooperative NOMA over different channels and compared several performance parameters that were evaluated and derived in these implementations.

The paper provides a scope for recognizable future work and presents a brief idea of the new techniques that can be united with NOMA for better performance in wireless systems.

Improving the diversity of recommendation information has become one of the latest research hotspots to solve information cocoons. Aiming to achieve both high accuracy and diversity of recommender system, a hybrid method has been proposed in this paper. This study aims to discuss the aforementioned method.

This paper integrates latent Dirichlet allocation (LDA) model and locality-sensitive hashing (LSH) algorithm to design topic recommendation system. To measure the effectiveness of the method, this paper builds three-level categories of journal paper abstracts on the Web of Science platform as experimental data.

(1) The results illustrate that the diversity of recommended items has been significantly enhanced by leveraging hashing function to overcome information cocoons. (2) Integrating topic model and hashing algorithm, the diversity of recommender systems could be achieved without losing the accuracy of recommender systems in a certain degree of refined topic levels.

The hybrid recommendation algorithm developed in this paper can overcome the dilemma of high accuracy and low diversity. The method could ameliorate the recommendation in business and service industries to address the problems of information overload and information cocoons.

One challenge for tourism recommendation systems (TRSs) is the long-tail phenomenon of ratings or popularity among tourist products. This paper aims to improve the diversity and efficiency of TRSs utilizing the power-law distribution of long-tail data.

Using Sina Weibo check-in data for example, this paper demonstrates that the long-tail phenomenon exists in user travel behaviors and fits the long-tail travel data with power-law distribution. To solve data sparsity in the long-tail part and increase recommendation diversity of TRSs, the paper proposes a collaborative filtering (CF) recommendation algorithm combining with power-law distribution. Furthermore, by combining power-law distribution with locality sensitive hashing (LSH), the paper optimizes user similarity calculation to improve the calculation efficiency of TRSs.

The comparison experiments show that the proposed algorithm greatly improves the recommendation diversity and calculation efficiency while maintaining high precision and recall of recommendation, providing basis for further dynamic recommendation.

TRSs provide a better solution to the problem of information overload in the tourism field. However, based on the historical travel data over the whole population, most current TRSs tend to recommend hot and similar spots to users, lacking in diversity and failing to provide personalized recommendations. Meanwhile, the large high-dimensional sparse data in online social networks (OSNs) brings huge computational cost when calculating user similarity with traditional CF algorithms. In this paper, by integrating the power-law distribution of travel data and tourism recommendation technology, the authors’ work solves the problem existing in traditional TRSs that recommendation results are overly narrow and lack in serendipity, and provides users with a wider range of choices and hence improves user experience in TRSs. Meanwhile, utilizing locality sensitive hash functions, the authors’ work hashes users from high-dimensional vectors to one-dimensional integers and maps similar users into the same buckets, which realizes fast nearest neighbors search in high-dimensional space and solves the extreme sparsity problem of high dimensional travel data. Furthermore, applying the hashing results to user similarity calculation, the paper greatly reduces computational complexity and improves calculation efficiency of TRSs, which reduces the system load and enables TRSs to provide effective and timely recommendations for users.

North London Forensic Service is one of the largest NHS medium secure units in the country. Sarah Hill and Robert Halsey describe how the hospital held an inaugural Festival of Culture. With the well‐documented over‐representation of black and minority ethnic (BME) service users in secure hospitals, the event aimed to provide a forum for user involvement and celebration, as well as feeding into the wider race equality agenda. It also provided an opportunity to realise the benefits and value of therapeutic risk taking.

On a world basis, 15% of the population has a disability. Having a disability can result in a higher frequency of health-related information needs than other users might experience. The Web represents a widely used source for health information. People with disabilities, however, often encounter barriers during online searching, such as inaccessible information, poorly designed search user interfaces and lack of compatibility with assistive technology. Consequently, many users are potentially excluded from a range of information sources. Measures are therefore needed to remove these barriers to avoid health disparities that can result from unequal access to information. Public libraries have a social responsibility to include all user groups, and should aspire to make fully accessible services. A good tool in this context is the implementation of the universal design mind-set, where the purpose is to develop services that are available to all people. This chapter discusses how universal design can be a premise for equal access to health information and potentially reduce health disparities in the context of users with disabilities. Both library services and education of librarians will be addressed.

In order to enhance, consolidate and differentiate online services, developers are increasingly becoming concerned with issues of usability. Lists of design guidelines and evaluations of existing systems are extensive but attempts to place this applied science on a rigorous footing have largely failed. Despite legitimate advances in HCI (Human‐computer Interaction), no clear set of principles has emerged that is relevant to practitioners or vendors of online systems. Most previous studies have been concerned with designing the system for a ‘standard’ user. This paper will present some early findings of our work concerned with discriminating the relative effects of the cultural values of users and their organisational setting in configuring online systems.