Building User Trust in Recommendations via Fairness and Explanations

The purpose of this study is to compare presentation methods for use in the validation of the Trust in Selfdriving Vehicle Scale (TSDV), a questionnaire designed to assess user trust in self-driving cars. Previous studies have validated trust instruments using traditional videos wherein participants watch a scenario involving an automated system but there are strong concerns about external validity with this approach. We examined four presentation conditions: a flat screen monitor with a traditional video, a flat screen with a 2D 180 video, an Oculus Go VR headset with a 2D 180 video, and an Oculus Go with a 3D VR video. Participants watched eight video scenarios of a self-driving vehicle attempting a right-hand tum at a stop sign and rated their trust in the vehicle shown in the video after each scenario using the TSDV and rated telepresence for the viewing condition. We found a significant interaction between the mean TSDV scores for pedestrian collision and presentation condition. The TSDV mean in the Headset 2D 180 condition was significantly higher than the other three conditions. Additionally, when used to view the scenarios as 3D VR videos, the headset received significantly higher ratings of spatial presence compared to the condition using a flatscreen a 2D video; none of the remaining comparisons were statistically significant. Based on the results it is not recommended that the headset be used for short scenarios because the benefits do not outweigh the costs.

Download Full-text

Stream-based explainable recommendations via blockchain profiling

Integrated Computer-Aided Engineering ◽

10.3233/ica-210668 ◽

2021 ◽

pp. 1-17

Author(s):

Fátima Leal ◽

Bruno Veloso ◽

Benedita Malheiro ◽

Juan Carlos Burguillo ◽

Adriana E. Chis ◽

...

Keyword(s):

Historical Data ◽

Positive Impact ◽

Empirical Evaluation ◽

Recommendation Systems ◽

Use Cases ◽

Collaborative Filter ◽

Model Based ◽

Collaborative Recommendation ◽

Smart Contract ◽

User Trust

Explainable recommendations enable users to understand why certain items are suggested and, ultimately, nurture system transparency, trustworthiness, and confidence. Large crowdsourcing recommendation systems ought to crucially promote authenticity and transparency of recommendations. To address such challenge, this paper proposes the use of stream-based explainable recommendations via blockchain profiling. Our contribution relies on chained historical data to improve the quality and transparency of online collaborative recommendation filters – Memory-based and Model-based – using, as use cases, data streamed from two large tourism crowdsourcing platforms, namely Expedia and TripAdvisor. Building historical trust-based models of raters, our method is implemented as an external module and integrated with the collaborative filter through a post-recommendation component. The inter-user trust profiling history, traceability and authenticity are ensured by blockchain, since these profiles are stored as a smart contract in a private Ethereum network. Our empirical evaluation with HotelExpedia and Tripadvisor has consistently shown the positive impact of blockchain-based profiling on the quality (measured as recall) and transparency (determined via explanations) of recommendations.

Download Full-text

The Sharing Economy: Rhetoric and Reality

Annual Review of Sociology ◽

10.1146/annurev-soc-082620-031411 ◽

2021 ◽

Vol 47 (1) ◽

Author(s):

Juliet B. Schor ◽

Steven P. Vallas

Keyword(s):

Digital Technology ◽

Sharing Economy ◽

Environmental Benefits ◽

Annual Review ◽

Publication Date ◽

Racial Inequalities ◽

Carbon Footprints ◽

Transformative Potential ◽

Intellectual Foundations ◽

User Trust

The sharing economy is transforming economies around the world, entering markets for lodging, ride hailing, home services, and other sectors that previously lacked robust person-to-person alternatives. Its expansion has been contentious and its meanings polysemic. It launched with a utopian discourse promising economic, social, and environmental benefits, which critics have questioned. In this review, we discuss its origins and intellectual foundations, internal tensions, and appeal for users. We then turn to impacts, focusing on efforts to generate user trust through digital means, tendency to reconfigure and exacerbate class and racial inequalities, and failure to reduce carbon footprints. Though the transformative potential of the sharing economy has been limited by commercialization and more recently by the pandemic, its kernel insight—that digital technology can support logics of reciprocity—retains its relevance even now. Expected final online publication date for the Annual Review of Sociology, Volume 47 is July 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Download Full-text

