Knowledge Recommendation Systems with Machine Intelligence Algorithms: People and Innovations
This book takes readers on a journey into the world of knowledge recommendation and of systems of knowledge recommendation with machine intelligence algorithms. The book illustrates knowledge recommendation using two examples. The first is the recommendation of reviewers and experts who can evaluate manuscripts of scholarly articles or research and development project drafts. The second is innovation support, which involves bringing science and business together by recommending information that pertains to innovations, projects, prospective partners, experts, and conferences meaningfully.
The journey commences with a review of the literature on knowledge recommendation. The key objective of this chapter is to provide insights into knowledge recommendation's help in the construction of a recommender system of reviewers and experts and of Inventorum, a system that supports innovativeness. It also describes the selection of the algorithms that transform data into information and then into knowledge, which is then used in the information systems. The insights derive from a quantitative assessment of the subject of knowledge recommendation and thoughtful qualitative analysis of selected issues.
Subsequent chapter focuses on the recommendation of reviewers and experts for the evaluation of scholarly articles and research and development projects. Its main objective is to propose a recommendation system of reviewers and experts--specifically, its architecture and recommendation algorithm--by presenting case studies that concern the architecture and functions of each of its modules.
The next chapter focuses on the recommendation and sharing of information on innovations. Its main objective is to propose a recommendation system that supports innovativeness and information sharing. The purpose of such a system is to reduce the time necessary for users to find the right innovations, potential business partners, experts, and conferences.
Then, the following chapter presents details on the data acquisition and information extraction algorithms that are used in the reviewer and expert recommendation system and in Inventorum. The chapter's primary objectives are to present the algorithms' underlying details and to justify their selection among other possible solutions.
The next chapter describes the technical aspects of the reviewer and expert recommendation system and Inventorum. The primary objective of this chapter is to explain the systems' information architectures, technologies, and user interfaces. Much attention is paid to user interfaces--the only implementations of the systems that are visible to their users. Selected system usage statistics are also discussed. These pertain to the period between mid-2012, when the systems were made available to the public, and mid-2022.
The final chapter summarizes all considerations and offers suggestions for further action on knowledge recommendation. The systems and algorithms presented in this book are informed by contemporary solutions described in the literature, as well as including many compelling, novel, and original aspects. The development of science is an iterative process, and all astute changes are worthy of further study. Novelty and originality can be observed in the following areas: (i) the analysis and synthesis of knowledge recommendation accomplishments since 2000; (ii) the design, development, and implementation of two IT systems supplemented with content-based recommendation algorithms to apply knowledge recommendation in practice; and (ii) the development and practical application of selected heuristic and machine learning algorithms to create individuals' expertise profiles and enterprise innovation evaluations.
Customer Reviews
ThriftBooks® and the ThriftBooks® logo are registered trademarks of Thrift Books Global, LLC
