Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues ...and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by crosscompress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that crosscompress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-the-art baselines. MKR is also shown to be able to maintain satisfactory performance even if user-item interactions are sparse.
Information privacy refers to the desire of individuals to control or have some influence over data about themselves. Advances in information technology have raised concerns about information privacy ...and its impacts, and have motivated Information Systems researchers to explore information privacy issues, including technical solutions to address these concerns. In this paper, we inform researchers about the current state of information privacy research in IS through a critical analysis of the IS literature that considers information privacy as a key construct. The review of the literature reveals that information privacy is a multilevel concept, but rarely studied as such. We also find that information privacy research has been heavily reliant on studentbased and USA-centric samples, which results in findings of limited generalizability. Information privacy research focuses on explaining and predicting theoretical contributions, with few studies in journal articles focusing on design and action contributions. We recommend that future research should consider different levels of analysis as well as multilevel effects of information privacy. We illustrate this with a multilevel framework for information privacy concerns. We call for research on information privacy to use a broader diversity of sampling populations, and for more design and action information privacy research to be published in journal articles that can result in IT artifacts for protection or control of information privacy.
This book is a quick-paced guide that focuses on the core concepts and knowledge, in just enough words, to help aspiring as well as existing CISOs learn about vital tasks in an easy way. This book ...will take you from the basics of CISO and security leadership roles to complex key tasks necessary for becoming a global CISO.
While information privacy has been studied in multiple disciplines over the years, the advent of the information age has both elevated the importance of privacy in theory and practice, and increased ...the relevance of information privacy literature for Information Systems, which has taken a leading role in the theoretical and practical study of information privacy. There is an impressive body of literature on information privacy in IS, and the two Theory and Review articles in this issue of MIS Quarterly review this literature. By integrating these two articles, this paper evaluates the current state of the IS literature on information privacy (where are we now?) and identifies promising research directions for advancing IS research on information privacy (where should we go?). Additional thoughts on further expanding the information privacy research in IS by drawing on related disciplines to enable a multidisciplinary study of information privacy are discussed.
•PLS-PM has been subject to many improvements in last years.•Prior PLS guidelines have not covered the entire recent developments.•We explain how to perform and report an up-to-date empirical ...analysis with PLS.•We provide a fictive illustrative example on business value of social media.
Partial least squares path modeling (PLS-PM) is an estimator that has found widespread application for causal information systems (IS) research. Recently, the method has been subject to many improvements, such as consistent PLS (PLSc) for latent variable models, a bootstrap-based test for overall model fit, and the heterotrait-to-monotrait ratio of correlations for assessing discriminant validity. Scholars who would like to rigorously apply PLS-PM need updated guidelines for its use. This paper explains how to perform and report empirical analyses using PLS-PM including the latest enhancements, and illustrates its application with a fictive example on business value of social media.
Das moderne Bibliotheks- und Informationswesen setzt sich mit vielfältigen Anforderungen auseinander und entwickelt sich ständig weiter. Die Reihe Bibliotheks- und Informationspraxis greift neue ...Themen und Fragestellungen auf und will mit Informationen und Erfahrungen aus der Praxis dazu beitragen, Betriebsabläufe und Dienstleistungen von Bibliotheken und vergleichbaren Einrichtungen optimal zu gestalten. Die Reihe richtet sich an alle, die in Bibliotheken oder auf anderen Gebieten der Informationsvermittlung tätig sind.
Purpose - The purpose of this review is to draw out patterns of information seeking behavior of graduate students as described in the empirical research published from 1997 to the present.Design ...methodology approach - A systematic search of databases for studies on information behavior and graduate students was employed in order to retrieve studies for a systematic review. Common themes that emerged from the literature were synthesized into a discussion of behavior patterns. Additionally a study quality analysis was conducted for all retrieved studies using a critical appraisal checklist for library and information research.Findings - This review revealed that graduate students begin their research on the internet much like any other information seeker, consult their faculty advisors before other people, and use libraries in diverse ways depending on the discipline studied. Additionally differences were noted between international and home students, and doctoral and master's students.Practical implications - The findings of this review indicate that information behavior research conducted on graduate students should delineate between masters' and doctoral students. Further, the findings may inform both academic librarian and faculty practice as to how to assist students with their research by helping them to understand how students typically approach research and how other institutions address common issues with special populations, such as non-native speakers and distance learners.Originality value - No comprehensive review of information behavior studies, encompassing only the behaviors of graduate students has been conducted to date.
Based on literature from the domains of organization science, marketing, accounting, and management information systems, this review article examines the theoretical basis of the information overload ...discourse and presents an overview of the main definitions, situations, causes, effects, and countermeasures. It analyzes the contributions from the last 30 years to consolidate the existing research in a conceptual framework and to identify future research directions.
Information needs analysis Dorner, Daniel G; Gorman, G.E; Calvert, Philip J
2017., 2017, 2013, 2015., 2017-07-12
eBook, Book
If you want to provide an information service that truly fulfils your users' needs, this book is essential reading. Analysing and assessing the information needs of clients is key to the provision of ...effective service and appropriate collections in both face-to- face and virtual library services. The importance of information needs analysis is widely recognized by information professionals, but currently there is little substantive, detailed work in the professional literature devoted to this important topic. This new book is designed to fill that gap, by supporting practitioners in developing an information needs analysis strategy, and offering the necessary professional skills and techniques to do so. It will offer guidance to team leaders and senior managers in all areas of library work, especially those involved in collection management, service provision and web development, and is equally applicable to the needs of academic, public, government, commercial and other more specialized library and information services. The text adopts a hands-on, jargon-free approach, and includes relevant examples, case studies, reader activities and sources of further reading. Key areas covered include: * what is information needs analysis? * how is needs analysis conducted? * what are the varieties of needs analysis? * how are analyses evaluated and reported? Readership: The book will be essential reading for library and information practitioners, team leaders and senior managers. It will also be a core text on course reading lists in departments of library and information studies.