A Relay Selection Algorithm Based on User Trust Degree for D2D Communications

10.21203/rs.3.rs-176476/v1 ◽

2021 ◽

Author(s):

Xiaobin Li ◽

Haoran Liu

Keyword(s):

Success Rate ◽

Social Relationship ◽

Relay Node ◽

D2d Communications ◽

Relay Nodes ◽

Trust Degree ◽

Relay Communication ◽

Relay Selection Algorithm ◽

User Trust

Abstract The emergence of 5G has promoted the rapid development of the Internet of Things(IOT), the dramatic increasing of mobile equipment has led to the increasing shortage of spectrum resources, D2D(Device-to-Device) communication technology is widely concerned for its ability to improve the utilization of spectrum resources. In order to expand the communication scope, relay nodes are introduced into D2D communications, as the third party of D2D relay communication, the quality of relay nodes directly affects the quality of communication process. In order to make more users willing to participate in relay communication, social relationship is introduced into D2D relay communication, However, as an explicit relationship between people, the function of social relationship in D2D communication is limited by the mobility of users and the variability of communication scenarios. In order to find a more reliable relay node and upgrade the connection success rate of D2D relay communication, implicit social relationship between the users need to be mined. Aiming at that, user trust degree (UTD) is established in this paper. By combining the explicit relationship which is called the social connectivity degree with the implicit social relationship called the interest similarity degree, and considering the user’s movement, a relay selection algorithm is presented to help sender find a relay node with a deeper user trust, which can increase the user’s willingness to participate in D2D relay communication and upgrade the success rate of communication connection, so this algorithm can ensure the security of the relay node and can improve the throughput performance. Simulation results show that this algorithm can increase the success rate of connection, improve the overall throughput of the system and improve the user's communication experience.

Download Full-text

Policy gaps and technological deficiencies in social networking environments: Implications for information sharing

SA Journal of Information Management ◽

10.4102/sajim.v15i1.542 ◽

2013 ◽

Vol 15 (1) ◽

Author(s):

Stephen M. Mutula

Keyword(s):

Social Networks ◽

Social Networking ◽

Business Education ◽

Social Networking Sites ◽

Internet Security ◽

Literature Survey ◽

Digital Networks ◽

Education Politics ◽

The Social ◽

User Trust

Background: With the growing adoption and acceptance of social networking, there are increased concerns about the violation of the users’ legitimate rights such as privacy, confidentiality, trust, security, safety, content ownership, content accuracy, integrity, access and accessibility to computer and digital networks amongst others.Objectives: The study sought to investigate the following research objectives to: (1) describe the types of social networks, (2) examine global penetration of the social networks, (3) outline the users’ legitimate rights that must be protected in the social networking sites (SNS), (4) determine the methods employed by SNS to protect the users’ legitimate rights and (5) identify the policy gaps and technological deficiencies in the protection of the users’ legitimate rights in the SNS.Method: A literature survey and content analysis of the SNS user policies were used to address objective four and objective five respectively.Results: The most actively used sites were Facebook and Twitter. Asian markets were leading in participation and in creating content than any other region. Business, education, politics and governance sectors were actively using social networking sites. Social networking sites relied upon user trust and internet security features which however, were inefficient and inadequate.Conclusion: Whilst SNS were impacting people of varying ages and of various professional persuasions, there were increased concerns about the violation and infringement of the users’ legitimate rights. Reliance on user trust and technological security features SNS to protect the users’ legitimate rights seemed ineffectual and inadequate.

Download Full-text

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

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.e1096.0785s319 ◽

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.

Download Full-text